203 results listed
Among the electrical machines the shaded pole
motors are the most difficult ones in terms of modeling and
analysis. This difficulty is arising from the non-uniform airgap and
unbalanced windings on its stator. Because ofthese the airgap flux
contains rich space harmonics, and this complicates the
mathematical modeling and simulation of these machines. On the
other hand, small size of these machines results in strong end
effects. Hence the 3-D modeling of magnetic field analysis poses an
important advantage. Therefore, in this presentation a 15 W, 4
pole shaded pole motor has been modelled in 3-D using Finite
Elements (FE) method to determine some important performance
parameters such as the airgap flux distribution and the saturation
effects in the motor laminations. In this process magnetic field
distribution have been obtained for three different case which are:
a) Main winding is excited but shading rings and rotor cage are
not excited
b) Shading rings are excited, but stator winding and rotor cage
are not excited
c) Both the stator winding and shading rings are excited, but
rotor cage is not excited
Finally, advantages accrued from such an analysis is discussedin
detail.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Adem Dalcalı
Mehmet Akbaba
Thyroid cancer is the type of cancer caused by the cells of the thyroid gland. This is less common than other types of cancer. If the correct diagnosis is made and appropriate treatment is given, the disease can be completely removed.
In this study, 3D models of thyroid cancer were modeled using DICOM images. As is known, dicom is the de-facto file standard in medical imaging, and these files contain many metadata. We used some of these meta-attributes to calculate the Hounsfield Unit. In addition, the pixel values are calculated according to the average attenuation of the tissue corresponding to a scale of -1024 to + 3071 on the Hounsfield scale. The DICOM images used in the study were obtained from real patients under the supervision of specialist doctors. Thyroid cancer tumors were modeled as 3D using the pixel values of Marching Cubes Algorithm.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ahmet Haşim Yurttakal
Hasan Erbay
T. İKİZCELİ
S. KARAÇAVUŞ
G. ÇINARER
We propose a new clustering ranking based multiobjective evolutionary algorithm. The algorithm uses decision maker’s preferences to reduce the search space and obtain a final set of preferred Pareto-optimal solutions. A new clustering ranking operator using Hierarchical Clustering on Principle Components (HCPC) and K-means methods is developed. We also develop a new crossover operator. The algorithm is implemented on several problems. The work is still in progress.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Erdi Dasdemir
B. Y. ÖZCAN
In any working environment, to perform visual tasks efficiently and accurately, adequate and appropriate lighting should be provided. The quantity and quality of illumination in any work place control by the type and duration of activity. The Illumination can be provided by daylight and artificial light together or separately. To calculate the illumination intensity at point C on the R plane from a light source at point A where the light distribution in space is known; besides the direct rays from point A to point C, the rays reflected from other planes must also be considered. By using this information, for inner work area a computer-aided modeling application has been developed by developing an algorithm that recommends the number and location of the selected luminaire considering the minimum illumination level recommendation specified in EN 12464-1 standard (which is European Standard that specifies lighting requirements for indoor work places). In this study, it was aimed to provide visual comfort in closed areas by focusing on only artificial light illumination.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Bayram Akgül
A.BİLİCİ
H. KUTUCU
The number of people with some kind of physical disabilities in the world is around 1 billion. The rate of people who need physiotherapy increases with the aging world population every passing day. Physiotherapy may not be completed with exercises made only in hospital. Therefore, patients should do the exercises given by the physiotherapist at home. The main problem here is that only 31% of the exercises performed by the patients are done correctly. Nowadays, in addition to traditional treatment methods there are studies on telerehabilitation to solve such problems. The aim of this study is to ensure that the shoulder rehabilitation exercises are performed at home by the patients and to provide physiotherapists with meaningful data about the exercises. In this study, Improved Shoulder Physiotherapy Application (ISPA) was presented using Microsoft Kinect 2 for shoulder rehabilitation exercises. ISPA is a hardware and software product that uses the joints on the patient's skeletal system. In the proposed system, the angular values are calculated using the joint points taken from Kinect 2 and the patients are simultaneously guided to do shoulder rehabilitation exercises correctly.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Burakhan Çubukçu
Uğur Yüzgeç
Raif Zileli
Ahu Zileli
Radio Frequency Identification (RFID) is not a new technology, but it is a new tool for improving performance of the manufacturing systems. There are many references to RFID implementation in the literature. Increase of the efficiency and speed of processes and improvement of information accuracy are some of the common benefits of RFID implementation. But there are many benefits not seen at first glance. Also there is a cost of RFID implementation as well as benefits. In this study, the objective is to carry out a detailed literature review in this field and to compare the studies in the literature for discussing similarities and differences. Thus, the study leads to discover new opportunities to extend research in this field.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Süleyman ERSÖZ
Ali Fırat İnal
Adnan AKTEPE
Ahmet Kürşad TÜRKER
Abstract: Fires, which are a phase of transition from outside the control to a certain time and place, cause social, economic, psychological and psycho-social loss of people. Due to the facts, fires can take place in the field of study of many disciplines. In order to strengthen the defense systems against the fires, both literary and scientific studies have been given to both social sciences and science and engineering.
The purpose of this study is; the distribution ratios of the postgraduate thesis studies done in the field of fire by searching the literature, the related fields and concentration rates shall be determined and to be assigned to the studies planned to be done in the future and to determine the areas that have not been studied.
In this study, 318 postgraduate theses obtained from the screening of the "fire" in the National Thesis Center of Higher Education Council (YÖK) were examined. The obtained data were interpreted using the IBM SPSS Statistics 22 program. Theses prepared mainly in master's degree are written in Turkish and English languages.
As a result, fires address a wide range of masses and neighborhoods, mostly theses on forestry and engineering sciences. Fire safety, forest fires, fire extinguishing systems, fire resistance of materials, fire detection and warning systems. It has been seen that working in the areas of fire intervention and extinguishing, fire terminology, fire behavior and classes, air (area / port) fires, fire extinguishing materials and technologies, fire training and application simulators, fire standards development are inadequate.
Özet: Belli bir zamanda ve mekanda kontrol dışına çıkan yanma olayının geçiş yaptığı bir faz olan yangınlar, insanlar üzerinde sosyal, ekonomik, psikolojik ve psiko-sosyal olarak kayıplara neden olmaktadır. Yangınlar, yapıları itibari ile birçok disiplinin çalışma alanında yer alabilmektedir. Yangınlara karşı savunma sistemlerini güçlendirmek amacıyla hem sosyal bilimlerden hem de ağırlıklı olarak fen ve mühendislik bilimlerinden literatüre bilimsel çalışma kazandırılmıştır.
Bu çalışmanın amacı; literatür taraması yapılarak yangın alanında yapılmış olan lisansüstü tez çalışmalarının dağılım oranları, ilgili alanlar ve yoğunlaşma oranları belirlenerek gelecekte yapılması planlanan çalışmalara önayak olmak ve çalışma yapılmamış alanları belirlemektir.
Bu çalışmada, “yangın” kelimesi Yüksek Öğretim Kurulu (YÖK) Ulusal Tez Merkezi’nden tarama yapılarak elde edilmiş olan 318 adet lisansüstü tez incelenmiştir. Elde edilen veriler, IBM SPSS Statistics 22 programı kullanılarak yorumlanmıştır. Yüksek lisans ağırlıklı olarak hazırlanmış olan tezler Türkçe ve İngilizce dilleriyle yazılmıştır.
Sonuç olarak, yangınlar geniş bir kitleye ve çevreye hitap etmekte olup, ağırlıklı olarak orman ve mühendislik bilimleri konularında tezler yazılmıştır. Yangın güvenliği, orman yangınları, yangın söndürme sistemleri, malzemelerin yangına karşı dayanımları, yangın algılama ve uyarı sistemleri konularında ağırlıklı olarak çalışmalar yapılmıştır. Yangına müdahale ve söndürme, yangın terminolojisi, yangın davranışları ve sınıfları, hava(alanı/limanı) yangınları, yangın söndürme maddeleri ve teknolojileri, yangın eğitimi ve uygulama similatörleri, yangın standartlarını geliştirilmesi konularında çalışmaların yetersiz olduğu görülmüştür.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mustafa Dogan
M. Ali Biberci
Sedat Cat
Forest fire is an important issue that damages
thousands of hectares of forest and all creatures inside it. In this
study we have developed an early fire detection system running on
low-cost, lightweight Raspberry Pi module integrated with an
infrared camera. The infrared camera acquires the live video of
the fields, then if a fire occurs, our software detects the fire by
taking both motion and color characteristics of a flames into
account. In our study, there exist two phases: first, motion
detection phase is applied to the view, if a motion is detected in the
view, then, color detection phase is applied to determine the
flames. Obtained results indicates that our fire detection system
can detect a forest fire clearly and smoothly without requiring any
external equipment and manual intervention.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Yasin Ortakcı
Emrullah Yildirim
Oğuzhan Dereci
A multiobjective bus transportation problem is studied in this research. Due to the complexity of the problem, a multiobjective evolutionary algorithmbased solution approach is developed. The solution approach is implemented on a real world problem. The preliminary results are promising. The research is still in progress.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Erdi Dasdemir
M.C. TESTIK
O.M. TESTIK
C. TUNCER SAKAR
In this paper, a measurement system composed of a single low-cost sensor and a shape estimation algorithm is proposed. Measurement mechanism consists of a low-cost infrared sensor, two servo motors and a microcontroller. This mechanism provides flexibility to scan at different heights and angle intervals. From the obtained scanning results, the features of the shapes are extracted and objects are classified accordingly.Classified objects are square prism, triangular prism, cylinder and pyramid. The extracted features are change in the width of the object depending on its height, having corner, corner angle and slope of the surface. The algorithm uses segmentation and fractured line fitting on the contour data of the shapes. The proposed algorithm is proved to be superior to our former method using RANSAC algorithm.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Keziban Şaloğlu
Arda Hoşafçı
Merve Birbilen
Alpay Baybörü
Ege Dinler
Ahmet Güneş
It has been widely assumed by the research community
that the network reconnaissance attacks in IPv6 networks are
unfeasible because they would take tremendous effort to perform
address scanning of 2^64 hosts in an IPv6 subnet. However, recent
research has revealed feasibility of these attacks by investigating a
number of native IPv6 networks. The research concluded that an
intelligent attacker could easily reduce the target search space by
predicting the network host addressing schemes when performing the
scanning. This indeed enhances security concerns and undermines the
chances of IPv6 being deployed. This paper overviews the IPv6
addressing strategies currently used and proposes a new replacement
strategy to mitigate reconnaissance attacks. The new strategy is
evaluated against some reconnaissance attack approaches. The
experimental results confirm the effectiveness and validation of the
new addressing strategy in terms of the mitigation of reconnaissance
attacks.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Shubair Abdullah
In this study a novel four dimensional (4D) chaotic system is introduced. To prove chaotic behavior of the system, time series and phase portraits are presented. A novel pseudo random number generator (PRNG) application of the chaotic system is realized to show the system is suitable for engineering applications like encryption and data hiding. In order to realize PRNG, the chaotic system is discretized with numerical methods. The next step is selection of different number of bits from different state variables obtained from the chaotic system. NIST 800-22 statistical tests, the highest international standard, are performed for the generated random numbers to prove the proposed PRNG has sufficient randomness and successful results are obtained.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Sezgin Kaçar
F. YALÇIN
B. ARICIOĞLU
A. AKGÜL
Measuring software maintainability is of vital
importance for improving software product quality. Using a
software quality model in the development life cycle, the quality of
the system can be continuously evaluated and improved to reduce
the maintenance cost. According to ISO/IEC 25010 Software
Quality Models Standard, the maintainability characteristic of
software product quality is composed of five sub characteristics;
modularity, modifiability, reusability, analyzability and
testability. This paper proposes a quality measurement model to
evaluate the maintainability of software classes in terms of their
reusability and modifiability characteristics in large-scale
software systems. The model is based on software properties that
are strongly related to reusability and modifiability, such as size,
complexity, cohesion, coupling, and inheritance. First, our method
categorizes metric values of software classes in the test system as
low, medium and high. This categorization is done based on the
average and median values for these metrics that are obtained
from reference software systems. Then, the proposed
measurement method uses the levels of the metrics to calculate the
reusability and modifiability scores of each class in the system. The
scores fall in one of the five categories; very low, low, medium,
high, and very high. The developers of the software system can
examine classes with low and very low scores and then refactor
them if necessary. This continuous evaluation and refactoring
during the development can increase the quality of the system and
reduce maintenance costs. We applied our model on two largescale
industrial mobile applications and discussed the results with
the development teams of the systems. We saw that our approach
could reasonably grade classes on their reusability and
modifiability characteristics.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Özlem Akalın
Feza Buzluca
The main objective of this research is design and realization of a wireless, secure, remote monitoring, control and feedback systemusing GSM technology for the patient health. In this study, CRUD (Create, Read, Update and Delete) operations can be performed on a Windows Communication Foundation (WCF) server using the developed mobile application andMySQL database. This system also includes a ripped QR scanner that prevents the browsers from entering QR code information because a crypto QR definition of the patient's identity number was developed. All the patients’ assay results and their radiological views are recorded along their reports. Patients who need regular follow-up can send their daily, weekly and monthly results to the physician using this application. In an instant panic situation, this system can communicate to the 112-emergency services and by the help of a push-to-talk button, system can send the patient's instant location to the phone number indicated by short message service (SMS). If 112-emergency departments support the connection, system can also send this location information automatically to 112-emergency systems. Transmitted data is archived and visualized both on a mobile phone and on a central server. The experiments on the proposed system gave promising results that is accurate in scanning, clear in monitoring, intelligent in decision making and reliable in communication.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Hilal Kaya
F.V. ÇELEBİ
T. YILMAZ
M.B. MURATOĞLU
S. ERARSLAN
As known, web crawlers are programs that automatically browse on the web. Their purpose is to automatically navigate pages, saving source links that have target links, marking pages according to the words in those links, saving, indexing, collecting data to bring personalized ads, etc. Although the web crawlering algorithm is simple, it has various difficulties with respect to the existing pages on the web and the resulting amount of data. The semantic web works on generating computer readable data and is intended to overcome the quantity of data generated. Ontologies represent a pivoting source for semantic web applications. Ontology based crawlers scan the web by focusing on related web pages along with a specific ontology based on area ontology. The main advantage of the ontology based web crawlers over other crawlers is that no Conformance Feedback or Training Procedure is required to move wisely. In addition, both the number of documents and the more effective and efficient results will be obtained during the scanning process. As a result; The main advantage of an ontology based web crawler over other web crawlers is that it does not require intelligent, efficient operation and relevant feedback. In this study, traditional and ontology based web crawlers approaches and its infrastructure are examined. In addition, differences between ontology based web crawlers and traditional web crawlers have been investigated. A brief of literature summary on the subject has been included.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Yasemin Gültepe
A.B. ÖNCÜL
E. ALTINTAŞ
F. UĞUR
Nowadays, the content used on the internet is increasingly provided by mobile technologies. Mobile communication, which started with only voice transmission and then continued to undergo a major transformation with messages, mails, images and videos. As the amount of data accessed from mobile media increases day by day, researchers continue to be interested in the network access area, network access speed, data download/upload speed, and data security areas in mobile technologies. In this study, we explained First Generation (1G), Second Generation (2G), Third Generation (3G), Forth Generation (4G) and Fifth Generation (5G). Finally compered them briefly.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Muhammet Çakmak
Zafer Albayrak
Neural networks (NNs) is used to solve many engineering and science problem. Generally, feedforward architecture is preferred and gradient-based learning algorithms are extensively operated to tune all parameters of NN iteratively. This training method is a conventional one, but training process takes a long time due to the slowness of gradient-based learning algorithms. This slowness has been an important drawback in their applications. To overcome this disadvantage, extreme learning machine (ELM) concept introduced to science community in near past. Essentially, ELM is a data-driven learning algorithm for single-hidden layer feedforward neural networks (SLFNs). This algorithm provides extremely fast learning speed. In this study, performance of SLFNs learned by ELM algorithm is investigated on the problem of highly nonlinear dynamic system identification. As a result of studies on selected benchmark problems in the literature, it has been seen that ELM may not provide a good generalization success due to randomly chosen the number of hidden nodes and weight parameters for inputs in SLFN. For both the training and the test data set, very poor results have been obtained and observed surprisingly during the above-mentioned studies. Here, a simple heuristic approach has been proposed in this study in order to eliminate this bad situation and the findings obtained with this approach are discussed. Based on the obtained experimental results, it has been shown that the proposed approach determines the optimal the number of hidden nodes and a reasonable random selection of input weights required for a good generalization performance.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Cihan Karakuzu
Uğur Yüzgeç
The air transport has become the widely used option for the travel. The time saving and comfortable conditions encourage people to choose the airlines. The fierce competition and attractive market forced companies develop different pricing strategies to gain a competitive advantage. The ticket price, the charges for the luggage weight, special good carrying and seat selection are just many of the strategies developed by airline companies. The reaction of the customer is usually to choose the most economic option. Airline companies need a decision support system that will simulate the customer behavior against their strategies considering the strategies of their competitors. In this research we develop a simulation methodology for the domestic market in which we include different prices imposed by the airline companies and the buying preferences of the customers with the assumption that customer always choose the ticket with the minimum price. The airline companies then can analyze the consequences of their price strategies and expected strategies of their competitors.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ahmet Yucekaya
Researchers have been studying to understand and classify biological signals for better diagnose diseases and developing assistive technologies. These technologies are sometimes making it possible to communicate in ALS (Amyotrophic lateral sclerosis) patients, sometimes possible to use our computer, faster and more efficient without using our muscular systems. The steady state visual evoked potential (SSVEP) approach currently provides the high performance and reliable communication for the implementation of these technologies. Performance is usually measured by Information Transfer Rate (ITR) and the most important factor affecting ITR is signal window length.
In the presented paper a SSVEP based BCI (Brain Computer Interface) speller application is introduced and system performance is analyzed for different signal window lengths in experiments. The BCI speller has six box which has six letters in each box on the screen. The six letters in the selected box are distributed as one letter each box after the first selection by application. With the second selection, the letter which desired is displayed on the screen. The application contains Latin letters as well as Turkish letters. Experiments are performed on 3 healthy subjects. Subjects try to choose letter by focusing boxes which has flickering different frequencies. The minimum energy combination (MEC) method is applied to EEG segments that are different length in order to detect SSVEPs. The highest ITR value of 77.55 bit/min is obtained for subject 1 with 2 s signal window length. High accuracy and more useful a BCI system observed when system signal window length set 3 s.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
E. ERKAN
Mehmet Akbaba
In this study, geometric methods used to obtain
rectified photographs that will form a base for drawings of
building facades are examined. Mathematical models are
presented by informing briefly about the methods evaluated.
The subject is exemplified by a test study. In the test study,
firstly, the behavior of the related methods on the created artificial
image was examined and the applications on the real photographic
sets of the models obtained with different types and different
cameras were performed.
