FUZZY CLASSIFIER SYSTEM FOR CLASSIFICATION TASK

摘要

In this paper, we discuss a fuzzification of the classical architecture of a learning classifier system. In this paper, Fuzzy Classifier System (FCS) is used to automatically generate fuzzy if-then rules for pattern classification problem. First, we describe FCS where a randomly generated initial population of fuzzy if-then rules is evolved by typical genetic operations such as selection, crossover and mutation. Second, we apply a heuristic procedure for improving the performance of FCS and compare result of adding this heuristic procedure. The motivation behind this approach is that classifier systems will be capable of generating compact, high performance rule sets which are general and accurate.