Probabilistic fuzzy clustering algorithm for fuzzy rules decomposition

The Fuzzy C-Means (FCM) clustering algorithm is the best known and the most used method for fuzzy clustering and is generally applied to well defined sets of data. In this work a generalized Probabilistic Fuzzy C-Means (PFCM) algorithm is proposed and applied to fuzzy sets clustering. The methodology presented leads to a fuzzy partition of the fuzzy rules, one for each cluster, which corresponds to a new set of fuzzy sub-systems. When applied to the clustering of a flat fuzzy system the result is a set of decomposed sub-systems that will be conveniently linked into a Parallel Collaborative Structure.This work was supported by Fundação para a Ciência e Tecnologia (FCT) under grant POSI/SRI/41975/2001 and CITAB (UTAD)