The obtained results were evaluated statistically and various
conclusions were drawn and the suggestions were made for those
who want to apply the method and want to do the study in this
subject.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
A.SOYCAN
M.SOYCAN
Data mining and machine learning algorithms are utilized in order to discover meaningful information by thorough analysis of dataset. They are used in multi-disciplinary field. Wart is caused by the human papillomavirus. It inhibits body growth by activating ecdysone steroid production systematically. There are several treatment methods for this illness. These methods focused on offering a solution for people. In this framework, a study on the analysis of the best two wart treatment methods, Cryotherapy and Immunotherapy, is carried out. The first one of these datasets collected by applying the cryotherapy method consists of seven features. The second dataset collected by applying the immunotherapy method consists of eight features. Fuzzy Rule, Naive Bayes and Random Forest based models are designed in order to evaluate the effectiveness of these methods in wart treatment. The performances of these algorithms are judged within the frame of Accuracy and Sensitivity performance measures.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Kemal Akyol
Abdulkadir Karaci
Yasemin Gültepe
Self-Adaptive Systems (SASs) are systems that monitor and adapt their behavior autonomously in response to dynamic state and environmental conditions. A typical architecture of SASs is constituted of a Manager (Autonomic) Sub-System that controls a Managed Sub-System. A well known architecture of the Autonomic Sub-System is the MAPE-K model. It is constituted of the Monitor, the Analysis, the Plan, and the Execution stages and the Knowledge Base. The major challenge of SAS is that all the stages are subject to uncertainty. Consequently, it has a significant impact on the adaptation quality. Currently, uncertainty is considered as a first-class concern in constructing Self-Adaptive Systems. However, few detailed works have been done about uncertainty in MAPE-K Control Loop. This paper intends to survey the most recent research on uncertainty in the MAPE-K using FRAMESELF architecture which is a detailed MAPE-K loop. Precisely, we present the sources of uncertainty in each process of the FRAMESELF model. In addition, we focus on missedsources of that we believe the community should consider.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
S. OUARETH
S. BOULEHOUACHE
S. MAZOUZI
Retinoblastoma is a childhood cancer grows in retina. Although it could be treated in early stages, it can spread to nervous system and also other parts of the body and eventually may cause death in this situation. The prediction of survivability attracts a considerable interest and has been studied at different types of cancers, like breast, lung, colon and thyroid in literature by applying data mining methods. Data used in this study is obtained from The Surveillance, Epidemiology, and End Results (SEER) program which is an authorized data repository of cancer statistics. In our study, the survivability for retinoblastoma is predicted on SEER dataset consisting of 1258 patients by using data mining algorithms (support vector machines, logistic regression, multi-layer perceptron, naïve bayes, random forest and decision trees). Two strategies for imbalanced data which are over-sampling (synthetic minority over-sampling - SMOTE) and under-sampling are used. Results are analyzed and compared with the ones studied in other cancer types.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Gülistan Özdemir Özdoğan
Hilal Kaya
Baha Şen
I. CANKAYA
With the rapid development of computer science, today many universities in their academic departments are using various educational software systems to provide class-related resources, manage the learning activities, and organize the contents of courses. Although these software systems vary widely, the most needed one has tended to be the learning management system. Learning management systems have gained popularity in recent years in conducting online academic programs more commonly to develop and support off-campus education. Learning management systems make it easier for students and teachers to share resources and communicate with each other. As technology influx has expanded alternatives for educational software solutions in distance education organizations, the need for usability testing for learning management systems has increased for better learning experience. This study determined to measure how students perceive the usability of a cloud-based learning management system that is widely used by students and faculty members in many universities.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Hakan Özcan
B. G. EMİROĞLU
In this study, a voice encryption application is realized by using a four dimensional (4D) chaotic system with single parameter. The main purpose of use of a single parameter chaotic system is reduction of computational load in order to run the voice encryption application on low performance hardware. Since the chaotic system is four dimensional, the system has four state variables and for every state variable different values of initial conditions can be used. This makes the key space length sufficiently long. In the application, the state variables are obtained with Runge-Kutta (RK4) method. The voice encryption is realized by XORing the obtained state variables with the voice data. The security performance of the voice encryption is proved by comparing the encrypted and original voice data in both time and frequency domain.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Sezgin Kaçar
F. YALÇIN
B. ARICIOĞLU
A. AKGÜL
The Student Model is dedicated to personalize and
to adapt the learning. With pedagogical strategy self-switching,
the monitoring of the student model is the cornerstone of
pedagogical strategy adapting. To efficiently achieve the
monitoring operation, we propose a fine grained WildCAT based
Observable Bayesian Student Model. On one side, it represents
how the user relates to the concepts of the knowledge structure
using the pedagogical component. On the other side, it integrates
concept level sensors that results in an Observable Networks’
Sensors. This permits to ensure the collect of the instant student
knowledge level. In addition, it uses a publish/subscribe
communication model to notify the Student Cognitive changes to
the monitoring component. On this side, the Monitoring
Component subscribe as a receiver of appropriate cognitive
changes. To experiment the likelihood and the usefulness of this
model, a framework is constructed using WildCAT on a Student
Cognitive Level.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
S. BOULEHOUACHE
Selma Ouareth
Ramdane Maamri
General fundamentals of mathematics itself, geometric patterns, and tasks of mechanics field, physics, natural science and technology have the deep roots of developing of the theory of curves. The curves were studied in different ways and methods. At this stage of computerization, you can plot any curve. In this paper, an algorithm for finding the extreme points of a curve in explicit form in both polar and Cartesian coordinates is described.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Rita Nauryzbayeva
Nowadays, the effect of social networks on people's lives is quite high. This situation gives rise to the density of information exist over social networks. That is why, analyzing the spreading pattern of information on social networks is an important issue today. The aim of this study is to technically review the background of information spreading, especially the fundamentals of rumor spreading and analyze the well-known methods on SNs. As a result, this article provides an important background for those, who works on the information spreading over SNs.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Burcu SAYİN
Serap Şahin
Measurement and control of environmental variables
such as temperature and relative humidity have a significant
application in science, industry, agriculture, healthcare and
controlling and automation technological processes. These two
environmental parameters are critical to continuously measure
and keep in desired ranges for real working conditions. This paper
aims to obtain the values of temperature and relative humidity via
wireless communication which is one of the most common
communication methods. The transmission of the data was
performed using RF receiver and RF transmitter modules. The
SHT11 sensor was used to measure both temperature and relative
humidity of the environment for the same point. This application
is realized and successfully tested in this study. The transfer of
data to the computer is successfully provided. Obtained results can
be used and applied to increase a system’s life in automation and
control technologies.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
H. BAKIR
Ümit Ağbulut
Muhammet Sinan Başarslan
In this paper we introduce an algorithm for
constructing approximate Voronoi diagram of a set of pairwise
disjoint arcs on a plane. The arcs are represented by parametric
curves. On the first step, we discretize curves using the proposed
adaptive method. Then, we construct Voronoi diagram of the
discretized objects and process the obtained Voronoi graph such
that redundant edges and cells are removed. Finally, the edges of
the processed graph are approximated by Bezier curves giving the
parametric representation of the final Voronoi diagram. The total
complexity of the described algorithm is O(n log n) in average.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Dmytro Kotsur
Vasyl Tereshchenko
The reverse logistics processes, i.e. collecting the
recycling materials, have a major cost for the recycling companies.
Collecting the recycling materials with the shortest route,
recycling companies can reduce the transportation cost. In this
study, we introduce a case study on a travelling salesman problem
encountered in an accumulator recycling company. We introduce
a mathematical model and an artificial bee colony algorithm to
reach the shortest route of the distribution network in the case.
Scenario analysis for the performance evaluation of the proposed
bee colony algorithm has been made on high-scale benchmark
problems in the literature. (see, travelling salesman problems in
OR Library, http://people.brunel.ac.uk/~mastjjb/jeb/info.html).
It has been shown that the algorithm is efficient for an industrial
application, it is able to reach near-optimal solutions in reasonable
solution time.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Oğuzhan KORKMAZ
Çağrı Sel
SQL Injection vulnerability is one of the most important and prevalent vulnerabilities. It is important to make pen tests to develop secure applications. In this paper, we perform a penetration test and implement SQL Injection attack. The results are tested in the demonstration platform testphp.vulnweb.com. By this work, we aim to emphasize the importance of secure systems and make people aware of that. Otherwise, existence of such vulnerabilities in a system can bring to bad results and bad situations. Then, we make an automated tool for SQL Injection penetration test with the aim to finalize the test quickly and to provide a convenience for pen testers.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
A.MURZAEVA
Sedat Akleylek
In the past two decades, human action
recognition has been among the most challenging tasks in
the field of computer vision. Recently, extracting accurate
and cost-efficient skeleton information became available
thanks to the cutting edge deep learning algorithms and
low-cost depth sensors. In this paper, we propose a novel
framework to recognize human actions using 3D skeleton
information. The main components of the framework are
pose representation and encoding. Assuming that human
skeleton can be represented by spatiotemporal poses, we
define a pose descriptor consists of three elements. The first
element contains the normalized coordinates of the raw
skeleton joints information. The second element contains
the temporal displacement information relative to a
predefined temporal offset and the third element keeps the
displacement information pertinent to the previous
timestamp in the temporal resolution. The final descriptor
of the skeleton sequences is the concatenation of frame-wis e
descriptors. To avoid the problems regarding high
dimensionality, PCA is applied on the descriptors. The
resulted descriptors are encoded with Fisher Vector (FV)
representation before they get trained with an Extreme
Learning Machine (ELM).
The performance of the proposed framework is evaluated
by three public benchmark datasets. The proposed method
achieved competitive results compared to the other methods
in the literature.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Saeid Agahian
F.NEGIN
Cemal Kose
Today, breast cancer is the most common non-skin
cancer affecting women. Because mammograms do not give clear
findings until a certain age for the diagnosis of breast cancer,
ultrasounds are applied as an imaging technique. Then, according
to the findings in ultrasounds, imaging techniques like
mammograms or other detection techniques are applied. Patient
will be required mammograms if ultrasound findings look
suspicious or the patient is above a certain age. Patients will have
biopsy according to the mammogram findings and other risk
factor values. Each step in this process will lead the patient
anxiety, and expenditures. But the results of not performing these
processes will lead one case of cancer and leads the patient more
serious problems and expenditures. Therefore, every step of the
process is vital importance to predict the most accurate
information available. Computer-aided diagnostics (CADx)
models are helpful in working on a huge number of variables, and
related the risk factors and risk estimation together. Many CADx
models provide support for experts by evaluating the
mammographic findings and are used by radiologists to increase
the detection rate of missed cancer patients. In this study,
application of well-known data mining techniques is done on a
public breast cancer data set. As a novelty, Migrating Birds
Optimization (MBO) which is a fairly new metaheuristic is also
applied on the same data set and the results are discussed. It is
shown empirically that the MBO meta-heuristic presents
preferable performance to the well-known data mining
techniques.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Muyesaier AIHAITI
Ali Alkaya
- A complete knowledge of Tibiofemoral (TF) joint
kinematics is essential in understanding the function of he al thy
and pathological joint. The objective of the present study is to
determine the six degrees’ translations and rotations of TF joi nt
during 10-minute in-vivo creep loading while standing using Dual
Fluoroscopic (DF) images. A computational model was develope d
for the kinematics analysis of the right knee of a 24-year old
female participant with healthy legs. Magnetic Resonance
Imaging (MRI) was obtained for the unloaded joint and used for
reconstruction of the knee joint model, including soft tissues. A
high-resolution DF system was used to image the distal femur
and proximal tibia during 10 minutes of standing. Braces were
used to minimize flexions and rotations of the TF joint during the
measurement. Translations and rotations of TF joint as functions
of time were determined from the DF images with the JointTrack
software. Coordinate systems were established for 3D
model of distal femur and proximal tibia anatomically.
Rotational and translational orientations of the TF joint were
calculated based on these coordinate systems. The maximum
relative rotations of the distal femur with respect to the proxi mal
tibia during 10-minute creep with approximately half body
weight were 1.167 degrees in varus-valgus rotation, 4.334 degrees
in internal-external rotation, and 0.541 degrees in flexion. The
results showed a vertical displacement of 0.234 mm with very
small rotations during 10-minute standing. Finite element
modeling of the joint is in progress.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Sabri Uzuner
M.L. Rodriguez
Leping Li
Serdar Kucuk
In this study, we consider an intelligent placement of
electrical materials such as luminaire, oven, dishwasher, washing
machine, refrigerator, TV-phone socket, etc. for the appropriate
places for drawing electrical installation diagrams. Electrical
installation project drawings of the buildings are prepared on the
architectural projects which are prepared by the architects. When
the electrical materials as symbols are placed on the project, with
the type of building, the type and size of the inner area, the purpose
of use and most importantly other descriptive symbol drawings
(named as “architectural furnishing symbols”) are taken into
consideration. For example, if an oven symbol is found in a
drawing part, then it means that this part most likely is a kitchen.
Although any of one architectural furnishing has dozens of
different symbols, they are basically similar to each other with
small differences. In our application, "architectural furnishing
symbols" are introduced to the system using artificial neural
networks, then “electrical material symbols” are automatically
placed according to the furnishing symbols detected at the site.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Bayram Akgül
H. KUTUCU
When the evolution of human being is analyzed, it is
seen that almost all activities are developed by trial and error
method. However, it is also known that these methods are not
productive and cause much time loss. Therefore, various methods
have been developed to solve the problems encountered in
different situations. As to educational activities, they mainly have
quite different qualities than others. In general, education and
training is done collectively by bringing people at the same level
together. Although we accept individuals who are brought
together of the same nature, this is not a very correct approach in
many cases. In fact, people have different levels of knowledge and
experience. Scientific studies have even shown that each
individual's learning method differs. Therefore, whatever method
is used, it is difficult to obtain the desired efficiency in collective
learning. In this study, a new learning method based on interactive
learning and knowledge based learning systems has been
developed with reference to the personal differences that emerged
during learning. With this method, first, the strong and weak
aspects of the person related to the subject to be learned are
determined and then the interactive learning is provided with the
designed interface. In this learning method where learning is
performed at different periods with asynchronous learning
techniques, creating permanent learning by taking individual
differences into account is the ultimate goal.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Gokhan Atali
D.KARAYEL
S.S.OZKAN
Turkish Sign Language (TSL), which is a mother tongue of hearing-impaired individuals, is a natural language. Expression patterns used in this language are carried out within the settings of the rules of the language. In this study, a textual interpretation system from Turkish to TSL was developed. Within this context, a corpus consists of 230 sentences was composed. Beside the sentences included in the corpus, also the interpretation of the sentences entered by the user interactively can be made. The rules of both languages were taken
into consideration in the interpretation of the sentences. Firstly, Turkish sentences were parsed to words and then, morphological analyses of the sentences were performed withZe mberek. As a result of the morphological analyses, root/stem of the words and the affixes attached to the words were determined.
Some affixes are not considered as necessary in TSL. Therefore, the affixes which are not considered as necessary should be determined and ignored within the interpretation. Moreover, various rules were constructed for the transformation by considering the results of the morphological analysis rules and usage samples. Descriptions related to 489 signs and 6 non-manual signs were made in order to express the sentences included in the corpus in TSL. The number of the signs out of 489 were as follows: 81 static, 408 dynamic, 334 single, 155 repetitive, 6 sign union and 2 word combination. 6 non-manual signs were as fol l ows; baş önde (head ahead)" bö", baş yukarı da (he ad up) "by", kaş yükseltme (eyebrow raising) "ky", kaş i ndi rme (e yebrow l owe ri ng) "ki", past aspect "di" (past tense suffix) and continuous aspect "yor" (present continuous tense suffix). Usage numbers of the nonmanual
signs were as follows: 66 "bö", 12 "by", 38 "ky", 40 "ki", 94 "di" and 31 "yor".
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mehmet Fatih Karaca
Şafak Bayır
Rapid developments in information and
communication technologies over the last few decades have led to
cyberspace becoming a part of our daily lives. Protecting cyber
space from harmful activities has become a critical point of action
for policy makers around the globe as societies, governments and
businesses become increasingly dependent on the internet. So, it
is important to prepare and develop a national cyber security
strategy (NCSS) for the management of information and
communication systems, ensuring citizen safety, and protecting
critical infrastructures. In this study, the concepts of cyber
security were mentioned and the national cyber security
strategies of some of the leading were examined. In the last part,
the implementation stages of a good national cyber security
strategy were focused on.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Cihan Ataç
Sedat Akleylek
Co-authorship networks provide a broad view to the connectivity properties of scholars, together with patterns of knowledge diffusion in scientific society. Network science provides a substantial framework for discovering the dynamics of these interactions those are defined by co-authoring a paper together. We constructed a complex network consisting of co-authorship links between authors, using the data retrieved from Web of Science Core Collection. Date retrieved is limited to 67248 publications addressed from Turkey in engineering field, including the timespan between 1975 and 2018. Analysis performed through this massive dataset resulted a complex network of 78883 nodes (authors) and 194232 edges (co-authorship links). Authors exhibit an average degree (neighbor) of 4.925, which increases to 6.687 in weighted analysis. Network exhibits an invincible clustering coefficient of ~0.8, while the average path length is close to 18. Together with the power-law consistent degree distribution that labels the network as scale-free, we also presentedtop “most central” authors of this network with respect to betweenness, closeness and eigenvector centrality measures, each defining the “importance” of an author in different aspects.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
İlker TÜRKER
Rafet Durgut
Oğuz Findik
In the empirical sciences, experiments are carried out in the laboratory so that the results may be applied in other locations where the conditions are the same as in the laboratory. Hence, it should be possible to establish certain causal statements in the laboratory, which can be transported to real-world environment. In the present paper, experiments were carried out on wireless sensor networks in the laboratory and the results were transported to environments where experimentation is impossible. The tool Tetrad was used to arrive at the causal directed acyclic graph for the wireless sensor network in the laboratory. The concepts of selection diagram, the principle of transportability and the condition for failure of transportability are discussed. The applicability of transportation algorithm for typical environment and also the failure of the same are analyzed. Simulations are carried out using the simCausal package in R programming and the validity of the probability expressions transported by the transportation algorithm are shown to be correct.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Karthik P. C.
E.POOVAMMAL
In this paper, performance of joint transmit and receive antenna selection in cooperative MIMO channels is investigated over Rayleigh fading environments. A cooperative MIMO communication scenario in which all of the terminals are equipped with multiple antennas is considered where source want to transmit data to the destination with the help of the relay. The techniques developed in literature to combat error propagation effect in digital relaying networks such as cooperative maximal ratio combining (C-MRC), virtual noise (VN) based detection and selective relaying (SR) are exploited in this study to obtain new antenna selection criteria for cooperative MIMO systems. Only one antenna is selected and activated at each of the three terminals in a manner to minimize the end-to-end bit error rate (BER) of the overall system. This approach eliminates the requirement of space-time signaling in system design and reduces the complexity and cost by minimizing the number of the required RF chains in the network. Unlike most of the studies in the literature, we assume that the direct link between source and destination exists. Numerical results have shown that a diversity order of (nS + nR) * nD can be achieved for VN and SR based transmissions where nS, nR, and nD are the total number of the antennas at the source, relay and destination, respectively. Among the considered schemes, the best performance is obtained in case of SR based system model.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ozgur Ozdemir
Mass appraisal of real estate is a complex problem
because of multiple criteria. Developed technologic methods
provide a solution by transforming into the form of simple and
easy. Multiple Regression Analysis (MRA) is frequently used in
academic and practice studies in the world and our country. New
method quest continues according to recent advances in computer
technology. Artificial Neural Network (ANN) which is one of the
artificial intelligence methods should investigate in order to use in
the valuation because it can imitate human brain.
The aim of this study is to estimate with ANN method the value
of real estate. The study data consisted of the market samples
concerning the plots in Centre Neighborhood of Konya. The data
of the 558 samples were collected as main headings in the form of
Legal, Physical, Locational and Neighborhood Features. The data
set was separated for 70% training and 30% test. The market
values of the plots were forecasted by using 70% training data with
ANN and MRA methods and compared by testing 30% data in
both methods. According to the results, it has seemed that success
of ANN method is higher than the success of MRA method.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Fatma Bunyan Unel
Şükran Yalpır
Today, the role of software testing in the life cycle of
software development has significantly increased. The process of
software testing implementation include: planning, designing,
creating, executing and supporting of the tests. At the same time,
there was a transition from direct testing to quality assurance,
covering the software development cycle in general.
In this paper, we proposed the directions for solving problems in
software testing. Solving of this problems requires knowledge,
logical reasoning, the experience of an engineer for quality control
software. Using an artificial intelligence methods in a software
testing allowed us to found the ways for executing of tests
classification and optimization.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Yuliya Kozina
N. Volkova
O. Osadchiy
The main purpose of the semantic web is to develop standards and technologies that will enable well-defined and linked information and services to be easily computer-readable and computer-understandable in the web environment. Linked data is one of the approaches used to acquire meaningful integrity by gathering data-related data collections by creating semantic links between the web pages that make up the content of the semantic web. Linked data is based on RDF (Resource Description Framework) technology. RDF is a data model that provides space-independent formal semantics with respect to chart resources. In a linked data application, the most important decision point is how to access the linked data. Linked data crawler is a program that explores linked data in web by tracking RDF links. In this work, DBLP (Database Systems and Logic Programming) data set is used as a source of Linked Data. DBLP gradually expanded toward all fields of computer science. An example will be presented related to pageRank sorting of RDF resources in the DBLP dataset. As a result; the search area has shrunk and search results have improved.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Yasemin Gültepe
Kemal Akyol
Abdulkadir Karaci
In this study, Artificial Atom Algorithm, which is a new meta-heuristic algorithm approach, have been used to calculate the threshold value which is frequently performed in image processing applications. The entropy-based method has been adopted for the target function which is common in the meta-heuristic algorithms. For this aim, Shannon entropy and a new entropy method, Fractional Order Entropy, have been used. It is seen on standard test images that the Artificial Atom Algorithm can be applied to image processing applications. In addition, the results of the application were supported by comparing the values produced by certain parameters of fractional entropy with the values produced by Shannon Entropy.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Burak Açma
Emine Çiftçi
Burhan Selcuk
Linear Ordering Problem is an NP-hard
combinatorial optimization problem. Several metaheuristic
algorithms (Tabu Search, Memetic Algorithm, Variable
Neighborhood Search, Simulated Annealing, Scatter Search,
Greedy randomized adaptive search procedure) present for the
linear ordering problem in literature for finding high quality
solutions. This paper presents an Artificial Bee Colony algorithm
for solving the linear ordering problem. The results are compared
between the other implementations of metaheuristics and
Artificial Bee Colony algorithm can produce good solutionsfor the
linear ordering problem instances.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Emrullah Sonuc
In this study, four artificial neural network models
are designed for the daily meal demand in places where mass
meals are produced. It is aimed to avoid the cost of overproduction
in the places where mass meals are produced and at the same time
to prevent the ending of the meals with less food production. In the
study, the number of people eating food was estimated by using the
data obtained from the university dining hall. Feed-forward
neural network, function fitting neural network, cascade-forward
neural network, and multilayer perceptron neural network
models and linear regression methods are used in the developed
prediction models. The best results were obtained with multilayer
perceptron with 93% accuracy and cascade-forward neural
network models with 85% accuracy
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Derya YERGÖK
C.T. GÜVEN
Mehmet Acı
New and less energy consuming methods are developed to reduce the increasing heating costs day by day. Heat transfer method is one of the most commonly used methods for heating an environment. The amount of heat required to heat an environment in a heat transfer technique is found by the amount of heat lost from the environment. In this study, artificial neural networks were used for estimating the monthly heat demand for the heating needs of a greenhouse in Elazığ province with 2017 meteorological and spatial data. The amount of heating has been tried to be estimated using the MATLAB program with the lowest error. Heating Degree-Day (HDD) values and latitude, longitude and altitude data were used for analyzes to be made in the artificial neural network model. It has been estimated that the heat requirement for the heating of the greenhouse is lower than the heat requirement for the heat transfer method in the designed artificial neural network model.The artificial neural networks model has been found to be a useful method for studying the heating of greenhouses.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Özlem Alpay
Ebubekir Erdem
Text classification, which is a sub-field of the natural language processing, is utilized for the solutions of problems in various areas. One of these areas is the author detection in written texts. When a person writes a text, he or she makes several marks due to the spelling characteristics. Author detection or recognition means that ownership of the text is questioned by comparing these spelling features. Different features belonging to the author can be extracted from texts and many comparisons can be made. In this study, author recognition was performed using bigram, trigram and quadrigram frequency property with the Naïve Bayesian approach for decision making. 120 different Turkish books written by 20 Turkish authors in different distributions were studied. Initially, the authors' bigram, trigram and quadrigram frequency properties were extracted from the books. Then, the comparison of the n-grams performances attained by Naïve Bayesian method is examined through this paper.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Samet Kaya
A. GUNES
Recognition and interpretation of human activities
are very interesting and hot topics that are frequently studied in
the field of computer vision. Especially with the advent and
development of the Microsoft Kinect depth sensors, the expansion
of the study fieldhas gained momentum in the positive direction.
