A new traversing and execution algorithm for Multilayered Fuzzy Cognitive Maps

This paper introduces a new algorithm for traversing and executing multilayered fuzzy cognitive maps (ML-FCMs) that aim to enhance this methodology, which is designed for handling complicated large scale problems. The methodology is based on the decomposition of the parameters of the problem under investigation into smaller quantities, organised in a hierarchical structure forming a multilayered FCM model. The present work aspires to eliminate the weaknesses of the existing ML-FCM algorithm, which reside in the way activation levels are calculated for those concepts decomposed into a set of parameters at lower layers in the map. The current algorithm calculates these levels by completing a full iteration cycle at the lower level thus losing the information produced between the iterative steps. We attempt to solve this problem by introducing the enhanced ML-FCM algorithm, (EML-FCM) which allows calculations in-between iterations and takes into consideration the change of activation levels in a more detailed form. The strong features of the proposed EML-FCM algorithm are presented and discussed, in addition to the provision of a comparison between the two algorithms.