Multi-objective evolutionary fuzzy cognitive maps for decision support

This paper proposes an extension of genetically evolved fuzzy cognitive maps (GEFCMs) used for decision-making, aiming at increasing their reliability and overcoming its main weakness which lies with the recalculation of weights corresponding to more than one concept every time a new multiple scenario is introduced. A new evolutionary approach is proposed to support multi-objective decision-making based on the introduction of a dedicated genetic algorithm (GA), which is responsible for finding an optimal weight matrix that satisfies two or more activation levels among the participating concept nodes. This evolutionary methodology is very appealing since it offers the optimal solution without a problem-solving strategy once the requirements are defined