Thanks to RGBD cameras, which also provide depth information
in addition to the RGB image, researchers benefit from many
advantages in terms of privacy, accuracy and precision. In this
study, automatic segmentation of repeated 3D human activity is
proposed. A public dataset containing the repeated action
sequences are recorded using the RGBD camera. The action
sequence in this dataset includes similar and different action
information. In order to identify and label each action in sequence,
it is necessary to perform the segmentation process. To be able to
perform a successful segmentation process, the data must be preprocessed
to remove noise. For this purpose, a total variation
based noise removal method is used. Human action recognition
and detailed error analysis can be performed through the
segments derived from the output of this work.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Rafet Durgut
C. OZCAN
Oğuz Findik
The blockchain technology is a hot topic and a new technology in recent years. It is not only an underlying technology for many applications like Bitcoin application, but also it is a kind of thinking including cognitive and mental processing and understanding for artificial intelligence and human enhancement. All data or services are digitized. So, this leads to deal with big data. It is a challenge to deal with big data from the perspective of performance, scalability, availability and privacy in centralized systems. Blockchain is applicable to big data and brings different perspective how to process, store, read and write data. Also, the aim of this paper is to show that better solutions are possible in a decentralized way. Even the technology is in its early stages, the blockchain technology will be in future due to its superior features. Therefore, it is better to adopt this technology as soon as possible to place in future. This paper gives a brief about how the blockchain could approach to big data and analyzes existing information regarding the challenges of big data from the side of the blockchain.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Senem Kaplan
Serap Şahin
İngiltere’nin AB’ye girişi sancılı olmuştu. İki kez Fransa tarafından veto edildikten sonra 1973’te,
o zamanki adıyla Avrupa Ekonomik Topluluğu’na üye olan İngiltere, içine girdiği andan itibaren
en kritik konularda Birlik için hep sorun oldu. Ekonomik bütünleşme için son derece önemli iki
konu olan Schengen Alanı ile Avro Alanının dışında kalmayı tercih eden İngiltere, siyasi
konularda da sık sık Almanya-Fransa eksenindeki ülkelerle ters düştü. İngiltere’nin AB’den çıkış
tartışmalarının hız kazanması Aralık 2009’da yürürlüğe giren Lizbon Antlaşması’ndan sonradır.
Brexit, Birleşik Krallık’ın Avrupa Birliği ile ilişkilerinde en önemli dönüm noktası olmuştur. Bu
nedenle, Brexit’e giden süreci, nedenlerini ve sonuçlarını incelemek konunun daha iyi
anlaşılmasını sağlayacaktır. Referandum, arkasında bölünmüş bir ülke bırakmıştır. Özellikle
İskoçya ve Kuzey İrlanda'da gençler ve kentsel nüfus AB'de kalmayı tercih ederken, büyük
metropol alanlarının dışında yaşayan daha yaşlı ve az eğitimli nüfus İngiltere’nin AB’den
ayrılması yönünde oy kullanmıştır. Referandum sonrasında Avrupa’nın geri kalanı şok içinde ve güvensiz bir durumda kalmıştır. Kimin kazandığının tam olarak belli olmadığı bir referandumun ardından, Brexit’in sonucunda da ne olacağı tam olarak belli değildir. Referandum neticesinde İngiltere tarafından elde edilen siyasi pozisyon, Birleşik Krallık'ın ve belki de AB'nin, dünya siyasetinde egemenlik iddiasını bırakması sonucunu doğurabilir. Bu çalışmanın amacı; AB üyeliğinin devamının İngiltere açısından ekonomik getirileri açıkça ortadayken Brexit nasıl gerçekleşmiştir? Birleşik Krallık’ın AB’ye tam üyeliğine ilişkin alternatifleri nelerdir? Antlaşmasız bir ayrılığın taraflar açısından sonuçları neler olabilir? sorularının yanıtını bulmaktır.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ali AYATA
In large scale software applications, bug
localization is a difficult and costly process. Many issues or bugs
may be reported at both development and maintenance phase of
software development lifecycle. Hence, it is important for
developers to discover the location of the bug. In general, source
codes and bug reports are used for identifying bug location with
the help of Information Retrieval (IR) techniques. In this paper,
we present an IR-based bug localization approach named
BugSTAiR that uses structured information of source files, source
code history, bug reports and bug similarity data if exists. To do
best of our knowledge it is the first system developed for
JavaScript source files. The experimental results show that
accuracy of the system is promising (~%30 on Top 1) on file level
bug localization.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mustafa Ersahin
Semih Utku
Deniz Kilinc
With the increasing of data size in recent years, processing and analyzing of the big data has become difficult. Therefore, interest in this area has also gone up. In 2006, Geoffrey Hinton, the pioneers in the field of machine learning, developed a deep learning model at the University of Toronto. The basis of the deep learning model is based on the use of a large number of hidden layers in artificial neural networks. Previously, increasing the number of hidden layers in artificial neural networks, deepening the network, was not preferred because it caused complexity in calculation processes. Deep learning that provides a nonlinear transformation of the big data can model complex relationships with a multi-layered structure. As this model provides more comprehensive attribute learning, the classification becomes more successful. For this study, Convolutional Neural Network (CNN) model is represented for the large-scale image classification. CNN is the most widely used deep learning model in feature learning, recognition, and classification. In order to obtain a powerful image classifier, there should be large amount training data. Because of that, data augmentation techniques are used to boost the performance of the deep networks. In this study, data was increased using image augmentation methods that create artificial training examples through different ways of processing techniques such as adding noise, rotating, shifting, shearing, and resizing. The data that consists of car photos taken from the rear and are provided from the literature are separated into 40 categories. Finally, the classification performances using different deep learning CNN models such as AlexNet, VGG16, and VGG19 are evaluated and experimental results are reported.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Kübra Uyar
Erkan Ülker
The purpose of the study is to efficient classification of Cardiotocography (CTG) Data Set from UCI Irvine Machine Learning Repository with Extreme Learning Machine (ELM) method. CTG Data Set has 2126 different fetal CTG signal recordings comprised of 23 real features. Data is two target class description that are based on fetal hearth rate and morphology pattern. The classification criteria based on morphology pattern (A-SUSP) is used in this study to serve better decision options to operators. Accuracy of ELM method will be compared with previous works in literature.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ayşenur Uzun
E. ÇAPA KIZILTAŞ
E. YILMAZ
In this paper, Padé approximation based on truncated total least squares method (P-TTLS) is defined as a nonparametric method to estimate the nonparametric regression model and to obtain an optimal estimation, determination of the truncation level is illustrated. Here, three selection method are used for choosing the truncation level which are GCV, AICc and REML respectively. To compare and interpreting the performances of the criteria, a simulation study is carried out and results are presented.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
D. Aydin
E. YILMAZ
In the last decade, technological innovations and a changing economic and regulatory environment have resulted in a renewed interest for distributed generation. In most cases distributed generation systems are represented in the form of autonomous energy centers, since the connection of distributed generation to centralized electrical networks is being limited to the lack or imperfection of the regulatory framework and effective means of controlling technological regimes. In this paper is carried out a comparative analysis of the operation principles and options for connecting to the distribution network of autonomous power plants using different types of distributed energy resources. While connection of distributed energy resources to distribution network, one of the main tasks is distribution of loads between generating capacities. An algorithm for solving this problem is also presented in the paper.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
A. ARIFJANOV
R. ZAKHIDOV
Nuri Almagrani Ali Almagrahİ
In recent years, with the growing popularity of smartphone, near field communication (NFC) based mobile
applications commenced to be used in public transportation. This development provides an opportunity to collect additional and province independent data about passengers and so it allows development of better data mining applications. The present study is conducted to compare classification algorithms on public transport data collected by NFC-based mobile phone ticketing application for the first time. In this paper, five popular classification algorithms have been considered to investigate various target attributes in terms of accuracy rates: Naive Bayes,
C4.5 Decision Tree, Random Forest, Support Vector Machines, and k-Nearest Neighbor. The study presented in this paper can be useful to provide decision support for public transportation.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ufuk Demir Alan
D. BİRANT
By the development of technology, image
classification algorithms frequently use to identify land use and
land cover of any area in remote sensing studies. Due to the
diversity and complexity of land cover on the wetland areas, it is
quite difficult to obtain accurate results related to the earth's
surface. The main purpose of this research is to compare the
overall accuracies of object based and pixel based image
classification methods. Arslantaş Dam Lake is structured on
Ceyhan River for irrigation, flood control and electricity
generation in Osmaniye province. In this study, Landsat-8 LDCM
satellite image of Aslantaş Dam Lake with spatial resolution of
30m, acquired on December 29, 2017 was used. Firstly, image was
classified by pixel based classification with support vector
machines (SVM) method. After that, image was reclassified by
object based classification with K-nearest neighbour (KNN)
method. Five classes namely lake, agricultural area, soil,
vegetation and building area were determined by using these
algorithms. Ground truth data were gathered from aerial
photographs, available maps and personal informations. Finally,
overall accuracies of these methods were compared. It is observed
from the classification results that object based KNN method
provide higher accuracy than the other classification method.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mustafa Hayri Kesikoğlu
Sevim YASEMİN ÇİÇEKLİ
Tolga Kaynak
This study aims to compare Turkey’s computer
engineering undergraduate programs to compare with “European
Union country” programs. In this way, it is aimed to contribute to
the improvement of the programs in our country. Additionally,
Erasmus programs of the universities in our country are aimed at
reducing the adjustment problems experienced by the students
going to European Union countries. All these operations are
performed with data mining algorithms.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
S. KILICER
Ruya Samli
In parallel with the development of the technology, the storage of the data more easily and quickly and the faster processing on the stored data can make an important contribution to the creation and analysis of networks of coexistence. Complex networking plays an important role in analyzing and revealing common characteristics and structures of connected clusters depending on various characteristics. In this study, a network of association between male tennis player in the Australian Open, the French Open, the US Open and the Wimbledon tennis tournaments, known as four major international tennis tournaments between 2000 and 2017, has been established.While each tennis player is defined as a node in the network of associations created, the competitions of the tennis players with each other are defined as the links connecting these nodes. The universal principles of complex networks such as scale-free, small world, clustering have been examined. Furthermore, through Gephi software, the structural characteristics of networks are visualized by using the data obtained from this association network. As a result of the study, it was seen that the networks among the tennis players struggling in the related tournaments were carrying real world network characteristics and that the data obtained from these networks can be used for network analysis.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Oğuz Findik
Emrah Özkaynak
Today, with the development of information technologies, studies on the evaluation of relations between people, objects and events to put it simply relations between creatures and facts have taken place among general topics. As the data related to the relationships between creatures and facts continue to increase and become storable together with developing technology, new methods are being developed for analyzing and evaluating these data. There are both semantic and structural relations within the obtained data stacks. Complex network analysis is one of the most common methods used to reach semantic relationships as a result of analyzing and evaluating these relations. In this study, a network was formed among the teams who competed in the UEFA Europe League between 2004-2017 by using the data of football competitions played after the groups. As a result of the evaluation, different categories such as last 32, last 16, quarter final, semi final and final matches are analyzed and the similarities of the networks to the real world networks are compared with the data obtained about the network structures. As a result of the study, it is observed that the teams that compete in the UEFA Europe League are similar to the real world networks.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
E. E. SULAK
H. Yılmaz
Emrah Özkaynak
In this study, two recent nature-inspired optimization
algorithms Salp Swarm Algorithm (SSA) and Ant Lion
Optimization (ALO) were introduced and a comparison with two
algorithms was realized. For these comparisons, constrained
optimization test problems were solved with these algorithms.
The effects of the penalty coefficients on the solution of
constrained problems were also studied. Results were submitted.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Pakize Erdogmus
Muhammed Gocer
Ebru Dudak
Nurcan Ozkan
Existing networking systems are hardware-based and
rely on inflexible architectures. In recent years, Software defined
networks (SDNs) has emerged as a new paradigm for nextgeneration
networks. SDNs are proposed to separate control plane
and data forwarding plane in the traditional networks to reduce
the increasing complexity of the network equipment. This
separation enables a programmable and flexible hardware
infrastructure via OpenFlow protocol and provides great
opportunities in terms of reducing operating cost, simplifying
network management tasks, gathering network statistics, and
accelerating innovation.
Logging is a structure that records the events of a system and the
users in the system. With logging operations, the actions making
by each device can be recorded. Especially in places where more
than one person connects to the internet such as hotels, cafes,
restaurants, student dorms and companies etc., it is necessary to
monitor and take logs of the events. Already, by the Law No 5651,
to combat certain crimes committed on the internet, it has become
obligatory to take logs to institutions or people who provide
collective internet services.
In this paper, a logging and monitoring system has been designed
and implemented. For logging and monitoring proceses, sFlow,
OpenFlow, Floodlight, Open vSwitch, node.js, and MySQL
technologies have been used. sFlow technology is used to monitor
the networks. sFlow standard gives complete visibility into the use
of networks enabling performance optimization, usage, and
defense against threats. OpenFlow is a protocol used in SDN
environments to enable the SDN controller to interact with the
data forwarding plane of the network devices. Floodlight software
is used by SDN controller for network operations. Open vSwitch
software which enables to handle the traffic loads is installed at
Raspberry Pi 3 hardware. The obtained results show that the
proposed system can take the flowtable records, transfer the
records to node.js via sFlow, and save the records to MySQL via
node.js. Finally, the network traffic is successfully monitored and
logged.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Bilal Babayigit
S. KARAKAYA
In this study, we created probability maps of
earthquake occurrences using Kriging method from Geostatistical
techniques with the Geographic Information Systems (GIS) in the
NAFZ (western, central, eastern). Geostatistical techniques had
both the capability of producing a prediction surface and provide
some measure of the certainty or accuracy of the predictions.
Kriging method depended on mathematical and statistical models.
Kriging was an interpolation that can be exact or smoothed
depending on the measurement error model. Kriging used for
statistical models that allow a variety of output surfaces including
probability. We used an instrumental catalog for Ms≥4.0
magnitude between 1900-2017 period.
Additionally, Kriging method fitted a mathematical function to a
specified number of earthquakes or all earthquakes within a
specified radius, to determine the output value for each region. We
have used
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Tuğba Türker
Yusuf BAYRAK
Network security has become one of the most
important issues in today's world. Along with the widespread use
of the Internet, corporations and companies share important
confidential information over networks. The protection of this
information, which may lead to serious harm if third-parties have
access to it, is vital. Moreover, with increased cyber attacks,
corporate or private networks are under serious threat. Increasing
the security of networks is of vital importance, because corporate
networks are especially critical to national security. In this study,
necessary protocols, equipment, technologies and necessary
precautions have been investigated in order to make data
communication in virtual private networks, which is one of the
most used network technologies today, to be done safely.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Seyit Böge
Ali Öztürk
Direction of gravity is a natural way of orienting
oneself in an unknown environment. Human beings do thi s wi th
equilibrioception. It would be beneficial to estimate the directi on
of gravity from a single image for many tasks such as
autonomous driving and augmented reality where the knowledge
of location of the agent is very important.
Extracting this knowledge from an image usually requires a
reference to be identified. For example, a traffic light can give
away the direction of gravity as it has to be placed in an
environment in a specific way with respect to the gravity.
Reference-based approaches require a lot of hand modeling for
solving the problem. When there are a lot of images with ground
truth data is available, one can model these references implici tly
using machine learning techniques.
We propose to use a set of images along with readings from
inertial magnetic unit (IMU) taken from a smart camera
observing an indoor environment. This data includes a lot of
images as well as ground truth labels for gravity direction
extracted from the IMU readings. The data is fed to a
convolutional deep neural network to estimate the gravity
directions formulated as regression as well as classification
problem. We show that this modeling works quite well with a fe w
hundred images when we formulate the estimation as a
classification problem. The details of the networks trained and
the results obtained are presented in depth. Further research
with more images but with less accurate ground truth data is
underway.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Betül Z. Türkkol Abuzarifa
Yakup Genç
The technology to calculate the fire and failure rate of the glass from the glass line in the glass factories that are manufactured is facilitated by the technology. Waste and mistakes must be identified and improved for product and service quality. One of the methods used to calculate these rates is Failure Mode Effect Analysis (FMEA). The FMEA technique is a very powerful numerical analysis technique for preventing errors before they occur. In this study, a sample application of the Process FMEA study, one of the FMEA variants, was carried out for the glass sector. The problem to be addressed is defined as determining the error and waste rates of the glass from the thermopane line in a quality oriented business with the Perfect Scanner machine to reduce these ratios and increase the productivity. Types of errors obtained from Perfect Scanner data; the questionnaire survey conducted in the production area and the feedback from the customers were collected in 5 issues. These; scratches, stains (fingerprints), coating failure, stains between laminating glass, air bubbles. We determined and implemented the changes that will improve the process to eliminate or reduce the reasons for the types of errors encountered. Thus, by measuring the performance of the thermopane line of this company which has an important place in the glass industry, the negativity of the performance in production is minimized and customer satisfaction is increased.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Adnan AKTEPE
Behiye Beste ŞAKAR
Umut Aydın
Ayşe Nur Hayyaoğlu
Süleyman ERSÖZ
- Although the number of lanes of roads in residential
cities is constant, the number of vehicle in traffic is increasing
every year. This causes traffic congestion at certain times, such as
before and after work hours. Thus, instead of traditional methods,
intelligent systems have become a necessity to control traffic lights.
For this problem, there are traffic signaling applications
developed with using image processing and artificial intelligence
techniques in literature. In this study, an application was
developed to provide more detailed data for traffic signaling
applications. Used Faster R-CNN model was trained and tested in
Karabük and trained model detected 76 of 79 vehicles in 23 test
frames and achieved 96% success.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
murat GENÇER
Nesrin Aydın Atasoy
Data collection, data retention and analysis are
becoming more and more important every day because of the fact
that technology is involved almost all our life. The processing and
analysis of the data can become more difficult with increasing
precision.
In three-dimensional surface modeling, due to the increase in
sensitivity and data size depending on the surface state and extent
of the surface, collecting and processing the data may become
difficult. As a solution to this situation, we can see that
Computational Geometry is used extensively. Computational
Geometry derives intermediate interpolations by taking the start
and end data as references instead of keeping each data separately.
In this way, it is possible to model by determining intermediate
values based on the mentioned reference points.
There are various methods in Computational Geometry such as
intersection detection, point position and triangulation. According
to the needs, a solution way can be produced by various geometric
computations. In our study, "Delaunay Triangulation" which is
the most used type of triangulation methods will be examined.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mustafa Aksin
Emrullah Demiral
Ismail Rakıp Karas
This study aims to simulate the actual working environment of the excavator type work machine and to train the operator the driving movements on a robot excavator. In this study, the design, manufacture and control of training simulator was realized for the purpose of obtaining driving ability of excavator on simulator before actual machine use was started. In our country, the training of the work machine operators is carried out on real machines.
For use in work, small size excavator robot which has two palettes and composed of boom, stick and bucket and able to control these organs with hydraulic flow such as real machine was manufactured. The simulation of hydraulic components to real machine movements is provided and with the designed drive circuit, the movement of the pallets and the return of the upper structure were performed with wireless control over the RF channel.Control functions of the excavator robot resemble the use of real machine driving. A camera was placed in the driver's cabin on the robot and the camera images were transferred to the video glasses system of the instructor outside the robot working area. The purpose of using video glasses is to simulate actual use. The trainer has the impression that he is using the excavator completely inside the robot independent of the outside space.
Three different experimental studies were carried out using the excavator robot. Experimental environment has been prepared so that the operator who will receive the training can perform these applications. These are: 1) Canal digging, 2) Ramp up and lowering from ramp, 3) Using the excavator as a crane.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Oguz Cevik
İbrahim Çayıroğlu
This paper describes an antenna design that is suitable for microwave imaging and radar applications. Microwave imaging technology has attracted many interests nowadays and it has been used in a variety of applications such as: non-destructive testing and evaluation, through-the-wall imaging, concealed weapon detection at security check points, structural health monitoring and medical imaging. Similarly, radar-based applications have been popular in many areas. The basic idea of using microwave imaging and radar systems is to transmit electromagnetic waves from a transmitting antenna to the target material and receive the scattered waves at a receiving antenna. For this reason, the choice of the antenna plays an important role for the system. There is a need for compact sized, low cost and high efficiency antennas which can radiate ultra-wideband signal to transmit short pulses. Furthermore, these antennas should have similarly end-fire radiation pattern to obtain good resolution of the produced images for using both in imaging systems and radar applications. In this study, firstly a conventional compact-sized rectangular patch antenna is designed. Then, various optimizations are performed on that antenna by using High Frequency Structural Simulator (HFSS) software. After that, this antenna is fabricated and tested with Vector Network Analyzer. The fabricated antenna has a simulated and measured bandwidth from 4 GHz to 9 GHz for |S11|<10 dB, respectively. The return loss results show that the good impedance matching is obtained through the working frequency band. The proposed antenna has nearly stable end-fire radiation patterns throughout the frequency range. All of the results exhibit that the designed antenna can be used in high range radar applications and is a good candidate for microwave imaging applications.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ali Recai Çelik
M.Bahattin Kurt
Selcuk Helhel
Easy availability and cheapness of microcontrollers, intelligent sensors and wireless technology equipments have paved the way for different engineering and industrial applications of control systems. Conventional closed greenhouses, which are one of these spaces, have been converted into high-tech plant production units. A low-cost greenhouse automation system which can be monitored at computer environment by virtue of an interface created in Matlab GUI programming language is proposed in this study. To this end, a model greenhouse system taking into consideration temperature, air humidity, light intensity and soil’s physical quantities as input parameters was made. The output parameters used in the model greenhouse were heating, ventilation, irrigation and lighting control. It was determined that the system created by comparing with conventional control systems, was more advantageous in terms of usage, monitoring and programming. Ease of use was provided to the user due to control and monitoring of physical quantities in the greenhouse by virtue of the Matlab GUI interface. The most prominent characteristic of the offered system is that it can easily be used for other agriculture and poultry stockbreeding areas by making small changes in the software infrastructure.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ferzan Katircioglu
Lifting hooks are the components that ensure reliable and economical lifting and transport of loads. By selecting the shapes, dimensions and appropriate materials to be used, a reliable and economical lifting hook is obtained. In this study, stress analyzes of lifting hooks were carried out primarily with two different analytical approaches. Then, modeling of the hook was made in computer environment and the finite element analysis was done in the computer environment. The analysis results and standardized values for different loads are compared under the same conditions. The study shows that computer-aided finite element analysis can be applied reliably and economically in studying the stress states of lifting hooks.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Alp Ozdemir
Yusuf Aytaç Onur
Metamaterials are man-made artificial materials that are not a natural material but rather have different electromagnetic properties. One of the features mostly studied in recent years is that it nearly absorbs all incoming electromagnetic waves. These features make it possible to invisibility against remote sensing systems. Thus, the radar cross-section area (RCA) representing the radar visibility can be reduced by covering the target plane with metamaterial. As a first step in this work, the unit cell of the metamaterial, which has a resonance effect, is designed to achieve high absorption at 6.0 GHz. Then, using the unit cell's scalability feature for this metamaterial, two more-unit cells with resonance effect at 5.0 GHz and 7.0 GHz were designed, respectively. Subsequently, all three were brought next to each other and super-cell structure was introduced. The structure obtained shows 94.62% absorption at 5.08 GHz, 99.95% absorption at 5.98 GHz and 90.42% absorption at 7.02 GHz, respectively, in the C band region (4-8 GHz).
