Optimization in Genetically Evolved Fuzzy Cognitive Maps Supporting Decision-Making: The Limit Cycle Case

This paper presents the dynamic behavior of a hybrid system comprising Fuzzy Cognitive Maps and Genetic Algorithms, and focuses on the behavior observed when the system reaches equilibrium at fixed points or limit cycle. More specifically, the present works examines the theoretical background of the equilibrium and limit cycle behaviors and proposes a defuzzification method to handle the latter case. The proposed method calculates the mean value of a limit cycle and uses this value in the defuzzification process along with a confidence rate, which indicates the reliability of the results.