LS-SVM Based on Chaotic Particle Swarm Optimization with Simulated Annealing
The generalization performance of LS-SVM depends on a good setting of its parameters. Chaotic particle swarm optimization (CPSO) with simulated annealing algorithm (SACPSO) is proposed to choose the parameters of LS-SVM automatically. CPSO adopts chaotic mapping with certainty, ergodicity and the stochastic property, possessing high search efficiency. SA algorithm employs certain probability to improve the ability of PSO to escape from a local optimum. The results show that the proposed approach has a better generalization performance and is more effective than LS-SVM based on particle swarm optimization.
KeywordsSupport Vector Machine Root Mean Square Error Particle Swarm Optimization Simulated Annealing Simulated Annealing Algorithm
Unable to display preview. Download preview PDF.
- Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceeding of the 1995 IEEE international conference on neural network, pp. 1942–1948 (1995)Google Scholar
- Eberthart, R., Kennedy, J.: A new optimizer using particle swarm theory. In: Proceeding of the sixth international symposium on micro machine and human science, pp. 39–43 (1995)Google Scholar
- Yi, D., Ge, X.R.: An improved PSO-based ANN with simulated annealing technique. Neuro-computing 63, 527–533 (2005)Google Scholar
- Zhang, C.K., Shao, H.H.: An ANN’s evolved by a new evolutionary system and its application. In: Proceedings of the 39th IEEE conference on decision and control, Sydney, Australia, pp. 3562–3563 (2000)Google Scholar
- Shi, Y., Eberhart, R.: Empirical study of particle swarm optimization. In: Proceedings of congress on evolutionary computation, pp. 1945–1950 (1999)Google Scholar
- Eberhart, R., Shi, Y.: Particle swarm optimization: developments, applications and resources. In: Proceeding of the 2001 IEEE International Conference on evolutionary computation, pp. 81–86 (2001)Google Scholar