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Barış Doruk Güngör
Serdar Kucuk
M. Kasap
Various coating methods are used in the development of organic textures. The MALDI method is one of the most important one amongst the others. Three-axis robotic spraying devices are frequently used in tissue engineering. The inboard joints of the robot manipulator are designed with prismatic joints. The last two joints are designed with two revolute joints which are composed of a two-axes spherical wrist. With this design, complex surfaces can be reached with any orientation angle.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Barış Doruk Güngör
Serdar Kucuk
M. Kasap
Unmanned Aerial Vehicles (UAVs), are air aircraft that can fly autonomously without human control or that can be controlled by a ground station. In parallel with the technological developments of the present day, it has been observed that the use of UAVs is also greatly increased. In this context, new working areas were needed together with the widespread use of UAVs. As a result of the researches, the autonomous control works was seen to become the foreground. Within the scope of this study, an autonomous landing system has been implemented for UAVs. The images taken with the help of the camera located at the bottom of the UAV are subjected to image processing techniques on the Linux based operating system to determine the landing track. In the scope of the study, the landing station detected is a circle with a "H" in the middle. The letter "H" on the landing station can be changed color according to the location. For example; the landing station can be red in football ground, can be blue in empty ground. Images taken from the camera are subject to the image processing technique. First of all, the image is removed from noises. Then, it is classified according to the “H” letter color on landing station. Pixels which are same with "H" letter are changed to white color, others changed to black color. So that, it is determined how many shaped has been found. The shapes are ordered according to their size and compared with the landing station. If the similarity rate is over 75%, the target is determined.Once the determination, the altitude of UAV will gradually decrease and the image acquisition and measurement process will be repeated until it reaches a desired position. After arriving at the desired position (Eg z<=20 cm), the UAV performs descent by stopping engines.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Çağrı Çiçekdemir
H. UCGUN
Uğur Yüzgeç
M. KESLER
One of the purposes of video surveillance systems is
to detect anomalies which are unexpected situations at a certain
location or at a frame. Anomalies can be related to motion or
appearance according to its spatial position. In this paper, we
propose an anomaly detection system based on spatio-temporal
features. Features from Accelerated Segment Test (FAST) is used
for detection of corners location. Optical Flow magnitude and
orientation of these points is used as spatio-temporal features. A
grid is
to the frames to neutralize the effect of proximity to the camera.
Normal patterns are clustered with an unsupervised neural
network so called Self-Organizing Maps (SOM). In test videos if
extracted features cannot model with normal clusters, associated
grid cell will be marked as anomaly
Keywords - Video Surveillance, Anomaly Detection, Features
from Accelerated Segment Test (FAST), Optical Flow, SelfOrganizing
Maps (SOM)
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Kadriye Öz
Ismail Rakıp Karas
In the literature, machine learning algorithms are
frequently used in detecting anomalies in network traffic and in
building intrusion detection systems. Deep learning is a subfield of
machine learning that trains a computer-based system to perform
humanitarian tasks, such as disease diagnosis, speech recognition,
image recognition, fraud detection, and making predictions. In the
experimental study, NSL-KDD dataset was used for evaluating the
performance of the proposed deep learning based DDoS detection
model. NLS-KDD dataset contains normal network traffic and 23
different DDoS attacks that consists of 41 features. In the
experimental study two different experiments are carried out.
Firstly, the proposed deep neural network detected the Dos attacks
with 0.988 classification accuracy. In the second experiment, the
number of features of NSL-KDD is reduced to 24 by examining the
previous feature reduction research on NSL-KDD dataset. The
proposed deep neural network classified the all cyber-attacks with
0.984 classification accuracy. The 10-fold cross validation is used
for all experiments. As a result, the proposed deep learning based
DDoS detection achieved good performance.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ayşegül Sungur Ünal
Mehmet Hacibeyoglu
EEG signals are commonly used data sources in BCI
applications. For this reason, recent studies to analyze the EEG
signals in the most accurate way are increasing rapidly. When
features are extracted from EEG signals, the use of methods
sensitive to local variations is of great importance for correct
classification of the signals. In this study, 1D-local binary pattern
(LBP) method which is sensitive to local changes was applied to
motor imager/movement EEG signals and the obtained features
were classified with the k-NN and SVM classifiers. Accordingly, in
the case of using the k-NN method, the lowest 99.98%, and highest
100% classification accuracy was obtained.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Funda Kutlu Onay
Cemal Kose
Light sleep is a sleeping period which occurs within
each hour during the sleep. This is the period when people are
closest to awakening. With this being the case people tend to move
more frequently and aggressively during these periods. In this
paper the most suitable moment for waking a person up will be
described. The characteristics of sleeping stages, detection of light
sleep periods and analysis of light sleep periods were clarified. The
sleeping patterns of different subjects were analyzed. The
detection of this moment and the development process of a system
dedicated to this purpose will be explained, and also some
experimental results that are acquired via different tests will be
shared and analyzed.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Egemen Turkyilmaz
Alper Akgul
Erkan Bostanci
Mehmet Serdar Guzel
With the development of technology, remote sensing
is commonly used for ecological studies and monitoring wetland
and management. Artificial Neural Networks are extremely
simplified model of the brain occurring by neurons and layers
connecting to neurons so artificial neural networks method is
frequently used to classify satellite images. In this study, Landsat5
satellite image with spatial resolution of 30m, acquired on
October 29, 2007 and Landsat-8 acquired on November 27, 2017
were used to identified the coastline changes at Kozan Dam Lake.
The lake is used as drinking and irrigation water. Therefore, it is
very important to examine the coastline changes of the lake. In
first step, image to image registration was made to conform image
coordinate systems of images to each other. Second step, images
were classified by artificial neural networks method. Four classes
namely lake, agricultural area, soil, and vegetation area were
determined. Third step, image classification accuracies were
determined. Finally, the changes in coastline of Dam Lake were
calculated by post classification comparison method. Coastline
change of Dam Lake was calculated as 0.6 km2 increase and the
change image map was created. At the end of the study Kozan Dam
Lake coastline changes were monitored by using remote sensing
methods.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Tolga Kaynak
Sevim YASEMİN ÇİÇEKLİ
Mustafa Hayri Kesikoğlu
This article will discuss the effect of performance variables in achieving optimal solution in single machine scheduling problem. First of all, To determine whether genetic algorithm solution is optimal, optimal solution values for different job size will be obtained by mathematical model. In this model, Primary performance measure is Tmax, while secondary performance measure is the number of tardy jobs (nt) and total tardiness (TT) values. Genetic algorithm performance variables are crossover and mutation ratio, generation and population size. However other variables are job size, strategies of scheduling. We will utilize statistical methods to understand the effect of performance variables. Application study is to schedule the bottleneck machine for a company in the textile industry.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Tugba Tunacan
S. Büşra ORTOĞLU
Inventory control models are one of the most mature
fields in the area of supply chain management but it is not
obvious how to extend inventory control models under different
types of problems where each problem has specific features and
includes many different limitations and constraints. In addition,
the dynamism of the real-world interactions occurring in
inventory control systems should be modeled with much details,
realities, and complexities. At this point, Simulation Optimization
(SO) models along with modern computing power provide a
significant opportunity to respond effectively in a dynamic and
stochastic environment. To remain competitive and viable in
today’s business climate, SOcan be explicitly taken into account
as a complementary tool. In this study, SO is used to develop a
multi-objective search for the inventory control system with
supplier selection where objectives of the SO model are
minimizing total supply chain cost and maximizing average
service level. The optimal values of the initial inventory, re orde r
point, and order-up-to level for supply chain members are
determined by proposed SO model. The proposed model has an
ability to analyze dynamics of the supply chain members and to
transform it into a clear structure for supply chain decisions.
This is very important in real-world settings because proposed
models lead to a large number of variants to manage a wide
range of decisions in the supply chain.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ayşe Tuğba Dosdoğru
Aslı Boru
Mustafa Göçken
Social media platforms such as Twitter have grown at
a tremendous pace in recent years and have become an important
source of data providing information countless field. This situation
was of interest to researchers and many studies on machine
learning and natural language processing were conducted on
social media data. However, the language used in social media
contains a very high amount of noisy data than the formal writing
language. In this article, we present a study on diacritic restoration
which is one of the important difficulties of social media text
normalization in order to reduce the noise problem. Diacritic is a
set of marks used to change the sound values of letters and is used
on many languages besides Turkish. We suggest a 3-step model for
this study to overcome the top of the diacritic restoration problem.
In the first stage, a candidate word producer produces possible
word forms, in the second stage the language validator chooses the
correct word forms and at the final word2vec is used to create
vector representations of the words and make the most
appropriate word choice by using cosine similarities. The
proposed method was tested on both synthetic and real data sets,
and we achieved a relative error reduction of 37.8% in our data
sets compared to the previous study with an average of 94.5%
performance.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Zeynep Ozer
İlyas özer
Oğuz Findik
In this paper, historical data of stocks in the XU030 index of BIST are examined by considering their trends and seasonal behaviors in order to forecast next five year’s stock prices by using ARIMA or seasonal ARIMA technique. Then, a mixed integer programming model is executed for generating a portfolio management for next five years. The proposed mixed integer programming model is based on knapsack problem. The knapsack problem is one of the most applicable portfolio management models.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Oğuzhan Ahmet Arık
As an instrument of democracy, voting is a critical issue. Although paper-based voting systems are still used commonly, e-voting systems have started to substitute under favor of improvements in the technology. This situation gives rise to need for secure, reliable, and transparent e-voting systems to make people trust. To do this, there are some security requirements that should be concerned and satisfied such as privacy, fairness, verifiability etc.
This study has an educational intuition that analyzes those requirements, theoretical background information related to cryptographic schemes behind them and creates a place-based e-voting design which was implemented for kiosk voting. As a contribution, Paillier homomorphic cryptosystem is used in our system. Moreover, our study includes a detailed criticism for the implemented system in terms of chosen cryptosystems and design modules with security and e-voting requirements.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Leyla TEKİN
Hüseyin Güven ÖZGÜR
Burcu SAYİN
Arzum KARATAŞ
Pelin ŞENKULA
Emre IRTEM
Serap Şahin
In the present study, effect of austenitizing time at
intercritical austenitizing temperatures was investigated on the
microstructural features of ductile cast iron. For this aim,
unalloyed ductile cast iron samples intercritically austenitized at
790 and 800 ° C for 1, 5, 15, 30, 60 and 120 min. The samples
were water quenched following intercritical austenitizing. Ferrite
+ martensite dual phase matrix structures have been observed in
intercritically austenitized and quenched samples. Martensite
volume fraction was increased with increasing austenitizing time.
The martensite volume fraction was significantly increased up to
30 min and no remarkable increment in martensite volume
fraction after 30 min. The martensite volume fraction can be
controlled both intercritical austenitizing time and temperatures.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Volkan Kılıçlı
Mehmet Erdoğan
Visible light communication (VLC), popularly known as light fidelity (Li-Fi), is a promising alternative to overcome the limitations of radio-wave communication. VLC is a green technology which uses light-emitting diode (LED) illumination to transmit data without needing fibre cables. VLC is applicable for both indoor and outdoor communication. In this study, we investigate the effect of sandstorms on VLC via simulating a vehicular-to-road VLC (V2LC) outdoor application. Sandstorms are a weather phenomenon which frequently occurs in the Arab peninsula and other parts of the world; in this context, researchers have not thus far addressed the effect of sand particles, which absorb and scatter light, on VLC. Our simulation is conducted using MATLAB software, and the results show that the effect of sandstorms on VLC is similar to that of fog and rain as investigated by other researchers. However, sandstorms are also different in terms of the nature of sandstorm particles, with different sizes and refraction indices when compared with rain and fog particles. We also find that high-density-clay sandstorms, among other types of storms, most severely affect VLC communication and limit the transmission range. Other low- and medium-density storms less severely affect VLC while exhibiting a relatively larger communication range.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
K. J. EBRAHIM
Alauddin Al-Omary
This article attempts to solve the problem of efficient
design of proportional+integral+derivative (PID) controller
applied to automatic voltage regulator (AVR) by employing
recently introduced symbiotic organism search (SOS) algorithm
for the first time. SOS is a metaheuristic proved recently to be
promising by benefitting from the idea of imitating natural
phenomena of interactive behavior seen among organisms living
together in a similar environment. PID controller design needs
proper determination of three control parameters. Such a design
problem can be taken as an optimization task and SOS is invoked
to find out better controller parameters through the new cost
function defined in the paper, which allows to evaluate the control
behavior in both time-domain and frequency-domain. For the
performance analysis, distinct analysis techniques are deployed
such as transient response analysis, root locus analysis and bode
analysis. The efficacy of the presented technique is widely
illustrated by comparing the obtained results with those reported
in some prestigious journals and it is shown that our proposal
leads to a more satisfactory control performance from the
perspective of both time-domain and frequency-domain
specifications.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Emre Çelik
In this paper, based on the laws of conservation and change of energy in the combination of the finite element method and minimization of the energy functional, is obtain a linear system of algebraic equations, the solutions of which allow us to find the values of the unknown variables.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Kanat Amirtaev
— Concrete steel bars used in the construction sector are
produced according to Turkish Standard, “TS 708 Steel for The
Rainforcement of Concrete- Reinforcing Steel”. Suppliers,
produce concrete steels using the Tempcore system that provide
the desired properties by developing processes for high safety and
low cost. The tempcore system is a process of giving a certain
amount of water to the surface of the concrete steel bar coming
from the finish rolling mill. In our study, our purpose is
estimating the mechanical physics properties of the concrete steel
bar produced by the tempcore system which is most common
method with multiple linear regression. Generating to elements of
chemical composition which are carbon, manganese and silica,
also parameters (water discharge, size etc.) affecting the strength
in the rolling process were determined as “independent
variables”. “The Yield Strength” and “Tensile Strength” as a
dependent variable is estimated by the Multiple Linear Regression
Method.
As a result of the study, it is aimed to reduce the amount of scrap
product that is erroneous and/or to be released to the waste by
preventing the production faults by predicting which yield values
of the input variables such as water flow will yileding in the
chemical composition.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Fuat Şimşir
Hande Vurşan
Social network analysis investigates relationships in a networked structure in order to interpret the roles of individuals and evaluate their respective importance. The common approach is employing graph theory that models the network as a graph data structure. Graphs are mathematical abstractions to model pairwise relations between objects. A graph is comprised of nodes connected with edges. While nodes indicate individuals in a network, edges signify relationships or interactions. In this paper, we evaluate the research performance of the European countries considering the research activities within the framework of European Cooperation in Science and Technology (COST). Founded in 1971, COST is the oldest and widest scientific intergovernmental framework in Europe supporting 37 countries including Turkey. COST can be considered as an incubator to set up interdisciplinary research networks since it provides support for network activities such as meetings, training schools, short scientific exchanges, etc. but does not fund the research itself. Therefore, we believe that the research network under COST can be a good indicator to analyze relationships between countries in research activities and evaluate the research performance of the countries. In this paper, we considered research actions funded by COST between 2012-2017 and evaluated research performance of the countries according to their participations andinteractions. To assess the performance, we modeled the relationships between countries on a directed graph and applied centrality analysis which is a common approach to evaluate the relative importance of a node within the network. Each action is coordinated by a management committee which is composed of a chair and at most two delegates per participant country. In the graph, each participant country is denoted with a node. We classify the countries according to their roles in the action. Since the proposer of the action becomes the chair, usually,we regard the country of the chair as a gateway to access the action. Therefore, to signify the relationship between two countries, a directed edge is added from the participant country to the respective country of the chair. Note that several projects were considered over a span of 6 years and multiple interactions between two nodes are indicated as the edge weight.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
İzzet Fatih Şentürk
Burak Taş
Recently, object tracking methods based on deep learning have shown great successes. Using deep neural network methods allows following the object even in highly complex scenarios by learning more details of the object in the video and the object motion model. The developed network architecture needs to be trained with a powerful dataset. The variety and size of the selected dataset affect the success of object tracking methods’ results directly. Some object tracking studies have also used image datasets to obtain the diversity in the training set in addition to the video dataset. The object in the image has gained some kind of artificial motion/action between the two images by making the certain rotational or translational movements. But the uses of this technique brings out the question of whether the object has gained a right action or not. In this study, a new perspective is introduced to provide the data the diversity which is required by deep learning-based methods. In this paper, ADnet, which is a deep learning based object tracking method, is used to test our new perspective which is mentioned above. For the training of the ADNet method, color spaces such as HSV, L*a*b*, NTSC, YCbCr, inverted HSV (converted to HSV channeled by taking BGR instead of RGB) were analyzed. As a result of the analysis, HSV and inverted HSV (IHSV) color spaces have been found out to provide stronger and more varied training dataset. Moreover, in order to prepare a proper training set for the object tracking, two different datasets were created with the videos taken from Vot2015 and Vot2014 datasets. Six different training sets were created for each group by translating them into RGB, HSV and IHSV color spaces. A separate ADNet network architecture was trained for each training set. Tests were carried out for each method with the dataset, which included 61 videos. This test dataset includes some videos which are not used in training dataset. In conclusion, it was found that stronger training sets could be created by applying different color transformations such as HSV and IHSV to strengthen the training set.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Hüseyin Üzen
K. Hanbay
In this paper, the magnetic field exposure analysis of
a human body due to underground power cables is carried out as
the simulation study. Simulations are implemented through a
finite element method (FEM). Human body is modeled as a two
layered cylinder. Upper layer of the cylinder is selected as an
average skin tissue and the inner layer is formed as an average
muscle tissue with realistic values at an extremely low frequency
(ELF) region. Shielding is applied as the mitigation technique and
aluminum (Al) is used as a shielding material. The thickness of 1,
2, 3 and 4 mm shielding materials are applied, respectively.
Evaluations are implemented with respect to the magnetic flux
density and the induced current density. 4 mm shielding which is
the thickest material used simulations shows the best shielding
results to mitigate the magnetic flux density and induced current
density. The worst shielding is obtained for the 1 mm thickness of
the material, as expectedly. Furthermore, as the distance of the
source increases, both magnetic flux density and induced current
density decrease. In other words, these parameters depend on the
distance between a source and observation points. Different
induced current density values of skin and muscle are observed
due to the different electrical properties of tissue. Assessments
have been done according to exposure limits published by the wellknown
organizations.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
K. ATES
H. Feza Carlak
Sukru Ozen
Speckle noise, inherent in synthetic aperture radar (SAR) images, degrades the performance of the various SAR image analysis tasks. Thus, speckle noise reduction is a critical preprocessing step for smoothing homogeneous regions while preserving details. Therefore, in a recent study, SDD-QL method was proposed which is a variational approach where
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Fatih Nar
Ferhat Atasoy
As known, attribute selection is a method that is used before the classification of data mining. In this study, a new data set has been created by using attributes expressing overall satisfaction in Turkey Statistical Institute (TSI) Life Satisfaction Survey dataset. Attributes are sorted by Ranking search method using attribute selection algorithms in a data mining application. These selected attributes were subjected to a classification test with Naive Bayes and Random Forest from machine learning algorithms. The feature selection algorithms are compared according to the number of attributes selected and the classification accuracy rates achievable with them. In this study, which is aimed at reducing the dataset volume, the best classification result comes up with 3 attributes selected by the Chi2 algorithm. The best classification rate was 73% with the Random Forest classification algorithm.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Adil Çoban
Ilhan Tarimer
Computational forensic is a far-reaching field for criminal and civil laws in this age. Aim of this project is to develop an educational tool to analyze persistent storage devices to find possible evidences. Evidences are found as metadata information on these drives. These metadata information are collected in a comma separated value-CSV format document. This CSV file can be imported to a database and can be easily analyzed. By the classical forensic investigator tools mostly can analyze only one media at a time, but by this way more than one digital evidence can be comparatively analyzed. Also, deleted files may hold evidences, so recovering of deleted files is an additional topic for this study. The structured codes and related documents have shared on github as an open project; to give a chance to extension of this study by new projects and we hope that the product of this study can be useful tool for computational forensic courses.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Hüseyin Güven ÖZGÜR
Serap Şahin
In this paper, we propose an anti-spoofing method
that employs the fusion of various full-reference and no-reference
image quality assessment techniques to detect fake and real ear
images presented to biometrics systems under print attacks. In this
context, full-reference image quality assessment measures such as
Error Sensitivity Measures, Pixel Difference Measures,
Correlation-Based Measures, Edge-Based Measures, Spectral
Distance Measures, Gradient-Based Measures, Structural
Similarity Measures and Information Theoretic Measures are
used. Additionally, no-reference image quality assessment
measures such as Distortion Specific Measures, Training Based
Measures and Natural Scene Statistics Measures are implemented
to distinguish fake and real ear images. A comparative analysis of
the performance of these quality metrics and the proposed method
using decision-level fusion of all aforementioned measures are
performed. The experimental results are presented using AMI and
UBEAR ear databases by creating print attack counterparts of the
ear images used in these databases.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
İmren TOPRAK
Önsen Toygar
Image Enhancement is a required and indispensable technique in order to improve the image quality of digital images. Much as the digital cameras and mobile phones are available everywhere, lack of clearness on the side textures, emerging of dark or bright areas and creation of noise occurs due to reasons such as failure of camera foci, lack of lighting and atmospheric disturbances. As such, it is necessary and beneficial to develop an effective improvement algorithm in digital images addressing such negative issues and noises. The fundamental function of image improvement is to generate a new density value for each pixel value in the image through utilization of the transformation function after the density value of each pixel of introduction image is received. The proposed conversion function is named Regional Similarity Transfer Function (RSTF) in the study and the conversion is applied by taking into account the density distribution similarity between neighbor pixels. The intuitional optimization technique preferred mostly in engineering applications recently, named Gravitational Search Algorithm (GSA) has been utilized with an eye to optimize the parameter values of the proposed RSTF conversion function (1). An objective evaluation criterion was employed with a view to measure the quality of the images by finding the parameters of the conversion function with GSA. The objective function three performance measures-namely entropy value of images, sum of edge densities and number of edges- of which were combined, was preferred (2). Our experimental results reveal the fact that the proposed method efficiently eliminates the noises received from the images while increasing the image quality.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ferzan Katircioglu
Zafer Cingiz
In this paper, one-shot-learning gesture recognition
methods are reviewed and an approach of hand gesture
recognition using one-shot-learning is proposed. This approach
aims to recognize new categories of gestures from a single video
clip of each gesture. The gestures are generally related to a
particular task, for instance, hand signals used by divers, finger
codes to represent numerals, etc. In this study, both RGB and
depth images are utilized for a given dataset. A rich dataset,
namely the ChaLearn Gesture Dataset (CGD2011), are employed.
