Numerical Coding and Unfair Average Crossover in GA for Fuzzy Rule Extraction in Dynamic Environments

In this paper, we propose a GA with a new crossover method appropriate for real value chromosomes, called the ”Unfair Average Crossover”, an automatic fuzzy rule extraction method that uses our GA and a real value chromosome coding method in which parameters in membership functions of fuzzy if-then rules are directly represented. It is shown that our method is superior to conventional methods using discrete chromosome coding in cases where there is a tendency for data to change dynamically.