Nafiseh Sedaghat - Islamic Azad University,Mashhad Branch
Mohammad-Bagher Naghibi Sistani - Ferdowsi University, Mashhad
Mahdi Yaghobi - Islamic Azad University

This paper presents chaotic genetic algorithm to fuzzy rule extraction for function approximation. The chaos is a general phenomenon in nonlinear system and has some special characteristics such as ergodicity, regularity, randomicity, and acquiring all kinds of states in a self-rule in a certain range. It has such sensitivity that a tiny change of initial condition can lead to a big change of the system. Chaos optimization algorithms as a novel method of global optimization have attracted much attention; and therefore we use it with genetic algorithm to optimization of fuzzy rules. As a case study we use CGA to fuzzy rule extraction based on patterns for function approximation. Results show good performance of CGA as a global search technique in comparison with most recent approaches bacterial memetic algorithm (BMA) and bacterial evolutionary algorithm (BEA).

Chaos, Optimization, Approximation,Fuzzy rule