The dataset is divided into 20 different files which include 940
videos in total. Although training the system with only one
example is difficult, depth and RGB images provide many new
possibilities. We used the standard deviation of the depth images
of a gesture and motion history image (MHI) method. Also, two
dimensional fast fourier transform (2D FFT) is used to reduce the
effect of camera shift. It is seen that FFT has no distinct effect on
the image quality. Then, we compare image templates based on the
correlation coefficients and Levenshtein, Mahalanobis, Frobenius
distance measures. The Levenshtein distance measure is more
suitable to match image templates compared to other distance
measures. It is observed that MHI method gives better hand
gesture recognition accuracy about one-shot-learning.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Esma Şeker
Oğuz Findik
In software development processes, architectural documents can be prepared by the beginning of the project like Big Design Up front (BDUF) if software projects requirements are prepared with details and reviewed by the team. However, software projects with a lot of uncertainties or ambiguous requirements do not have any process to prepare and record architectural decisions during the software development. In recent years, agile software development has become very popular in the software industry. Therefore software development teams try to adopt their software processes against changing requirements and dynamic market conditions with using agile methodologies. Because of the underlying philosophy of agile, agile teams started paying more attention to working product over comprehensive documentation and big design up front. However agile software development also contains architectural and design decisions during the development. One of the agile principles also points that the best architectures, requirements, and designs emerge from the agile team during the development. Nevertheless, agile methodologies do not offer any processing cycle for architectural documentation in their process. In this article, we will propose how the architectural decisions will be documented in agile frameworks, which one is the most popular Scrum framework.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mustafa Savasci
Fatih Cetin
Caglar Cakir
Oğuz Findik
As is known, it is often difficult to store and
transmit images used in various computer applications. A
possible solution to this problem is to use one of the known data
compression techniques because they help to reconstruct the
image with a lower number of measurements. In this study, a
new Singular Value Decomposition (SVD)based technique is
proposed to compress images. The advantage of using SVD is
that it both has energy compression capability and is easily
adaptable to local statistical variations of the image.
Furthermore, the SVD can be implemented with non-square,
non-reversible matrices of size m x n. However, how to
determine the threshold value for image compression in the
SVD technique is still one of the fundamental problems. In this
study, the desired threshold value is calculated by dividing the
sum of the differences between the obtained singular values by
the rank of the matrix. Simulation results confirm the feasibility
of our proposed method.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
A. SUTCU
Ali Degirmenci
Ömer Karal
I. CANKAYA
This paper shows the implementation of an impedance control method to regulate the interaction forces between a robotic arm and the environment,when there is connect between them. A complete description of the system to model and control both an RR robot arm and its interaction with the environment is simulated and detailed by Matlab/Simulink; from the generation of a mechanical model in SimMechanics (Matlab) after export its 3D drawing. The description and setting of a dynamic model based on computed torque control, to cancel out the nonlinearities existing on the dynamic model of the robot. It is based on feedback linearization and computes the required arm torques using the nonlinear feedback control law, and lastly control of the reaction forces is done using the impedance control method after modeling the environment. This type of control modifies the dynamic behavior of the robot when there is contacting with the environment and it is widely used in industrial robots.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ali Alshawi
Selcuk Kizir
Today, there are some difficulties of planning a social activity. One of the biggest challenges is that people have more mobile lifestyles in the last few decades. For this reason, the possibility of participating of people in a particular event varies according to the person’s current location. However, the fact that today's people are mobile as well as online, this makes it possible to reach them virtually even if they are not physically reachable. In this study, an approach has been developed to identify and recommend the most suitable candidates according to the compliance and location of the people for a social activity that is planned at a certain capacity. In the developed approach, people are weighted according to their compliance and physical distance to the event. Then, people are sorted by the location of the event. The most suitable people are identified, not more than the capacity of the event. The proposed approach uses person characteristics (gender, age, areas of interest), the Euclidean distance of the people to the event and the location where the event is to be done. The proposed approach also uses the Clarke & Wright Saving Algorithm, which is a heuristic algorithm and is mostly used in vehicle routing problems in the logistics area. Thus, the most appropriate persons can be identified that can be invited to an event with minimal cost. Furthermore, in addition to the use of this algorithm, if people invited to the event are taken by car, it is possible to determine the most suitable routes and to ensure that people are collected according to these routes and participate in the event.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Levent Sabah
Mehmet Şimşek
Computer-aided curve and surface design models are used to design surfaces that do not have a particular shape. Since these surfaces cannot be expressed by known mathematical functions, curve and surface modeling methods such as Bezier, B-Spline and Non-Uniform Rational B-Spline (NURBS) have been developed. In this study, an application is developed that allows the NURBS curve algorithm, which is used as a method in 3D modeling, to be computed using Field Programmable Gate Array (FPGA) with parallel processing capability and displayed on the LCD touch screen. The B-Spline basis function which NURBS based on are sampled mathematically. The parametric values used in the display of the NURBS curves and surfaces are presented on the LCD with user interaction. Parametric values such as control points, knot vector, and weight vector are separately sampled for curves and mathematical solutions are given. The NURBS curve for user-defined control points can be displayed in real time on the screen. In addition, an implementation of the NURBS algorithm in the Visual Studio platform was developed and obtained results were compared.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Yasin Öztürk
C. OZCAN
In daily life we may encounter many different optimization problems. There are many different algorithms developed for solving these problems. The abundance of optimization problems in every field, such as science, engineering, economics, health, communication, production, etc., have made these algorithms are more popular. These algorithms are divided into two main groups as mathematical based and meta-heuristic based algorithms. The meta-heuristic algorithms are inspired by the nature events in general. In this study, we deal with the Vortex Search (VS) algorithm, which is one of the meta-heuristic algorithms. This algorithm is inspired from the vortex pattern produced by the vortical flow of stirred fluids. We proposed some improvements on vortex search algorithm to increase the performance of the original VS algorithm. To show the performance of Improved Vortex Search (ImpVS) algorithm, we used well-known meta-heuristic algorithms, such as Differential Evolution (DE) algorithm, Particle Swarm Optimization (PSO) algorithm, Artificial Bee Colony (ABC) algorithm, Simulated Annealing (SA) algorithm and original Vortex Search (VS) algorithm. The obtained Benchmark results show that the proposed ImpVS algorithm has got the competitive performance for the optimization problems.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Gökhan Uçar
Uğur Yüzgeç
Using Synthetic Aperture Radar images become popular in many military or civilian applications such as algorithm design, geo-referencing and Automatic Target Recognition. One of the main reason is SAR images can be obtained in any weather condition like rainy or cloudy weather even without daylight.However, Synthetic Aperture Radar (SAR) images contain multiplicative noise called speckle which makes analyzing images difficult. Therefore, there are many algorithms developed about despeckling SAR images in last decades. Each algorithm has strengths and weaknesses such as some algorithms work great in texture areas and some can work fine about homogeneous regions. To achieve more efficient result in despeckling SAR images, we proposed a method which uses 3 despeckling algorithms (SSD, MSAR_BM3D and FANS) and apply those algorithms in the regions which they are powerful. The proposed method splits a SAR image into smaller images and use Convolutional Neural Networks to categorize the sub images to find which algorithm is the best for that region. Afterwards, sub images despeckled using the algorithm which CNN selected and sub images come together and create the final despeckled image. The proposed method aimed despeckling of noises from the Synthetic Aperture Radar images more effective than the available despeckling algorithms.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Yusuf Şevki Günaydın
Baha Şen
Hiding and securing information is a basic demand
throughout humanity. People have used their own bodies,
languages, writings, etc. to provide this need. Steganography is
acknowledged by science and art that researches hiding
information methods. Steganography consists of two element
basically that cover and secret information. In the past, people
used their bodies and poems, diaries for cover and used tattoo and
acrostic methods for secret information. In recently thanks to the
developments of technology, Steganography has widened its
methods and study areas. There are four Steganography methods
which are text, image, audio and video in computer science. All
types of Steganography methods have distinctive different ways to
hide information. But if we want to mention the most used ones,
we can say that changing characteristic of text (like color, font size)
in text Steganography and changing Least Significant Bit(LSB)
way for other types of Steganography methods. The LSB is a way
that we overwrite the LSB of each byte of the cover (image, video,
audio) with secret information binary representation. In our
project, we are developing an android mobile application that
allows user to hide a secret information inside any image. The
image can be captured instantly or selected from user gallery. We
are using LSB image Steganography method in order to hide
secret information in image. Beside this, we encrypt the secret
information with an encryption algorithm before inserting it in
image. At the end, user can save the result image for the future or
share with somebody who able to see the secret information only
with this application.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Celalettin Misman
Mehmet Hacibeyoglu
This study proposes an information security risk
assessment approach based on Bayesian networks and Fuzzy
Inference System in order to evaluate and calculate both
qualitative and/or quantitative risks. The proposed preliminary
model is developed to analyse test processes for a software services
company in order to evaluate the information security risks. In
order to collect data for our risk assessment model, assets,
vulnerabilities, threats, and related risk values are identified and
analyzed with experts and managers based on the testing process
in the company. Threats, vulnerabilities, risks, and their relations
are constructed with a Bayesian network and marginal
probabilities for each risk are calculated. Several fuzzy
membership functions are designed for assets’ values, risks’
probabilities, and relative risk values. Fuzzy decision rules are
constructed for some of the chosen risks by using the assets’ values,
relevant risk probabilities, and relative risk values. In the final
stage, the impacts of risk (loss) values are calculated by
aggregation and defuzzification. Promising results have been
obtained so far and this preliminary model will be used as a basis
for an enhanced model, which can be successfully used for
information security risk assessment and management with less
subjectivity, more reliability, and more flexibility.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Sevilay Beken
Mete Eminağaoğlu
The use of machine learning techniques has significantly increased recently. The classification of normal or abnormal situations in network traffic is successfully applied with machine learning techniques. It is possible to encounter False Positive situations during the classification process. With Probabilistic Neural Network (PNN) model, it is aimed to explore the intrusion and its types within network traffic with probabilistic distribution. Knowledge Discovery Dataset (KDD99) will be used in this study.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ibrahim Atay
Osteoarthritis (OA) is the most common form of joint disease, and its impact is set to grow as the prevalence of obesity rises and our elderly population increases. As a result of this disease, it is necessary to make structural examinations for the determination of the deformations that occur. One of the methods used for structural analysis of biological samples is the wide-angle X-Ray scattering (WAXS) device. In this study, hip bone samples taken from humans during surgery were investigated using wide-angle X-ray scattering technique. Hip bone specimens were primarily compared based on regional density and later on based on sex. As a result of scatter patterns, the presence of crystal structures has been determined. The values of crystal structure obtained depending on low and high dense region and sex are different.As a result of gender related comparisons, it was found that crystal structures were better in males than females.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Tuba Çayir
D.KARAARSLAN
K.MEMİŞOĞLU
Semra Ide
O.Gundogdu
The finite element method (FEM) is a computational
technique that is often used to solve biomedical engineering
problems. The biphasic cartilage model plays important role in
representing the mechanical behaviour of the articular cartilage .
In order to obtain accurate results in finite element analysis of
articular cartilage, it is necessary to determine appropriate FEM
parameters such as mesh density and finite element type. Mode l s
with small element sizes in the FEM allow more accurate re sul ts
to be obtained however it requires longer calculation time. In
contrast, large element size can lead to non-precision results
while shortening the calculation time. The type of the elements
may also change the results of FEM analysis for biomechanical
problems. The purpose of this study is; to evaluate the effect of
the mesh size and type of the finite element on the resul ts of the
numerical biphasic tissues. In this study, in order to achieve thi s
goal a series of compression analyzes were performed on the 3D
biomedical models with different mesh density and element types
using ABAQUS 6.13 software and the results were compared.
The analysis results showed that mesh density element type and
element type had little effect on the maximum reaction force . On
the contrary, the mesh density had greatly increased the
computational time.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Sabri Uzuner
E. ZURNACI
M.L. Rodriguez
Serdar Kucuk
The use of technological devices in education has become inevitable today as technology is proceeding at a dizzying pace. Technological devices and softwares developed within the scope of these devices have become especially used within the game-based learning system. Especially in pre-school level, to teach some concepts to illiterate children, game based learning system is used.
In this study, a platform based on Kinect V2 was developed with the aim of teaching English words to pre-school children. The study was tested on a select group of pre-school children. Eventually it has been observed that the English equivalents of the concepts of color and shape have been retained for a longer period of time due to the support of this visual and audio software material. In addition, it has been determined that the motivation of the student is made permanent because it enables to learn by amusing.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Merve Varol Arısoy
Ecir Uğur Küçüksille
Recently, through development of several 3d vision
systems, widely used in various applications, medical and
biometric fields. Microsoft kinect sensor have been most of used
camera among 3d vision systems. Microsoft kinect sensor can
obtain depth images of a scene and 3d coordinates of human joints.
Thus, anthropometric features can extractable easily.
Anthropometric feature and 3d joint coordinate raw datas which
captured from kinect sensor is unstable. The strongest reason for
this, datas vary by distance between joints of individual and
location of kinect sensor. Consequently, usage of this datas without
kinect calibration and data optimization does not result in
sufficient and healthy. In this study, proposed a novel method to
calibrating kinect sensor and optimizing skeleton features. Results
indicate that the proposed method is quite effective and worthy of
further study in more general scenarios.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mahmut Selman Gökmen
Mehmet Akbaba
Oğuz Findik
Many people live with various health problems due to smoking, obesity and sedentary life. Especially, many people have severe illnesses such as lung cancer and asthma because of smoking. However, people unfortunately do not quit smoking easily. It is aimed to change the lifestyles of people with the mobile application that will be developed in order to solve these problems. In the proposed system, a cloud based mobile application will be developed under the supervision of a family physician. The treatment plan will be given as a result of the medical history and physical examination who applied to family physicians to quit smoking. Patients will be able to access this treatment plan through mobile application. After that, patients will be able to record and monitor daily cigarettes, nutrition and exercise. The doctor will check the information that the patient has entered and will be able to detect if the patient is not fit in treatment. Accordingly, doctor can update the treatment plan and create the most appropriate treatment model for the patient.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
İlay Ilter
Alp Kut
Vildan Mevsim
Semih Utku
This paper describes the stages faced during the
development of an Android program which obtains and decodes
live images from DJI Phantom 3 Professional Drone and
implements certain features of the TensorFlow Android Camera
Demo application. Test runs were made and outputs of the
application were noted. A lake was classified as seashore,
breakwater and pier with the accuracies of 24.44%, 21.16% and
12.96% respectfully. The joystick of the UAV controller and
laptop keyboard was classified with the accuracies of 19.10% and
13.96% respectfully. The laptop monitor was classified as screen,
monitor and television with the accuracies of 18.77%, 14.76% and
14.00% respectfully. The computer used during the development
of this study was classified as notebook and laptop with the
accuracies of 20.04% and 11.68% respectfully. A tractor parked
at a parking lot was classified with the accuracy of 12.88%. A
group of cars in the same parking lot were classified as sports car,
racer and convertible with the accuracies of 31.75%, 18.64% and
13.45% respectfully at an inference time of 851ms.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ali Canberk Anar
Erkan Bostanci
Mehmet Serdar Guzel
Filtering can be used for different purposes in image
processing. One of them is to reduce noise in the image. In this
study, local variance based on switching filter is designed to
remove Gaussian noise from gray scale images. During filtering
process, local variances of each pixel is calculated and then pixels
are classified as five clusters according to their local variance
values by the k-means clustering method. Depending on the result
of the clustering, variance of the Gaussian filter kernel is tuned. In
the smooth regions, in which variances of the pixels are low, higher
standard deviation Gaussian filter is applied. Higher variance
pixels represent the edge pixels, therefore lower standard
deviation Gaussian kernel is applied to preserve the edges. In
clusters with medium variance pixels, the standard deviation value
in the Gaussian filter is changed depending on the local variance
values. Experimental results show that designed local variance
based switching filter gives better performance to remove the
Gaussian noise at various levels compared to the classical filters.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ali Degirmenci
I. CANKAYA
Ömer Karal
Recep DEMIRCI
In almost all areas of the life-cycle, measurement, contolling and even achieving in stable/desired values of temperature have big importance. The man-kind’s daily activities are influenced by various control systems in almost every direction. Also, control systems are widely used in all sectors of the industry. This study mainly focused on measuring and controlling the temperature values. The purpose is to keep stable the analog temperature data at the desired temperature by performing the necessary control procedures. In designed temperature control system, analog temperature values were measured by K type thermocouple. Since the temperature measured by the thermocouple is in the mV level, this data must be raised to 0-5 V to be supplied to the Arduino analog input (A0). The AD620 instrumentation amplifier was used for the upgrade. The digital output data from the Arduino PWM3 block is transmitted to the SSR (Solid State Relay) using the 74HC244 buffer. Temperature control was performed by the PID control software preparing in the LabVIEW program. In this study, temperature values are successfully obtained with a ±%1.5 accuracy via Labview.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
H. BAKIR
Muhammet Sinan Başarslan
Ümit Ağbulut
Customer satisfaction plays an essential role in financial institutions. Particularly in the banking sector, a series of customer satisfaction studies is carried out in order to ensure the continuity of the customers with the bank. The most important ones of these are; questionnaires, feedback from the branch staff, and the increase in the client's banking transactions. By analyzing these studies, the satisfaction level of the customers can be measured. However, these measurements do not have a complete mathematical accuracy and can be misleading. In this study; the facial image of the customers who come to the bank are perceived by the camera and evaluated by emotional analysis. In this way, it is determined that the customer is satisfied or non-satisfied when leaving the bank. Problematic banking applications are also identified with the help of the analytical result of emotional analysis. In addition to this, the branch personnel of the bank who behave well to the customers are determined and performance evaluation is made more accurately.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Bulut Karadağ
A system is a set of interacting components are
connectedin such a way that the vibration or response in the state
of one component affects the state of others. A dynamic system is
described by time differential equations; therefore, the future
response of the system is determined by the present state of the
system (the initial conditions) and the present input. Modeling and
simulation are the prerequisite to the design of a dynamic system,
as the designing and manufacturing a system and then testing it
for expected performance would be unavoidably expensive. Wide
spread availability of high speed and high storage capacity
computers makes the simulation process even more attractive
before the manufacturing stage for observing the expected
performance of complex dynamic systems. However, before
simulation phase of a system the mathematical model of the system
must be prepared. For complex mechanical systems it is not always
easy to establish the mathematical model. On the other hand, it is
much easier to establish the mathematical model of an electrical
system. Furthermore, simulation software is richer for electrical
systems. For these reasons in this manuscript modeling of a
complex mechanical systems will be realized using electrical
circuit analog and then will be simulated as an electrical circuit.
Advantages of this approach will be explored.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mehmet Akbaba
Adem Dalcalı
M. GÖKDAĞ
Power quality problems due to short circuit faults, are
defined as changes in voltage, current, or frequency in the power
system. Among the power quality problems in distributed
generation systems are island mode operation, harmonics in
current and voltage, voltage sags/swells, voltage interruptions and
transients. The most common power quality problem in the
distribution system is the voltage sags and swells caused by a short
circuit fault. In this study, various Power quality problems due to
short circuit faults such as line-to-ground, line-to-line and
multistage faults are modeled in MATLAB/Simulink
environment. In order to detect the voltage sag and swell
problems, firstly the voltage sag that occurs in case of failure is
examined and the response of the power system is observed. The
study also models multi-stage failures as a result of failure to
achieve relay synchronization. Examination of the voltage sags
and swells clearly revealed the resulting waveforms, the response
of the power system to the fault condition. Another advantage of
the realized work is that the developed model can be used to
measure the performance of the distributed generation system in
failure diagnosis and classification studies.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
A.YILMAZ
Gökay Bayrak
Today, the use of meta-heuristic algorithms in solving non-linear and complex problems is becoming popular. These algorithms are inspired by natural selection, swarm intelligence, physical events and nature. Crab mating optimization algorithm is one of the meta-heuristic algorithms which was developed by V.R. Chifu in 2014. The crab mating optimization algorithm imitates the mating behavior of crabs in nature. One of the biggest shortcomings of this algorithm is that it has got the quite long running times for optimization problems. In this study, to increase the running speed of the original crab mating optimization algorithm, the mating process of the crabs in population was modified. A male crab mates with only a female crab in the new mating procedure. Therefore, the name of the proposed meta-heuristic algorithm comes from this new mating process as a Monogamous Crab (MC) mating algorithm. Vehicle routing problem (VRP) is the popular combinatorial optimization problem. VRP relates to the most appropriate route design to be delivered to a range of customer service by a number of fleets. In this study, the developed MC algorithm is adapted for the vehicle routing problem. The performance of MC algorithm was compared with those of metaheuristic algorithms. The results show that MC algorithm provides promising and competitive performance.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Burakhan Çubukçu
Uğur Yüzgeç
The Tree-Seed Algorithm, TSA for short, has been proposed for solving single-objective optimization algorithm by inspiring the relation trees and seeds in nature. In this study, its multi-objective variant tree-seed algorithm, MOTSA, is proposed for solving multi-purpose optimization problems by motivating its performance on single-objective problems. In order to overcome selection issue in multi-objective problems, the well-known strategies, non-dominated sorting and crowding distance, of NSGA-II has been integrated with the proposed MOTSA. By doing this, the highest quality solutions from the combined populations of trees and seeds are selected and transferred to the next generation. The MOTSA are applied to solve well-known three multi-objective benchmark problems and obtained results show that MOTSA is an alternative multi-objective optimization algorithm.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Gül Özcan
Ahmet Özkış
Mustafa Servet Kıran
Predicting movie success with machine learning algorithms has become a very popular research area. There are many algorithms which can be applied on a data set to make movie success prediction if the data set is prepared and represented properly. In this study, we explained how IMDB movie data was used for movie rating prediction. The data set extracted from IMDB was formatted and prepared for datamining algorithms. These algorithms were executed on WEKA application environment and the performances in movie ratings and confusion matrices were obtained. The seven machine learning algorithms used have performed well on the data set with varying performance ratings of 73.5% to 92.7%. Random Forest algorithm had the best performance of 92.7%. This is the highest score obtained among similar studies.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Didem Abidin
C. BOSTANCI
A. SİTE
In this research, we studied the new generation of telephone exchanges, and discussed how to convert the public number of the recipient into the new IPv6 system, within the telephone exchange and the possibility of serving recipient with the multimedia system.
