An Efficient Immune-based Symbiotic Particle Swarm Optimization Learning Algorithm For Tsk-type Neuro-fuzzy Networks Design

摘要

In this paper, we propose a new learning algorithm that can be used to design TSK-type neuro-fuzzy networks. Though there has been a great deal of interest in the use of immune algorithms (IAs) for computer science and engineering, in terms of fundamental methodologies, they are not dramatically different from other algorithms. In order to enhance the IA performance, we propose the immune-based symbiotic particle swarm optimization (ISPSO) for use in TSK-type neuro-fuzzy networks for solving the prediction and skin color detection problems. The proposed ISPSO embeds the symbiotic evolution scheme in an IA and utilizes particle swarm optimization (PSO) to improve the mutation mechanism. In order to avoid trapping in a local optimal solution and to ensure the search capability of a near global optimal solution, mutation plays an important role. Therefore, we employed the advantages of PSO to improve the mutation mechanism and used a method that introduces chaotic mapping with certainty, ergodicity and the stochastic property into PSO to improve global convergence. Unlike the IA that uses each individual in a population as a full solution to a problem, symbiotic evolution assumes that each individual in a population represents only a partial solution to a problem. Complex solutions combine several individuals in the population.