Optimizing of Interval Type-2 Fuzzy Logic Systems Using Hybrid Heuristic Algorithm Evaluated by Classification

Abstract

In this research, an optimization of the rule base and the parameter of interval type-2 fuzzy set generation by a hybrid heuristic algorithm using particle swarm and genetic algorithms is proposed for classification application. For the Iris data set, 90 records were selected randomly for training, and the rest, 60 records, were used for testing. For the Wisconsin Breast Cancer data set, the author deleted the missing attribute value of 16 records and randomly selected 500 records for training, and the rest, 183 records, were used for testing. The proposed method was able to minimize rule-base, minimize linguistic variable and produce a accurate classification at 95% with the first dataset and 98:71% with the second dataset