The influence of samples on meta-heuristic algorithm for parameter estimation of chaotic system

Abstract

Parameter estimation of chaotic system is an important issue in nonlinear science. The meta-heuristic algorithm is one of the effective estimation approaches, and has received increasing attention. However, few people have noticed the influence of the samples on parameter estimation. In fact, when using meta-heuristic algorithm for parameter estimation, the number of samples will affect the efficiency greatly. In this paper, this problem is investigated. The relationship between sample and step size, and the factors that affect the difficulty of parameter estimation are also considered. Experimental results show that it is more efficient to set the samples to a small number, and the number of estimated parameters is the most important factor affecting the difficulty of parameter estimation. Finally, to improve the precision further, a new hybrid chaotic particle swarm optimization algorithm which combines a special inertia weight with chaotic search is proposed. Results demonstrate that the new hybrid algorithm is more effective than the other four meta-heuristic algorithms.