Reduced fuzzy rule base design using Hybrid Elite Genetic Algorithm and Tabu Search

In this paper, Metaheuristic and Evolutionary algorithms have been widely used for optimal design of fuzzy systems. In this paper, we present new Hybrid Elite Genetic Algorithm and Tabu Search (HEGATS) learning algorithm for generating reduced knowledge base for fuzzy system. At each generation of Genetic Algorithm (GA), we calculate the best solution (elitist), this latter is introduced in Tabu Search algorithm to search its best neighbor solution which will be included in the new population of GA; this operation ensure the convergence of GA with a minimum number of generations. The algorithm dynamically adjusts the membership functions and fuzzy rules according to different environments. To demonstrate the effectiveness of the proposed algorithm, two numerical examples given in the literature are examined. Results prove the effectiveness of the proposed algorithm.