Bounded Fuzzy Possibilistic Method

摘要: Abstract This paper introduces the Bounded Fuzzy Possibilistic Method (BFPM) by addressing several issues that previous clustering/classification methods have not considered. In fuzzy clustering, data object's membership values should sum to 1. Hence, any object may obtain full in at most one cluster. clustering remove this restriction. However, BFPM differs from and possibilistic approaches allowing function take larger with respect all clusters. Furthermore, BFPM, a can multiple clusters or even relaxes boundary conditions (restrictions) assignment. The assigned boundaries satisfy necessity of obtaining memberships overcome conventional (overlapping). functionality proposed method has been proved geometry, set theory, other disciplines, when learning provide important arithmetic operations on different domains. Weighted Feature Distance (WFD) is also used cover diversity. Validity comparison indexes applied evaluate accuracy BFPM. Conventional are compared BFPM-WFD, terms accuracy, fuzzification constant, norms, covering diversity overlapping. results show algorithms perform better than methods.