3 results listed
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
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
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 Cyber Security and Computer Science
ICONCS
S. BOULEHOUACHE
Selma Ouareth
Ramdane Maamri