Improved Fuzzy Functions Based on A Genetic Fuzzy System

Modeling real -world situations has made use of systems for fuzzy inference that incorporate fuzzy rule bases (FRB). One of the limitations of these traditional fuzzy inference systems is the sheer amount of fuzzy procedures and operators that an expert needs to understand. In this work, we suggest an alternative schema for learning and reasoning that is based on fuzzy functions rather than if -then rule foundation structures. A novel fuzzy functions method optimized with biological algorithms is proposed to replace the fuzzy regulators and processes used by FRBs and increase the correctness of fuzzy models. The Improved Fuzzy Clustering (IFC) approach, a guided hybrid fuzzy clustering method that yields higher membership values, serves as the foundation for the new method's architecture identification. When creating fuzzy functions and improving them through evolutionary techniques, the proposed fuzzy functions methodology has the benefit of employing values for membership and other ambiguous details regarding the natural group of data samples as additional predictors. Comparison experiments utilizing real industrial and financial data demonstrate that the proposed approach is comparable or better in the modeling of regression issue domains.