Algorithm of behavior evaluation in multi-agent system

Abstract

Behavior based detection of unfavorable activities in multi-agent systems (presented in [3,4,5]) is an approach to the problem of detection of intruders. This approach refers to evaluation of behavior of every agent which exists in a multi-agent system. Process of behavior evaluation is distributed - every agent makes autonomous behavior evaluation of other agents. This means that an agent is evaluated separately by all agents in the environment of the secured system. That separate results of behavior evaluations have to be collected and an algorithm should be used in order to elect the worst agents which should be eliminated. Collecting and data processing of results of distributed behavior evaluations is the main topic of this article. © Springer-Verlag Berlin Heidelberg 2005.