Mehdi N. Fesharaki

Learn More
The paper deals with a modification in the learning phase of AntNet routing algorithm, which improves the system adaptability in the presence of undesirable events. Unlike most of the ACO algorithms which consider reward-inaction reinforcement learning, the proposed strategy considers both reward and penalty onto the action probabilities. As simulation(More)
In this paper an improved version of Ant-Miner algorithm is introduced and compared to the previously proposed ant-based rule mining algorithms. Our algorithm modifies the rule pruning process and introduces a dynamic pheromone evaporation strategy. The algorithm was run on five standard datasets and the average accuracy rate and numbers of discovered rules(More)
Immune System is a complex system, has been consisting of complex elements with complex interactions, which has characteristics like autopoiesis and evolution. As a model for living systems, Capra Cognitive Framework introduces the main components of living systems. In this paper, functionality of the immune system is going to be perused and simulated(More)
The paper Describes a novel method to introduce new concepts in functional and conceptual dimensions of routing algorithms in swarm-based communication networks.The method uses a fuzzy reinforcement factor in the learning phase of the system and a dynamic traffic monitor to analyze and control the changing network conditions.The combination of the mentioned(More)
Having full and accurate situation awareness is a critical foundation of successful decision-making in network centric environments. Virtual collaboration, virtual organization and people coordination are the result of Situation awareness in net centric systems. On the other hand, having situation awareness reduces operation cost and risk and increases(More)
Increasing complexity and dynamics of systems has reduced the efficiency of security tools. For overcoming this problem, security tools introduce newer patches, thereby the size of database and computation overloads are increased. By Biological Immune System (BIS) modeling and simulation, its behavior in different situations will be considered and the(More)
Developing distributed data mining applications in decentralized environments requires services both to find the needed resources (data, algorithms, computing nodes) and to share the inferred knowledge among users after the data mining process has been performed. The need for an efficient implementation of such functionalities is of great importance in(More)
The paper illustrates an open comprehensive distributed framework for audio/video applications which is based on service oriented architecture. The presented architecture not only introduces a high level of transparency on networked environments, it also supports some important system attributes such as reusability, maintainability, flexibility and(More)