The rapid development of telecommunication systems over the past decades has led to the latest development in the technology and the volume of services provided by the telephone exchange to recipients through the development of the software architecture.
The presence of modern microprocessors, their speed of work and their ability to implement a greater number of operations have created the possibility of providing many The idea of the work is to find the possibility of transferring the recipient number from the normal numbering system to the IPv6 network system by rearranging the distribution of the address again, eliminating the DHCP feature and redistributing the fields to suit the new numbering. Considering that any country is a major server and has a fixed address of the new address and small sub-division takes its title from the main server, and these sub-subdivisions can give new label to the recipients belonging to them.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
A. Hussian
A. Abdurrahman
Adam Abid Urbanek
Methods: In the provinces of Ankara, Adana and
Mersin, 9 chemical working job security survey studies and work
safety experts were carried out in this study. Computer software
is developed by creating a fuzzy logic based risk assessment
analysis model considering various hazards in occupational health
and safety in the chemical industry. Results: It is very difficult to
model risk in a workplace environment with many specific and
ambiguous hazards and model a system to simulate these hazards.
Software was developed by creating a fuzzy logic based risk
assessment analysis model in consideration of many hazards in
occupational health and safety in the chemical industry. An
alternative approach to risk assessment has been proposed using
fuzzy decision making approach and matrix method. With this
approach, occupational health and safety in the Chemical Industry
specialists are provided with blurred linguistic assessments before
calculations are made, and the inconsistencies in decision making
are reduced by taking arithmetic averages of these assessments. It
has been seen that the three most important risks in the metal
work done by creating the fuzzy logic based modeling of work
safety risk analysis model and software using the fuzzy decision
making approach and the matrix method to increase the job
security in the chemical industry. Conclusion: It is very difficul t
to assess risk in the chemical industry which are many specifi c
and indeterminate hazards, and to model a system to
simulate these hazards. In this study, a computer software
and hardware was developed by creating a fuzzy logic base d
risk assessment analysis model considering many hazards in
occupational health and safety in the chemical industry.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mehmet Zile
Methods: In the provinces of Adana and Mersin, 10
metal working job security survey studies and work safety experts
were carried out in this study. Computer software is developed by
creating a fuzzy logic based risk assessment analysis model
considering various hazards in occupational health and safety in
the Metal Industry. Results: It is very difficult to model risk in a
workplace environment with many specific and ambiguous
hazards and model a system to simulate these hazards. Software
was developed by creating a fuzzy logic based risk assessment
analysis model in consideration of many hazards in occupational
health and safety in the Metal Industry. An alternative approach
to risk assessment has been proposed using fuzzy decision making
approach and matrix method. With this approach, occupational
health and safety in the Metal Industry specialists are provided
with blurred linguistic assessments before calculations are made,
and the inconsistencies in decision making are reduced by taking
arithmetic averages of these assessments. It has been seen that the
three most important risks in the metal work done by creating the
fuzzy logic based modeling of work safety risk analysis model and
software using the fuzzy decision making approach and the matrix
method to increase the job security in the metal industry.
Conclusion: It is very difficult to assess risk in the metal
industry which are many specific and indeterminate hazards,
and to model a system to simulate these hazards. In this
study, a computer software and hardware was developed by
creating a fuzzy logic based risk assessment analysis mode l
considering many hazards in occupati onal health and safety
in the metal industry.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mehmet Zile
– In this study, real-time online mine detection unde r
water is performed using an unmanned underwater vehicle.
According to the underwater position of the vehicle, the data
from the vehicle camera is used to identify mine in a real-time
video stream. Here is an approach for underwater mine detection
based on the use of trained classifiers. Algorithm performance i n
real time video shooting of the vehicle is optimized to reduce false
positive rate by aiming to identify a mine segment of each picture
frame. According to the results obtained, it was ensured that
mine parts are successfully detected under changing conditions
with incorrect positive detection. Algorithms are developed using
the Python program.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
M.BERİK
Seda Karadeniz Kartal
Wireless Sensor Networks (WSN) are used for the
monitoring of objects in various fields of application as well as the
monitoring of military and civilian environments. The energy
consumption of sensors and the optimization of network lifetime
in WSNs are among the important problems that are constantly
investigated and for which solutions are developed by linear
programming method. Furthermore, different algorithmic
solutions have been developed to perform the dynamic deployment
of the nodes efficiently for the solution of this problem. The
proposed solutions require that the targets in the network are
covered by a minimum number of sensors. k-coverage, that
determines the degrees of coverage of the targets in the area of
interest, is an important criterion in determining the number of
sensors covering each target after the deployment of the sensors.
Because the coverage of the targets by a minimum number of
sensors and the minimization of the intersection area of the sensor
increase the lifetime of the network by optimizing the energy
consumptions of the sensors.
In this study, the dynamic deployment approach based on the
Whale Optimization Algorithm was proposed to provide the
optimum solution to the k-coverage problem of WSNs by ensuring
that the targets in the area are covered by a minimum number of
sensors. This approach, that performs the effective dynamic
deployment of sensors by covering the maximum number of target
points and ensuring the minimum degree of k-coverage, was
compared with the MADA-EM in the literature. Simulation
results have shown that this approach is optimum and can be
recommended in the solution of the k-coverage problem by
ensuring that the targets are covered by a minimum number of
nodes.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Recep Özdağ
Murat Canayaz
In this paper we present a cross-layer optimization
method for adaptive video streaming in cellular networks. The
proposed method makes use of a new scheduling algorithm,
tailored to adaptive video streaming applications, which provides
better allocation of radio resources in order to increase the video
quality experienced by the users. After introducing our novel
scheduling algorithm, we compare its performance with the stateof-the-art,
using DASH as the adaptive video streaming technique
and LTE as the cellular network technology. The results show that
introducing DASH-awareness into the network increases the
streamed video quality and the network utilization. We believe
that the proposed novel cross-layer optimization method can also
be applied to future cellular network technologies, such as 5G,
where application-aware resource allocation will be crucial in
supporting the required quality-of-service (QoS).
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ali Alkaya
Talha DEMIR
Burak GORKEMLI
Sinan TATLICIOGLU
Optimization algorithms yield acceptable results in
the shortest time, even if they cannot always guarantee the best
end result in the given problem. There are classical mathematical
methods and meta-heuristic methods that have become very
popular for solving optimization problems. Meta-heuristic
algorithms can be categorized in many type such as physics based,
social based, biological based, chemistry based, sport based,
swarm based, mathematics based and also hybrid based. In this
study, the Artificial Atom Algorithm (A3) is applied in parallel to
solve the Traveling Salesman Problem (TSP). A3 is chemistrybased
technique that is improved by inspired the compounding
process of atoms and the application of parallel A3 is particularly
easy and promises significant gains in performance especially for
large scale TSP. TSP is one of the route planning problems that
finds the lowest cost path of visiting all the cities on the giving map
and returns to starting point, it was aimed to plan the best route.
The performance of algorithm in terms of the city number, the
route distance and the calculation time of this route will be
examined. An interface will be designed to implement the
application and observe the experimental results.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ayşe Nur Altintaş Tankül
Burhan Selcuk
AntLion Optimization (ALO) algorithm is one recent of the meta-heuristic algorithms that was developed by Mirjalili in 2015. ALO algorithm imitates the antlion's hunting behaviour in its larvae phase. The long run time of ALO algorithm is the biggest disadvantage of this algorithm. To overcome this deficiency, we proposed some improvements on the mechanisms of the original ALO algorithm. In order to improve the ALO algorithm, firstly, the random walking distance was changed as twenty percent of maximum iteration instead of the maximum iteration number in the original ALO algorithm. We defined new movements between boundaries around the antlion on the phase of trapping antlion pits. In addition, the boundary checking process, the catching prey and rebuilding the pit were developed. The parallel machine scheduling problem (PMS) is defined that it is a set of independent jobs to be scheduled on a number of parallel machines. Scheduling process optimizes the production job sequences in terms of the different patterns. When there are the similar type of machines to be existing in multiple numbers, the jobs can be scheduled over these parallel machines at the same time. To show the performance of improved ALO (IALO) algorithm, some of well-known meta-heuristic algorithms were used in comparison works. The obtained PMS results show that the proposed IALO algorithm has very competitive results in terms of the mean, best, worst cost and standard deviation metrics.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Haydar Kılıç
Uğur Yüzgeç
In this paper, a particle swarm optimization (PSO)
algorithm is introduced to determine learning parameters
required for the backpropagation (BP) learning algorithm, which
is used for training of a feed-forward neural network (FFNN).
PSO algorithm utilized within the paper works slightly different
compared to conventional PSO (CPSO) algorithm in such a way
that each particle adjusts its position based on the best midposition
of all particles and its group’s previous best. The major
reason of such a change is to enhance the performance of CPSO
algorithm, which is explained in detail in the study suggested by
Tamer, S and et.al. To test the proposed method, a FFNN with
three layers is designed for function interpolation. Learning
parameters of the designed NN are determined by both
conventional error and trial method and the proposed method.
Afterwards, using these two groups of learning parameters, the
NN is trained and tested under the same conditions. According to
the test results, learning parameters determined by the PSO
provide a better performance and interpolating capability for the
NN than those determined by the conventional method.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Emre Çelik
Nihat Ozturk
Adem Dalcalı
The Galactic Swarm Optimization (GSO) is a novel method inspired by the movements of stars and star clusters. The GSO is a framework that uses the optimization methods known in the literature. GSO has a two-stage structure. In the first stage, the optimization method identifies possible good solutions by scanning the search space. In the second stage, the best solution is tried to be found by using possible good solutions. In the original GSO study, Particle Swarm Optimization (PSO) was used as an optimization method in both stage. In this study, Tree Seed Algorithm (TSA), a new optimization method in the literature, is used in GSO framework instead of PSO. In the experimental study, the performance of the GSO_TSA model has been investigated on numeric benchmark functions and obtained results are compared with GSO_PSO model.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ersin Kaya
Oğuzhan Uymaz
Sedat Korkmaz
Eyüp Sıramkaya
Mustafa Servet Kıran
Handwriting character recognition has been a popular problem among scientists for a few decades. United States Postal Service can be given as an example for a company that uses the recognition of digits in real life environment consistently. USPS uses digit recognition system to extract digits from pay checks and fastens the process of sending and receiving checks. Handwriting character recognition problem can be divided into two categories. Online character recognition and offline character recognition. A recognition pattern mainly based on angle of the strokes of stylus is called online recognition. A system is called offline when system takes images as inputs and tries to predict characters from given images by applying machine learning methods. We have worked on offline character recognition problem in this project. Many machine learning methods have been proposed over the years for solving this problem. In this paper we implemented 6 most popular machine learning methods to solve offline handwriting character recognition problem and compare the performance results to decide which method gives best accuracy results under pre-defined conditions. We have selected 92255 images from NIST Special 19 Database and used them as input images during the training phase of the selected machine learning methods. These methods are SVM, Decision Tree, Bag of Trees, Artificial Neural Networks (ANN), Deep learning network with autoencoders and Convolutional Neural Networks (CNN). We implemented all of these methods and compare the performance of the results according to accuracy metric. The results obtained from the comparison is going to help in deciding which ML method should be used to solve Offline Handwriting Character Recognition problem.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ş.G.KIVANÇ
Ahmet Emin Baktır
Baha Şen
With the increase in population density in cities, the use
of motor vehicles is increasing. In addition, traffic congestion,
causes some issues such as air pollution noise pollution that affect
both human health and urban life negatively. For the elimination
of the disadvantageous of the motor vehicle usage people have to
be encouraged to transport with non-motorized vehicle s such as
bicycle. In this study, views about cycling were taken by online
survey for the purpose of popularize the usage of bicycle in
Karabuk University Campus and campus transportation.
According to the obtained data, 30% of the participants were
female and 70% were male and they have the biggest share in the
age distribution, with 80% and 15-25 age range. Looking at the
educational status, 78% of them gave undergraduate education
and 13% gave a postgraduate education. 15% of the participants
were working and 85% were students. In the scope of the study,
bicycle usage of the people was examined. Accordingly, 43% of the
participants have a bicycle. It is also seen that bicycle use is 61%
when it is not bicycle owner. 84%, the highest rate in the
questionnaire assessed participants of the purpose of using the
bike has to have a positive effect on health. Among the factors
limiting the use of bicycles, the rate of 71%, which was the highest
rate, was the lack of bicycle routes and 65% was shared with motor
vehicles.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Özlem Battal
Zeynep Ozer
Optical Character Recognition (OCR) is the extraction of letters, numbers, punctuation marks, shortly the texts, from the images in the digital settings. As a result of this process, electronic images are converted into editable texts. In this study, the performances of character recognition techniques on upper-case letters, lower-case letters and numbers were evaluated in terms of various features. At first, training images with 10 typefaces were generated. Then, testing images were obtained by adding extra 10 typefaces into the system. The training images were formed in 36pt font size. However, the testing images were also formed in 12, 36 and 60pt font sizes in order to see the effects on OCR. Firstly, images were parsed into the characters, then, these images were stretched or squeezed into 100x80, 50x40, 25x20 and 5x4 pixels. Then, thresholding was applied to image files and each character was expressed as vectors having pixel value either 1 or 0.
For the OCR process, 3 algorithms were used; k-Nearest Neighbors (kNN), S upport Vector Machines (S VM) and Artificial Neural Network (ANN). Eucli dean Di stance, Inner Product and
Cosine Similarity were used for the measurement of similarity in kNN. The following results were obtained when the results are evaluated in terms of average means; the best classification was
realized with ANN and the least with Inner Product (k=3) in upper-case letters, the best classification was realized with ANN and the least with Inner Product (k=10) in lower-case letters and the best classification was realized with ANN and the least with Inner Product (k=10) in numbers. The best classification was realized with 36pt and the least with 12pt i n upper-case and lowercase
letters; and the best classification was realized with 60pt and the least with 12pt in numbers.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mehmet Fatih Karaca
Şafak Bayır
Over past two decades, many algorithms taking
inspiration from natural phenomena have been proposed by the
researchers. One of the famous algorithms is Artificial Bee Colony
(ABC) algorithm which is inspired by the intelligent behaviors of
the honey bees. Although original ABC algorithm has been
proposed for solving continuous optimization problems, in order
to effectively solve binary optimization problems original ABC
should be modified. Using logic operator, genetic operator, and
transfer function are the strategies to obtain binary solutions.
Knapsack is a well-known binary optimization problem which
aims to obtain a maximal knapsack packing. In this paper, various
binary variants of ABC algorithm (xorABC, crossoverABC,
vFunctionABC) are applied to 0–1 knapsack packing problem.
The performance of three binary variants of ABC is investigated
with respect to time and quality.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Bilal Babayigit
A. AYTIMUR
In industry, the priority of services provided by the companies are 7X24 (7 days 24 hours) uninterrupted services. Hence, the main reason why database should provide continuous uninterrupted services. The attributes of database services that provide high accessibility services should be reliability, availability and maintainability; features referred to as RAM (Reliability, Availability, Maintainability) in the literature. In addition to that in this paper, mathematical computation pertaining to the location and accessibility in ITIL processes will also be examined.
It is also aimed to investigate what should be done at the architectural level to ensure that the commands coming from Structured Query Language (SQL) results in high performance. When database or system administrators wrongly configures the architectures processing the queries, it may result in inadequate power systems that could have operated with high performance. This article then discusses what might be the necessary adjustments in order to use the resources of query systems more efficiently.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Nejat Yumuşak
Ahmet Yorulmaz
DC motors have a wide range of usage in the industry. So its control is one of the important topics. In literature, there are different control algorithms for the speed control of DC motor. This paper presents a comparative study of PI and Self-Tuning PI controller for the speed control of DC motor. DC motor is modeled and classicPI controller applies for the speed control of DC motor. Pole Placement method is used to get parameters of the PI controller which are Kp and KI. Fuzzy Logic is used for Self-tuning PI controller design. In this controller, Kp and KI controller gains are adjustable parameters and are updated depending on the speed error and change of error. Simulations of these two controllers are performed in the Matlab/Simulink. PI and Self-tuning PI controller are compared and results are given in graphs. The simulation results show that the Self-tuning PI controller has better efficiency than the classic PI controller.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Nurettin Gökhan Adar
Mustafa Eroğlu
R. KOZAN
This study was designed to investigate with ANFIS
(Adaptive network-based fuzzy inference systems) prediction
model for the behavior of concrete containing zeolite under the
effect of H2SO4. For purpose of constructing this model, 3
different mixes with 27 specimens of the 28, 56 and 90 hydration
days compressive strength experimental results of concrete
containing zeolite used in training for ANFIS system was gathered
from the tests. The data used in the ANFIS model are arranged in
a format of six input parameters that cover the age of samples,
Portland cement, zeolite, aggregate, water and hyper plasticizer
and an output parameter which is compressive strength of
concrete. In the model, the testing results have shown that ANFIS
system has strong potential as a feasible tool for predicting 28, 56
and 90 hydration days the compressive strength of concrete
containing zeolite under the effect of H2SO4.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Gıyasettin Özcan
Muammer Akçay
Yılmaz Koçak
Eyyüp Gülbandılar
Forest ecosystems play an increasingly important role
in the global carbon cycle that storing CO2 in the form of different
chemical compounds (lignin, cellulose, etc) from atmosphere by
photosynthesis. Determination of the amount of carbon is
extremely important in reducing greenhouse effect and preventing
global warming. Two different methods are used for determining
the amount of carbon stored in forests. In both cases, control
points necessary to determine the parameters of the different
stand. However, these studies are time consuming and costly. But
using geographical information systems and remote sensing
techniques can provide more accurate information in a shorter
time. In this study, we tried to estimate the amount of aboveground
carbon stored in pure scoth pine stands using various vegetation
indices. For this purpose Kunduz Forest Management Chiefdom
selected for study area. Forest management plans, topografic maps
and satellite image were used. The amount of carbon of pure scoth
pine stands were determined using single tree carbon allometric
equations. Relation between determined carbon data and various
vegetation indices obtained from Sentinel 2A satellite images in
2017 were examined. In order to determine relations various of
vegetation indices were tested. Relationship between results and
the band combinations investigated by using correlation analysis,
relationships between the variables modelled with help of
regression analysis.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Cemİle Çakir
In the stand pipes, which are the only evacuation point of
the raw gas released during the high temperature coking of the
coal, the section reduction occurs due to the carbonization and the
problem of degazing of the raw coke gas is experienced. This leads
to an increase in the internal pressure of the raw gas in the furnace
and emissions to the doors, which are the weakest points for sealing.
It also leads to energy losses depending on the amount of leakage.
The raw gas passing through the vertical chimneys is 900 degrees
and it is isolated with fireclay bricks to protect the metal parts. In
this improvement, high-alumina castable mortar is used instead of
fireclay bricks. This has resulted in a reduction in emissions and
maintenance costs.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Adnan NEHROZOĞLU
Erdal ÜNAL
Bülent ÖZTÜRK
Murat YAMAN
Ozan TURHAN
RC4 is an algorithm that encrypts a data in the form of a bit string with a specified key. The security of RC4 with high encryption speed depends on the random key. Speed of image encryption is very important parameter due to size of the data. Performance analysis was examined using color image encryption, because RC4 is usually used in speed-critical applications. RC4 showed that the desired values could not be obtained when examining the histogram, correlation coefficient and information entropy analysis results. Because of this, chaotic systems are used to increase the performance criteria of image encryption with RC4. Chaotic systems are very sensitive due to their inherent dependence on the initial conditions and dynamic variables. Not random and non-periodic oscillations these systems are performed in a certain frequency range. The RC4 algorithm are enhanced by using chaotic system-based encryption algorithms because of its key size capability and speed. Performance criteria have been improved using 2D Cat Map, Tent Map and Lorenz chaotic systems. When we examine only the encryption made with RC4 and the encryption made with RC4 supported with chaotic systems; more successful results are obtained from histogram, correlation coefficient and knowledge entropy analysis. In addition, the structure of chaotic systems is increased key sensitivity and key size and thus a more secure algorithm is obtained.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Sefa Tunçer
Cihan Karakuzu
F. UÇAR
The real estate has an important position
economically in the world. Proper valuation of the real estate
is important for the country's economy. For the real estate
valuation, it is necessary to know well the concept of value
related to real estates and the factors, which affect the real
estate value around the area. With the development of
computer technology, it is possible to reach quick and
accurate results by making detailed analyzes. In recent years,
developments in artificial intelligence technologies have
made artificial intelligence methods more attractive in real
estate valuation. Also, advanced geographical information
system (GIS) technology has started to use extensively in the
real estate valuation. Thus, the creation of the databases,
which has predominantly spatial information, for real estates
increased the role of GIS in real estate valuation methods.
In this study, positional analysis of agricultural data in the
GIS environment was conducted and the factors affecting
depreciation were examined. Artificial neural networks
model is developed by data that are prepared in GIS
environment. Subsequently, the success of the predicted
outcome was assessed. As a result of this work is aimed to
obtain accurate information about the value of agricultural
land using mathematical modeling. The results show that real
estate prediction study using ANN was in good agreement
with absolute success value of 93% and correlation
coefficient (R2) value of %76.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Şükran Yalpır
Osman Orhan
Hari̇ka Ülkü
Gamze Sarkım
Güneri Ervural
The number of vehicles in our country is increasing
day by day. Therefore, the most important reason for traffic
accidentsis human. These accidents are caused by reasons such as
nuisance, insomnia, alcohol consumption, excessive speed, not
obeying traffic rules.
