Optimization of fuzzy systems using group-based evolutionary algorithm

摘要: This paper proposes a group-based evolutionary algorithm (GEA) for the fuzzy system (FS) optimization. Initially, we adopt an entropy measure method to determine number of rules. Fuzzy rules are automatically generated from training data by measure. Subsequently, GEA is performed optimize all free parameters FS design. In evolution process, coded as individual. All individuals based on their performance partitioned into superior group and inferior group. The group, which composed with better performance, uses global operation search potential individuals. worse employ local near current best Finally, proposed model (FS-GEA) applied time series forecasting problem. Results show that FS-GEA obtains than other algorithm.