Co-evolutionary genetic fuzzy system: a self-adapting approach

The ability of an algorithm to adapt its strategy during the search process is an important concept associated with models inspired by GAs. In this paper a self-adapting mechanism is proposed to enrich the performance of a coevolutionary genetic approach, devised to support hierarchical, collaborative relations between individuals representing different parameters of Takagi-Sugeno fuzzy models. The resulting self-adaptive co-evolutionary genetic fuzzy system represents an alternative to release user from arbitrarily defining evolutionary and fuzzy parameters. The performance of the proposed approach is compared with another co-evolutionary GFS based on fixed evolutionary parameters and other approaches via examples of function approximation problems.