In this study, it is determined that the driver in the car is
drowsy. If the driver closes own eyes and yawning, alert system
gives a warning. In this real time application, eyes and mouth are
detected using Viola-Jones algorithm. Eyes and mouth according
to head movements are performed with Kanade-Lucas-Tomasi
algorithm. A counter is used for no iris detection on the eyes and
mouth is too more open state. These are using parameters in the
developed system. The developing prototype system works
successfully.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Furkan ÇAKMAK
Nesrin Aydın Atasoy
In core banking applications, delivering innovative ideas in a fast and reliable manner is extremely important for any corporation or organization. In the existing scenario, the result of increased competition between the companies and products, the core banking industry needs to better respond to dynamic market requirements, by offering new initiatives and services to better the user experience. This process needs to be minimal and with customer support interaction with technology in mobile and internet banking. In the past few years of financial industry, engineering education and knowledge are easy, intuitive for the user and provide the perfect customer experience. In the digital banking platform, the cutting-edge technology innovations and financial user experience designs create DevOps culture.
DevOps, which is a conceptual framework for the re-integration of development and operations in Information Systems, extends the agile methodology to create applications and deliver them across the environment in a fast and automated manner to improve the performance and the quality assurance. The approaches of Continuous Integration (CI) and Continuous Delivery (CD) are crucial for the practices of application development and release management. The objective of this paper is to create a proof of concept for management of systems that have a critical importance; quick and continuous copying of application files and database objects in a single package between Development, Test, Pre-Production and Production environments, integration with Load Balancer Systems, integration with request and call management applications, integration with source code management platforms, implementation of static code analysis and code review process, integration with automatic antivirus scan before testing, with only one automation for testing composed with built result application files for the creation automatic test process and definitions and only one platform structure that can make a new version deployment a release to many application architectures.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ahmet Sefa Oztas
Eren YEMEN
Ercan TUZUN
Appraisal of real estates which have a large important
for the country economics is pretty a hard occupation field. The
value of real estate indicates important level changes in
accordance with location and neighborhood features of their
places apart from legal and physical factors. Using value
prediction by explaining as mathematical these changes is a
complex problem. It is appropriate to use Geographical
Information Systems (GIS) application because of the size of the
study area in real estate valuation and the need to integrate the
attribute information into the map.
The purpose of this study is to provide using neighborhood
features affecting the value of real estate for mass appraisal. In
Centre Neighborhood of Konya, the neighborhood features were
taken into account, standardized with the help of GIS software by
producing the prediction and thematic maps in form of simple and
easy and made the ready form for valuation analysis. These maps
will be able to use as the base in all practices of valuation from
taxation to expropriation.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Şükran Yalpır
Fatma Bunyan Unel
The global problem of the growing city centres has many causes and requiring many different solutions. Existing urban infrastructures are having difficulty to meet the needs within the increasing population and urbanization of the cities. In this context, innovations must be made in many areas of the infrastructure of the cities such as Transport, Energy and Environment cleanliness. The most important increase due to the population growth in urban areas occurs in the traffic intensity. The number of vehicles increasing in traffic brings with it many new problems such as energy, time, and environmental pollution. Several field studies have been done so far to reduce and minimize traffic intensity. In this context, different solutions have been tried, such as speed controls, camera systems equipped with image processing techniques, and measures to reduce the intensity of intersection connections. As a result of interviews and determinations within the scope of this study, it is seen that traffic lights have a serious effect on traffic regulation.
In this study, the working principle of traffic lights was first investigated. In particular, the optimization and the techniques of signaling times of traffic lights have been examined. Traffic lights, which usually operate for a fixed period of time, can cause the vehicles to remain in traffic for a longer time and increase traffic intensity. Systems that operate according to the vehicle density cause very important improvements if they are operated through the appropriate mathematical model. In our work, queuing theory is mentioned, the application areas of theory are investigated and the data obtained from the field have been tested through this model. According to the queuing theory, the intensity of the intersection arms, the performance of the lights, arrival and the service ratios were obtained. With this study, it is aimed to bring a new approach to the density at the intersection of the city centers.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Fatih Güneş
Selim Bayraklı
Abdul Halim Zaim
Today, approximately 200 million people around the world are required to regularly check blood sugar levels every day, and this number is increasing day by day. If hyperglycaemia and hypoglycemia occur as a result of blood sugar level abnormalities, serious tissue and organ damage and, most importantly, vital risks can occur. In generally, blood glucose level measurement methods are divided into three categories, which are invasive, minimally invasive and non-invasive. In invasive methods people need to measure blood glucose levels by drilling their fingers, squeezing blood droplets on test strips and treating the results with portable glucometers. The process can be uncomfortable and complicated and has to be repeated many times each day. By using minimally invasive methods, the glucose ratio is determined by the help of tissue fluid or very little blood. Actually this method is uncomfortable for human life too. For this reason, there is a growing need for a new generation of non-invasive glucose-level monitoring systems in which the glucose level can be reliably determined. The goal of the ongoing works in literature are to prevent or delay early diagnosis and complications, rather than to treat the diabetes. This review giving a comprehensive knowledge about non-invasive design methods used in the literature.General definitions are given for each of the design methods. Scientists, laboratories and universities have been working on the design of non-invasive glucometer with various methods, yet there is no product that can measure with high accuracy.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ercan Mengüç
Selcuk Helhel
The importance of analysis high resolution satellite
imagery plays an important research topic for geographical
information analysis of cities. Geospatial data plays an important
role in important issues such as governmental, industrial, research
topics on traffic management, road monitoring, GNSS navigation,
and map updating. In this study, road detection from satellite
imagery methods are classified as classification-based, knowledgebased,
mathematical morphology and dynamic programming. In
the beginning, the road structures including feature and model are
analyzed. Then, the advantages and disadvantages of road
detection methods are evaluated and summarizez their accuracy
and performance based on road detection principles. Therefore, in
order to obtain remarkable results for road detection, it is better
to use more than one method. In after days, performing a complex
road extraction from a satellite image is still a necessary and
important research topic.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
İdris Kahraman
Ismail Rakıp Karas
Path planning problem plays an important role in mobile robot works. The robotic systems use intelligence algorithms to plan the path of the robot from one point to the other point. The main goal of path planning is to find the allowable movements of a robot in an environment with obstacles. These motions involve a path free of collision from the start position to the target position. In this study, Gray Wolf Optimization (GWO) algorithm was adapted to solve robot path planning problem. GWO algorithm imitates the hunting behavior and social leadership of gray wolves in nature. The leadership hierarchy consists of four grey wolf groups: alpha, beta, delta, and omega wolves. This algorithm comprises hunting mechanism with three stages: searching for prey, encircling prey, and attacking prey. In the test simulations of the robot path planning, we used a map with three circular obstacles. GWO algorithm was adapted to this problem. While finding the candidate solutions in path planning, three coordinate points are used between start and target points. For each iteration, these coordinate points are updated by GWO algorithm. If the solution point is in the obstacle zone, then violation is added to the cost function. The performance of GWO algorithm was evaluated with those of meta-heuristic algorithms for solving the robot path planning problem. The results obtained by GWO algorithm show that the optimal path is found for used test map.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Lokman DOĞAN
Uğur Yüzgeç
In recent years, intrusion detection (IDS) and
prevention systems (IPS) are vital in small and medium-sized
computer networks where data security is important. Examples of
these systems are Raspberry Pi (RasPi) computer with open source
IDS software. It is necessary to develop a rule-based architecture
in order to detect the attack by analyzing the traffic with this
system on a network. In this study, Snort IDS module has installed
on RasPi v3 computer and it has tried to measure alert
performance value according to the number of rules of developed
system. The scenario has that a total of an attack of 1 million data
packets, including one packet attack in 50 microseconds, to a
server on the network has been found to result in a nearly 15%
decrease in alert performance after about 7500 rules.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mustafa Coşar
H. E. KIRAN
This paper concentrates on a face biometric system
to investigate the face biometric and problems related to face
recognition under different illumination variations, pose and
partial occlusion. A face recognition system is developed to
recognize face images based on Principal Components Analysis
(PCA). The implemented scheme applies histogram equalization
and mean-and-variance normalization for image preprocessing
step to reduce the effects of the illumination. In order to improve
the recognition performance, we implement a feature selection
method based on Genetic Algorithm (GA). The implemented
method improves the recognition performance of system by
selecting the optimized sub set of PCA features and removing the
irrelevant data. Several datasets of ORL, FERET and BANCA
databases are used in order to test the robustness of the developed
face recognition system.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Omid Sharifi
M. Ç. YILDIZ
M. ESKANDARI
Detection of the breast cancer at the early stage has gained much attention over last decades. In this paper, a simulation study of a radar-based ultra-wideband microwave system is presented to detect breast cancer tumors. The main principle of this technique is based on the significant difference in the dielectric properties of malignant breast tumors and normal breast tissue in the microwave frequencies. The tumor’s electrical properties, in particular conduction and specific absorption rate (SAR), change significantly from those of healthy biological tissue when exposed to microwave radiation. In the measurements, a simple planar breast phantom that consisted low dielectric constant material to represent the fat tissue and high dielectric constant material to represent the tumor is used. An ultra-wideband and high gain antenna is used to measure electromagnetic field data for tumorous and non-tumorous breast tissue. According to the obtained results, the used antenna and microwave system are successful for detecting the breast cancer tumor. Measurement system is developed by using High Frequency Structural Simulator (HFSS) software. Antenna design parameters, properties of the breast phantom, analysis and measurement results are demonstrated and explained clearly in the paper.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ali Recai Çelik
M.Bahattin Kurt
Selcuk Helhel
The increasing population ratio in cities and the
increase in vehicle and pedestrian traffic due to this population
also brought problems with the transition of emergency vehicles
such as ambulance and fire brigade. The aim of this study is to
present solutions for problems with traffic congestion in vehicles
with transit superiority in an emergency. It is also intended to
provide wireless communication between traffic signaling lights in
operation and visual warning monitors used in designated
locations and emergency vehicles. When the route is determined
via the mobile device on the emergency vehicle, the traffic light and
the predetermined locations are communicated and the other
drivers in the traffic will be alerted in an audible and visual
manner. Since these alerts will make in advance in the area where
the traffic intensity is, traffic accidents would be resolve and the
emergency vehicles would be continue without losing time.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Selim Özdem
Songül OZUM
Over the last decade, agile practices become very popular amongst software development. According to one of the phrases of the Agile Manifesto “Working software over comprehensive documentation” sometimes could lead practitioners to the misunderstanding of “documentation is not valuable” or “not needed at all”. Because of this understanding from software community, agile practitioners do not give enough attention to architectural related documents. However, documentation is also a communication way between people and this communication should be also simple and lean considering agile principles. Commonly used traditional architectural documentation is very comprehensive and detailed. Creation and maintenance of this architectural documentation take too much effort for agile teams. Therefore, existing architectural template documents cannot serve agile teams in the best way. Rather than using existing architectural documents, this article presents a new lightweight architectural documentation template that can be used maintained easily in agile projects.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Caglar Cakir
Fatih Cetin
Mustafa Savasci
Oğuz Findik
Many robot competitions are organized in the national and international arenas. Many different robots compete in many different categories. The difficulties encountered during the competition are tried to be solved later in the competitions. This contributes to the development of automation technology. In this kind of competition, there are robot categories such as sumo robot, mini sumo robot, and line follower robot. Competitions can be done using tournament, elimination and ranking procedures. In this study, automation suitable for all three types of procedure has been developed and expert systems were used. Significant features of the automation include; tournament automation with dynamic elements completely dependent on the field of display, QR code creation and reading, bidirectional and multiple communication, SQL database connection and configuration.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Abdulkadir Gül
Emel Soylu
In this study, multi-objective vortex search algorithm (MOVS), a new multi-objective metaheuristic optimizer, has been used to solve 3 different constrained benchmark problems. The performance of the MOVS algorithm is compared with NSGA-II, is a well-known multi-objective evolutionary algorithm, on different performance metrics. Obtained metric results show that the MOVS is a promising algorithm for solving multi-objective benchmarks. This study encourages researchers working on constrained mathematical or real-world problems to use the MOVS algorithm.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ahmet Özkış
Gül Özcan
Ahmet Babalik
Mustafa Servet Kıran
Fast developing GPU technology
increases the performance of search algorithms
used to solve NP-hard problems. Travelling
Salesman Problem (TSP) is a well-known NP-hard
problem. In this paper, we parallelize a popular
swarm algorithm, Artificial Bee Colony, to solve
TSP. Proposed algorithm is tested on small scale
benchmarks obtained by modifying Mandl’s Swiss
Road Network. Proposed implementation is tested
by three experiments performed on a host PC and
a GPU card. The results are compared against the
results generated by the serial implementatio n,
which is executed on the host PC. Test results for
the fully connected benchmark show that the
proposed parallel implementation has increased
the performance of the computation up to 150
times compared to the serial implementation.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Fouad Asil
Mustafa Gök
Building effective schedules in academical institutions considering the wishes and needs of administrative staff, professors and students at the same time is a rather difficult and time-consuming activity for staff involved in this work. Despite improvements in software and hardware technology in recent years, charts are still manually created in many educational institutions and the desired efficiency has not achieved. In this study, the course chart of Mersin University Engineering Faculty was built using Ant Colony Optimization (ACO) technique. While the course schedule was being formed, 9 departments, 24 common classrooms, 105 faculty members, 239 courses, 14.374 students who have attendance obligations and 8286 students who have not attendance obligations were taken into consideration. In the placement of the courses, adaptation to ACO algorithm has been achieved by targeting the maximum lecture minimum classroom usage. The appropriate hours of the lecturers were accepted as strict constraints and other cases were added to soft constraints. All courses of Mersin University Engineering Faculty have placed the course schedule to appropriate classrooms at the rate of 99% using ACO technique, and 17 classrooms of common 24 classrooms were determined to be sufficient for educational activities.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Semir Aslan
Cigdem Aci
Image segmentation is one of the most tedious and
challenging research of image processing field and defined as the
partitioning of a given image to a finite number of nonoverlapping
regions such that every homogenous region is
connected through a sharp line. When segmenting an image, each
pixel is assigned a label so that similar labelled pixels have
certain visual characteristics. Image segmentation is a popular
image processing task for image interpretation and analysis.
Especially, the scope of medical image segmentation includes a
wide spectrum of subjects including locating tumors, measuring
tissue volumes, planning the treatment, enhancing the medical
images, diagnosis, image retrieval etc. For image segmentation
and/or other image processes, various color spaces are used:
RGB, CMYK, HSI and YIQ. Each color space was proposed for
specific purposes and each of them has certain advantages over
the others. Color image segmentation provides the user much
more information comparing to grayscale image segmentation.
This paper performs different medical image segmentations
using CIE L*a*b color space. Images are converted to L*a*b
color space and color difference idea is used to segment the user
selected regions. This paper also covers commonly used color
models such as RGB, CMYK, HSI and YIQ.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Emrah Irmak
The field of human computer interaction (HCI) involves the creation of interactive computing systems for humans to enhance the quality of life of people especially with disabilities all over the world. This study proposes a multimodal system to give the opportunity to carry out all daily works with a personal computer (PC) for disabled people that cannot use their hands. In this study, it's aimed to create an interaction between the user and a machine that is performed by user's voice and eye movements. Turkish Speech Recognition was performed by using mel-frequency cepstral coefficient (MFCC) extraction, hidden markov model (HMM) and artificial neural networks (ANN). As a joint part of the software, an efficient eye tracking system with a Tobii 4C eye tracker, was developed having a feature of eye blink detection for controlling an interface that provides an alternate way of communication. This multimodal system was developed by the authors using Java language and Matlab library and the system performed promising results for Turkish training words. To increase the system's performance, usage of natural language processing methods is planned as a future work.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Hilal Kaya
F.F. İÇEL
F. ÖZATAK
S. KARAKOÇ
O. SARIYER
In this study, it was designed to investigate with four
different artificial neural network (ANN) prediction models for
the concrete behavior containing zeolite and diatomite under the
effect of H2SO4. The constructing purpose of this model, 3
different mixes with 27 specimens of the 28, 56 and 90 days
splitting tensile strength experimental results of concrete
containing zeolite and diatomite. Those experimental results used
in training and testing for ANN systems were gathered from the
tests. The days (age of samples), Portland cement, zeolite,
diatomite, aggregate, water and hyper plasticizer as input data
parameters and splitting tensile strength of concrete as an output
parameter are used in the ANN models. The four different ANN
models have strong potential as a feasible tool for predicting 28,
56 and 90 days the splitting tensile strength of concrete containing
zeolite and diatomite in according to the training and testing
results.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Yılmaz Koçak
Gıyasettin Özcan
Muammer Akçay
Eyyüp Gülbandılar
The using and importance of web services that
flexibly meet the need for communication regardless of
parameters such as platform, operating system are
increasing day by day. In a simple sense, Web services carry
a lot of data because they provide communication. With the
increasing usage of web services and evolving technology,
various methods have been developed to conceal data, to
provide security and to prevent access by third parties in
web services. At the same time, attack and injection
methods for web service servers or web services have been
developed. Some of these methods exploit the fact that the
web services are XML-based. For example, XML injection,
XPath (which stands for XML path language) injection are
some of them. However, perhaps the most common type of
attack are DOS and XDOS attacks. The purpose of this
study is to gather the reasons of web service attacks, the
precautions to be taken against the attack, the solutions for
the exploits.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Furkan Sabaz
Yüksel Çelik
Technology evaluation is quite important field of technology management. Potential technology investments can be assessed thanks to technology evaluation methods in practice. Patent documents are extensively used for technology evaluation in the literature. The use of patent documents provides an objective evaluation of technology in real life engineering applications. In this study, patent documents are analyzed based on mining high utility itemsets. Mining high utility itemsets is a data mining approach. HUP-growth mining algorithm is one of the algorithm proposed for mining high utility itemsets in the literature. HUP-growth mining algorithm is utilized for the analysis of patent documents in this study. To show the application of the algorithm in the field of technology evaluation, all patents related to geothermal energy are retrieved from the United States Patent and Trademark Office (USPTO). The results obtained from this study show that HUP-growth mining algorithm can be easily and effectively used for technology evaluation based on patent documents.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Serkan Altuntas
Mehmet Sezer
In this study, the real time yaw and depth controller
of unmanned underwater vehicle (UUV) are performed
experimentally. Firstly, the mathematical model of UUV is
obtained. The controllers are designed based on mathematical
model data. Then, the controllers are performed based on
experimental data. Data transmission from vehicle is provided
with fiber optic cable which is connected operator console in the
experiment. This operator console is connected to computerwhich
has MATLAB inteface. Vehicle is controlled with proportional
(P)-integral (I)-derivative (D) designed in MATLAB/Simulink
environment. Communication between the vehicle and controller
is provided using MATLAB interface during the experiment. The
experimental controller responses are compared with the
controller response of mathematical model.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
E. ERTUĞRUL
A. DEMİR
Ö.ŞENYÜREK
Seda Karadeniz Kartal
The Salp Swarm Algorithm (SSA) is one of the recently proposed nature-inspired metaheuristic algorithms. SSA mimics the life cycle of salp swarms. Salp swarm is an animal group which lived in oceans. The navigating and foraging behaviors are the characteristic properties of the salp swarms. These behaviors are modeled as an optimization algorithmin SSA and it is firstly proposed for solving continuous optimization problems. In literature, there is no binary version of this algorithm which uses transfer functions. In this work, SSA is modified for solving binary optimization problems by using transfer functions. Transfer functions are used to convert the continuous decision variables to the binary decision variables. With this modification, the structure of SSA has not been changed, but only the Sigmoid and the Tangent Hyperbolic transfer functions are adapted. In order to validate the performance of the proposed binary SSA, a well-known pure binary optimization problem, uncapacitated facility location problems (UFLP), set is considered. UFLPs are used for a benchmarking of many metaheuristic algorithms such as; artificial bee colony, tree-seed algorithm, particle swarm optimization, differential evolution and artificial algae algorithm. The experimental results of 12 UFLPs are compared with each other and state-of-art algorithms. Experimental results demonstrate that the SSA is a promising solver for lower dimensional problems, but its performance should be improved on higher dimensional problems.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ersin Kaya
Ahmet Cevahir Çınar
Oğuzhan Uymaz
Sedat Korkmaz
Mustafa Servet Kıran
In this study, specific absorption rate (SAR)
simulations of rat model have been carried out by using a finite
integration technique (FIT). Although FIT is similar with finite
difference time domain (FDTD) method in most ways, an integral
form of Maxwell’s equations are used in the FIT method. A
monopole antenna working at 900 MHz has been designed for the
electromagnetic source. Conductivity and permittivity of tissue
have been selected from realistic values and implemented for the
voxel based rat model.
Simulations have been implemented with the 5 W stimulation
power. Aforementioned antenna has been located at 3.5 cm and 5
cm away from the nearest point of the rat model, respectively.
Total SAR values are found as 0.483 W/kg for the 3.5 cm distance
and 0.315 W/kg for the 5 cm distance. Maximum SAR induced at
a head region as it is expected. Furthermore, cross section of the
head and body results indicate that induced SAR vary in different
parts of a body because of electrical properties of each tissue. As
the distance of the antenna increases, the SAR value decreases.
