SEARCH RESULT

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

Worldwide, vegetation cover functioning as the secure region for wild life, and natural water, air filter from pollution. Forecasting the vegetation dynamics assist the governments and managements to decrease the negative influence of vegetation dynamic fluctuations. In recent years, forecasting of precise vegetation dynamics become and highly important issue, due to rapid vegetation changings and the needs to protect this natural resource. The aim of this article is to forecasting the vegetation dynamics by applying neural networks (NN). Düzce region utilized as case study, which situated in the north west region of Turkey. Normalized difference vegetation index (NDVI) from Moderate Resolution Imaging Spectroradiometer (MODIS) were employed to create vegetation time series. From United States Geological Survey website, 300 NDVI interval data acquired and processed in ArcGIS software. The dataset of vegetation time series built based on required neural networks data structure. Spatiotemporal pixel based sampling strategy performed to forecast the vegetation dynamics. A number of geospatial data handling steps employed using Python and Matlab programing languages. Forecasting data separated to two subdivisions (training set, and testing set). Mean squared error (MSE) utilized as performance accuracy assessment metric. Neural networks effectively implemented using spatiotemporal data and achieve high testing accuracy. Consequences reveals the fitness of neural networks to forecast vegetation dynamics maps.

International Science and Engineering Application Symposium on Hazards
ISESH

S.K.M. ABUJAYYAB Ismail Rakıp Karas Emrullah Demiral