Results show that average SAR value in 1 gr rat tissue is higher
than the value in 10 gr rat tissue.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
K. ATES
H. Feza Carlak
Sukru Ozen
A well balanced dataset is crucial for the performance of the data mining classification algorithms. In medical datasets, the percentage of normal labeled classes is higher than the percentage of abnormal labeled ones, which is called as class imbalance problem in data mining. If training dataset is imbalanced, the classification algorithm generally predicts the labels of the majority class instances correctly and the minority class instances incorrectly which leads to a major problem for artificial intelligence based medical diagnosis systems. To overcome this problem, many researchers proposed over-sampling and under-sampling techniques in the literature. Over-sampling techniques increase the number of minority class instances, where the randomly chosen instances from minority class is duplicated and added to the new training dataset or synthetic instances are generated from the minority class. Under-sampling techniques decrease the number of majority class, where the randomly chosen subset of majority class is combined with the minority class instances as the new training dataset. In this study, the effect of over-sampling and under-sampling techniques in medical datasets is examined. For the experimental study, several medical benchmark datasets and well-known classification algorithms are used.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Mehmet Hacibeyoglu
Mohammed Hussein IBRAHIM
In recent years, ransomware have become one of the most important threats facing both individuals and organizations. Attackers use strong encryption methods to create dangerous and comprehensive malware, making their ransom software flawless. Surveys indicate an increase in the number of assailants in parallel with the increase in the number of victims and the increase in illegal income. In the early years, especially at the risk of individual ransom viruses, more complex attacks are now beginning to appear that lead to the encryption of multiple machines targeting companies and every device connected to the Internet. In this study, ransom virus attacks against Internet of Things (IOT) network which is formed by connecting multiple devices with each other are examined and a study is presented about the measures to be taken.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Semih Gençay
Yüksel Çelik
The importance of immovable value in urban areas
increases day by day. The immovable valuation is a planned,
disciplined and a wide-ranging subject. In this study, the
immovable value changes created by the changes in the properties
of the buildings and the immovable properties of the urban
structures from the past to the present day are examined. Plants
and buildings, which form the basis of urban construction of the
application, have been used together.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Şükran Yalpır
SÜleyman Şişman
Ali Utku Akar
There are many qualitative and quantitative decision-making criteria in supplier selection (e.g., cost, quality, service or lead time). The today’s business environment requires choosing the right supplier with the environmental concerns in addition to the well-known selection criteria. We claim that a supplier selection accounting for the environmental concerns increases the supply chain responsibility, e.g. customer satisfaction, cost reduction and a clean environment. Therefore, we introduce a multi-criteria decision-making problem accounting for the environmental and social indicators that might be used to select the supplier of a wood glue which does not contain environmentally hazardous substances. A real-life case encountered in the furniture industry, is analysed with an expert choice software using the analytic hierarchy process decision making methodology.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
B. BALIBAS
Çağrı Sel
Nowadays everyone is trying to record the moment everywhere and wants it to be perfect. Beyond resolution, there is a desire to get steady shots regardless of the environmental conditions. The gimbal stabilization system ensures a stable image by blocking motion-related vibrations before they are transferred to the camera lens axes. Thanks to the Three Axis Gimbal, perfect images can be achieved by minimizing the vibrations while jogging, climbing or coming down stairs, cycling, or using any kind of vehicle. In short, a three-axis gimbal can be integrated everywhere a fixed image is needed. It is envisaged that gimbal stabilization system will be needed in many scientific studies in the following periods.
The aim of this study is to present the Three Axis Gimbal mechanism. Three separate brushless servo motors are installed on each axis for absorbing unwanted movements. The gimbal is also equipped with an inertial measurement unit consisting of a gyroscope and accelerometer close to the camera mount point. The general control system and PID controller are simulated by using MATLAB and the results are shown graphically.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Emi̇ne Dere
M.OZCAN
Süleyman CANAN
Quadratic Assignment Problem (QAP) is based the facilities allocation, and it is a difficult combinatorial optimization problem. The objective of this problem is to make total assignment cost minimum while being assigned facilities to locations that are already known. To solve this problem, the different methods are used in the literature. Meta-heuristic algorithms are ones from these methods and in this study, we present a new version of recent antlion optimization algorithm for QAP. AntLion Optimization (ALO) algorithm was developed by Mirjalili in 2015. ALO algorithm is based on the hunting behaviour of the antlion. This algorithm comprises five stages: random walking mechanism, constructing trap, trapping in the antlion’s pit, sliding ants in the pit, catching the prey and reconstructing the pit. Although ALO algorithm is successful in benchmark functions of multi dimensions, it has got some drawbacks. The most notable improvement is the use of tournament method instead of roulette wheel method. In ALO algorithm, the antlion is chosen from the population by roulette wheel method for using in each ant's random walking model. The roulette wheel method is more successful in maximization problems. In the minimization problems, the tournament selection method is more efficient method than the other selection methods Therefore, we used the tournament selection method in this study instead of the roulette wheel method on random walking mechanism. This proposed algorithm has been called the tournament selection based antlion optimization algorithm (TALO). To evaluate the performance of TALO algorithm, we used well-known meta-heuristic algorithms. The results provide the proposed TALO algorithm has the best performance in comparison with those of the other algorithms.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Haydar Kılıç
Uğur Yüzgeç
Keeping the quality goals in software is not a matter of chance. It needs proper planning and continuous attention of the development team. The main responsible for achieving the quality goals is the software architect. The architect needs to contribute in: clarifying and defining the goals, make a design that maps the required quality. However, that’s not enough. The architect needs to govern all development and test activities to move towards the goals in harmony as a team. In the end, software quality depends on the design decisions, implementation and the also definition of the goals itself. A process for tracking the architectural quality is presented in this paper with an analogy to the development processes: “V Model” and “W Model”.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Onur Taviloglu
Fatih Cetin
Nowadays, it is tried to predict the future events through the data. Practical areas such as deep learning are primarily trying to regulate data, and then these data are used for estimation. There are many algorithms used in this area. Besides these algorithms, artificial neural networks are also widely used in this field. ANFIS is a special network that uses artificial neural network and fuzzy classifier. It computes the output by distributing the input data blurred by the membership functions with the fuzzy rules on the network. Some parameter values need to be set in ANFIS. In this study, ANFIS networks will be trained with the Whale Optimization Algorithm, one of the current swarm-based meta-heuristic algorithms to find suitable parameter values and evaluation will be made on sample problems.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Murat Canayaz
Recep Özdağ
In this study, the Opposition based learning Spiral Optimization Algorithm (OBLSOA) is presented for training Multi-Layer Perceptron (MLP). The main idea of Spiral Optimization Algorithm (SOA) is based on the dynamic step dimension in its spiral path trajectory. The primary opposition based learning (OBL) concept first was come from the Yin-Yang symbol in the ancient Chinese philosophy. According to OBL concept, if a candidate point is far from the solution, the opposite point of this candidate can be closer to the solution than that point. We applied OBL concept to spiral optimization algorithm for training MLP. OBLSOA comprises two main stages: the first is the opposition-based learning population initialization and the other is opposition-based learning generation jumping. To evaluate the performance of the proposed OBLSOA, we used eight standard datasets including four classification datasets (XOR, balloon, Iris, breast cancer) and three function-approximation datasets (sigmoid, cosine, and sine). The performance proposed OBLSOA was compared with the original SOA for all datasets in terms of the Mean Square Error (MSE) metric. The training and test results show that the proposed OBLSOA is able to be provide very competitive and effective in training MLPs.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Uğur Yüzgeç
Cihan Karakuzu
Network coding has emerged as a paradigm for communication systems in which each intermediate node in the network generates and transmits output data by encoding previously received packets in a manner to increase the bandwidth efficiency of the system. The multiple access relay channel (MARC) is one of the real-world reference network coded communication scenarios where multiple users transmit data to a common destination through the use of one or multiple relays. In this paper, performance of demodulate and forward protocol which is among the prominent digital relaying techniques is considered in MARC systems. A convolutional code is used as the channel code. Maximum likelihood (ML) detection and user selective relaying are utilized in order to decrease the performance degradation due to decision errors at the relay. The simulation results obtained for Rayleigh fading channels have shown that the examined joint channel-network coding approach is superior with respect to non-cooperative system by providing full diversity gain.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ozgur Ozdemir
Every new development in the field of software engineering opens new possibilities for education practices and engenders new opportunities for learning environments. In the world of rapidly developing information technology, cloud computing has given new directions to the structures of traditional learning management systems. Today online learning, as a form of distance learning or e-learning, has developed the capacity of organizations to reach more students than in a traditional classroom setting via scalable online services mainly thanks to cloud-based software solutions. Moreover, organizations have become more equipped with the help of sharing resources and gained enrichment by avoiding large expenditure on hardware and software for the required learning management systems. This work-in-progress study tries to analyze and summarize some trending features directly related with cloud-based learning management systems.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Hakan Özcan
B. G. EMİROĞLU
Sign language recognition is used to help communicate effectively between normal hearing peoples and hearing-impaired. According to literature review, Turkish sign language recognition studies are very few. For this reason, this study has been performed on Turkish sign language recognition. Depth cameras, such as the Leap Motion controller, allows the researchers to exploit depth knowledge to better understand hand movements. In this study, data of 10 letters in Turkish sign language was taken from Leap Motion. Five of these data are composed of letters (I, C, L, V, O) that It can be expressed with one hand, while the other five are composed of letters (B, D, M, N, K) that It can be expressed with two hands. The dataset was taken by two different people. Each person made five trials for each letter. Ten samples were taken at each trial. In this study, Artificial Neural Network, Deep Learning and Decision Tree based models were designed and the effectiveness of these models in recognizing the Turkish sign language is evaluated. Regression (R), Mean Square Error (MSE) and Estimation Accuracy performance metrics are used to evaluate models' performance. The data set was randomly divided into 30% for training and 70% for testing. According to the experimental results, the most successful models for the data set with 120 features are decision tree and DNN models. For the data set with 390 features, DNN is the most successful model.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Abdulkadir Karaci
Kemal Akyol
Yasemin Gültepe
In this study, we analyzed the hyper-parameters
which are frequently used in deep learning methods on a generated
DNN. On the Fashion-MNIST dataset, we had chance to interpret
the evolution of the model to the end as a result of tests performed
on a low epoch number. At the end of the study, we reached a
success rate of about 90 percent on the test data and showed that
the selected hyper-parameters by created model were the most
accurate.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Yusuf Yargı Baydilli
Ü. ATİLA
In this study, we presented the use of the A-Star algorithm to find the shortest path between a starting-point and ending-point on the map which is taken from Google Maps and segmented as grid-cells. The active paths on Google Maps are specified in the Algorithm Map by dividing into grids, and it is desirable to find the shortest path from the A* algorithm. In addition, the traffic intensity of various roads is shown on the Google Maps. This information is processed on the Algorithm Map so that the algorithm can find the shortest route by considering traffic density.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Emi̇ne Dere
A.DURDU
The use, interest and analysis of e-sales systems are growing by the innovations the internet data processing technologies. Institutions, which want to provide better services to the customers, must first handle the demands, needs, and requirements of the customers. State Supply Office is an institution that meets to a large extent of purchasing needs of institutions in Turkey. In this study, a scorecard was created for each customer by segmenting the customers using recency, frequency and monetary (RFM) analysis method on the state supply office dataset. These scorecards were used to determine which the customers are loyal and which customers are being lost. Then, Apriori Algorithm was utilized to conduct a joint analysis on the products purchased by the lost customers for tendering campaigns and discounts. In order to regain the lost customers, the campaign and discount schemes were constructed considering scope of the right products obtained by the Apriori Algorithm.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Hasan Ali Türköz
İsmail Babaoğlu
The main objective of this study is to automatically extract tea gardens from large geographic areas using high-resolution digital orthophoto maps. To achieve this objective, object-based image analysis and decision tree (DT) classifier were integrated. For segmentation, multi-resolution image segmentation algorithm was used which is implemented in Definiens Developer commercial software. Both scale and compactness parameters were empirically calculated that produced optimal results. The segmented objects were selected manually for training the DT classifier from all used images. Spectral and textural features were extracted from each segment and to make the features robust against local variations, they were extracted at two image scales and final feature vector was formed by averaging the two feature vectors. The selected optimal features were used to train the DT classifier and then applied it on the test data to generate thematic maps for tea gardens. The performance of the proposed method was evaluated by comparing results with the reference data that produced promising results for mapping tea gardens (overall accuracy 88%) on our dataset.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Akhtar Jamil
B. BAYRAM
Target detection and tracking in video data is a complex problem. Especially for designing and developing surface to air tracking systems should be dealt with this problem strictly. In this study a combination of an image processing technique and Probabilistic Multi-Hypothesis Tracker (PMHT) is used. The target is discriminated from the video data for target initiation. In the subsequent steps the same discrimination method is used to obtain proper data for track continuation. For target identification from video data a transformation is used and target based pixels are discriminated from the background. Then image is transformed into point measurement data with amplitude information. Thus, video data is made suitable for tracking with PMHT. The resulting algorithm performs target detection and tracking operations automatically.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ahmet Pakfiliz
Nowadays, many mobile applications have proposed to provide healthcare service. One of the most important healthcare problem all over the world is failure of the early detection and treatment of visual impairment. In this study, we have developed VisualDetector, a low-cost, user friendly and mobile visual impairment detection system which has two components. First component is an integrated circuit attached to the smartphone that measures the distance between user and smartphone, then, sends the measured distance to the smartphone via Bluetooth. Second component of VisualDetector is android-based mobile application that interacts with the user by executing vision tests. VisionDetector can detect visual acuity and colorblindness problems of the user without requiring to go to an eye clinic. Thus, early detection of visual impairment can be possible, and the expense of treatment will be decreased. The results indicate that our proposed system has a potential to use as an early detection tool for visual impairment.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Yasin Ortakcı
Alperen Toksoz
Burak Keskin
In this work, a new system depending on a device that can encode and decode push-button signals, modulated using Morse code conventions, were developed to build a low-cost communication medium based on Internet of Things (IoT). The proposed system consists of two parts: a base station and handheld terminals. The base station is a single board computer with a web application based on Node.js. Handheld terminals are small battery powered devices, developed using MCU's, that can communicate with the base station over the wireless network. They can encode and decode Morse code, and convert to text or speech depending on the configuration of the terminal, which can be extended by using different add-ons, such as an OLED screen or a text to speech module. Communication between terminals is orchestrated by the base station using IoT Technologies like MQTT. The handheld terminals can be used by disabled people as a mean for private conversation, or a gadget for entertainment purposes. The system is an uncomplicated and low-cost communication medium and implemented to find alternative use cases for the IoT technologies.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ovunc Ozturk
Yunus Emre Küçük
Ahmet Yalnız
3D models of scenes are widely used but reconstructing them in 3D is a challenging task. The task generally starts from data acquisition and ends with 3D model of the scene. There are various methods to achieve the task but most of them don’t offer a suitable solution for large scenes and implementing them is laborious even in the case of a small scene. The document is prepared to propose a solution to these problems and explain a project which implements the solution. The solution benefits from two approaches; a multi-agent drone system and an image based 3D reconstruction pipeline. These approaches and how the project implements them are explained in details.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Metehan Aydın
Erkan Bostanci
Mehmet Serdar Guzel
Internet of Things has entered our lives as many forms and devices and enabled us to connect even the smallest-size devices to the internet. This progression aided us by deploying sensors on the workspace we need, such as hospitals, buildings, all sort of vehicles, logistics, even automated manufacturing and factories. In terms of quantity, around 8 billion of sensors are connected to IoT systems by 2017. These sensors may be utilized in many ways, such as emergency reporting and data collecting. IoT mesh networks function not only in normal conditions, even in emergency situations such as climate disasters, fire, flood, earthquake, tsunami, war or terrorism-related nuclear, biological or chemical attacks or conventional attacks. Such circumstances cause mass panic and chaos resulting in serious consequences unless contained and controlled. In this study, we propose a conceptual design of a functioning prototype which has the operational ability to provide an auxiliary network connection, as well as detecting Internet of Things devices in the area of disaster, collecting IoT device info and providing a mobile WAN access to the user.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
B.KAYMAZ
T.ERCAN
Since the beginning of the 21st century, there have been revolutionary developments in technology with Industry 4.0. Artificial Intelligence has become a part of daily life in many fields, complex software has become capable of working in real time on devices such as mobile phones. Such advances in the technology get together humanity to Augmented Reality. In this field, both developed software are used for many purposes such as game, tourism, travel, medicine, military, industry, entertainment and education. In this study, a mobile application based on Augmented Reality working in both indoor and outdoor environment is presented in the architectural field.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
M.OKUR
M. BULUT
Y. SANTUR
In this study, we intended to recommend possible books to be checked out from Seattle Public Library (SPL) within a month. While it seems possible to make daily estimates from existing data, it will be more useful to make monthly data forecasts since SPL provides fresh data every month. The information obtained here will contribute to logistic modelling. Since some assumptions on the location of the books and storage capacity of each location are required for the better management of the resources, this problem can be considered as a warehouse resource allocation problem. In order to perform the required predictions, Naïve Bayes (NB) algorithm is applied on the Seattle Public Library Dataset (SPLD), which contains all of the checkout records between 2005 and 2017 in the SPL.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
A.KARAMANLIOĞLU
A. ÇETİNKAYA
A.DALKIRAN
M. KOÇA
A.KARAMANLIOĞLU
In this study, the world's largest graphics card manufacturer Nvidia's deep learning assisted drawing software tool "GauGan" has been investigated. GauGan which is firstly announced Nvidia GPU Technology Conference (GTC 2019) is basically a drawing tool. The difference between the other drawing tools is that it can transform simple drawing lines into realistic nature pictures by using deep learning. It is improved on previous drawing software tool which is called "pix2pixHD”. Nvidia has announced that it will use 1 million images on the Flickr platform as a set of data for the development of Deep Learning.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Y. SANTUR
In production systems, one of the main part routing problems is the determining the best process sequence and the
best machine-operation pairing. In real world systems, flexibility
is important to provide alternative part routings. The system is
considered flexible when certain operation of a part can be
processed on more than one machine. However, flexibility
increases the complexity of system. This paper deals with
assignment of operations to a machine and determining the best
process plan for each part under flexible environment. We used a
harmony search algorithm to cope with highly complex and
nonlinear problem in which makespan is considered as the
objective function and evaluated by using a simulation model.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ayşe Tuğba Dosdoğru
Aslı Boru
Mustafa Göçken
With the digital transformation era that we are in, the
systems that we physically process are now transferred to
electronic systems. In these days, Bitcoin [1] that is concept of
virtual money which is one of the popular topics entered our lives.
It is an end-to-end digital payment system over a decentralized
network. This system works with the Blockchain algorithm. We
can apply this technology to other areas in our digitalized life not
only to money transactions. In this project, electronic election
system is proposed and designed using the Blockchain technology
and preserving privacy.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
B. ESEN
M. ÖZKURT
İlhami Muharrem ORAK
Underwater sensor networks (UWSNs) are
composed of a certain amount of sensors and/or vehicles that
interactively glean data from underwater environment and
cooperatively perform predetermined tasks. Each of these
battery-limited sensors dissipates a considerable amount of
energy during sensing, communicating and data processing
activities, where replenishing the drained batteries is impractical
and time consuming, and interrupts the ongoing communication.
Therefore, energy conservation and routing strategies are vitally
important for accomplishing a certain task for a particular
underwater application. In this paper, we review the recent
advances in UWSNs, including their applications and joint
routing optimization and energy conservation techniques.
Finally, several appealing directions for future research on
UWSNs are presented.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Halil YETKİN
Faced with the growing demand for quality products
in markets and industries in agricultural sectors . from
consumers, sellers, and producers. The research aims to
respond to this, by using effective and efficient
technologies, namely image processing and computer
vision, to automate the process of inspection and
evaluation of the quality of agricultural products.
Conducted for many years by human experts. The use of
these technologies concerns both the detection of fruit
diseases and their classification. To follow this concept,
we chose to focus our work on fruits classification. whose
purpose is to separate infected fruits from those that are
not affected. However, based on the concepts of
computer vision, the proposed technique is centered on
three steps. The first step concerns preprocessing and
segmentation, in which, we resize and improve the
quality of the images. The second step involves, deep pretrained
models (Alex-Net), these are used for the
extraction of the features in the different fruits (banana,
apples, oranges). And finally, we performed the
classification, by using multi-class SVM. The studies
were conducted on the public dataset, the Kaggle dataset,
to obtain a 99.50% classification accuracy and on a new
dataset for a accuracy of 85.7%. The results clearly show
that the proposed method works well in terms of
improvement in classification accuracy and precision.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Rhudie Grace Zang Edzang
Mehmet Göktürk
In this study, it is aimed to estimate the fatigue life of
magnesium alloy by an artificial bee colony algorithm. Since notch
factor, stress rate and stress amplitude factors influence the
fatigue life, mathematical function models have been utilized for
the solution of the problem and the parameters of the function
optimized with artificial bee colony algorithm. The predicted
results were compared with the experimental results. These results
show that heuristic algorithms can be successfully applied in
fatigue life estimation.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
S. KARAGÖZ
C.B. KALAYCI
Ö. KARAKAŞ
Automated recognition and classification of bacteria
species from microscopic images have significant importance in
clinical microbiology. Bacteria classification is usually carried out
manually by biologists using different shapes and morphologic
characteristics of bacteria species. The manual taxonomy of
bacteria types from microscopy images is time-consuming and a
challenging task for even experienced biologists. In this study, an
automated deep learning based classification approach has been
proposed to classify bacterial images into different categories. The
ResNet-50 pre-trained CNN architecture has been used to classify
digital bacteria images into 33 categories. The transfer learning
technique was employed to accelerate the training process of the
network and improve the classification performance of the
network. The proposed method achieved an average classification
accuracy of 99.2%. The experimental results demonstrate that the
proposed technique surpasses state-of-the-art methods in the
literature and can be used for any type of bacteria classification
tasks.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Muhammed Talo
Property value is a reflection of locational, physical,
legal and economic factors. Spatial factors are the most important
factors among evaluation criteria. Geographic Information
System (GIS) provide capable tools that can be used to record
spatial information about value properties. The purpose of this
study is to developing a property valuation GIS tool, which
capable to estimate residential properties values. To achieve this
objective, tabular data was developed that geographically
represent of property information factors. Then, multi criteria
decision analysis MCDA used to evaluate the property value. The
tool capable to generate property values as percentage in the
tabular data. In this study, Safranbolu-Turkey region has been
studied. The property value influence factors are distance to main
roads, distance to markets, distance to child parks, distance to
schools, age of building, floor of building and distance to city
center. The tool capable to help Safranbolu municipality to
generate property evaluation for priced fair pricing, renting,
buying or taxation and based on the data updating.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
S.K.M. ABUJAYYAB
I.R. KARAS
C. AKICI
G. OZKAHRAMAN
Online marketing platforms have turned into large
volumes of information and opinion for customers with the
transition to Web 2.0. Customers refer to these resources in order
to obtain information before they purchase a product and to reach
the potential views of others about possible experiences. Businesses
also need customer feedback to improve the services they provide
and to explore which reviews are more valuable product
specifications. In this study, Sentiment Analysis (SA) was
performed with 2-pole (positive-negative) classification about
hotel businesses on an opinion dataset created by users. Deep
Learning based Recurrent Neural Network (RNN) architecture
was used in these analyzes. With the results of the RNN
architecture, the results of the classification based on score
conditional and editorial interpretation were compared and it was
observed that the performance of classification with RNN was
successful.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Kürşat Mustafa KARAOĞLAN
Volkan Temizkan
Oğuz Findik