A Novel Multi-population Particle Swarm Optimization with Learning Patterns Evolved by Genetic Algorithm
In recent years, particle swarm optimization (PSO) and genetic algorithm (GA) have been applied to solve various real-world problems. However, the original PSO is based on single population whose learning patterns (inertia weights, learning factors) has no potentials in evolution. All particles in the population interact and search according to a fixed pattern, which leads to the reduction of population diversity in the later iterations and premature convergence on complex and multi-modal problems. Therefore, a novel multi-population PSO with learning patterns evolved by GA is proposed to improve diversity and exploration capabilities of populations. Meanwhile, the local search of PSO particles which start in the same position also evolved by GA independently maintains exploitation ability inside each sub population. Experimental results show that the accuracy is comparable and our method improves the convergence speed.
KeywordsCo-evolutionary computation Genetic algorithm Particle swarm optimization
This work was supported by National Natural Science Foundation of China under Grant No. 61573166, No. 61572230, No. 81671785, No. 61472164, No. 61472163, No. 61672262. Science and technology project of Shandong Province under Grant No. 2015GGX101025. Project of Shandong Province Higher Educational Science and Technology Program under Grant no. J16LN07. Shandong Provincial Key R&D Program under Grant No. 2016ZDJS01A12, No. 2016GGX101001.
- 2.Kennedy, J., Eberhart, R.C.: A new optimizer using particle swarm theory. In: Proceedings the Sixth International Symposium on Micromachine and Human Science, pp. 39–43 (1995)Google Scholar
- 3.Kennedy, J., Eberhart, R.C.: Particle swarm optimization. In: Proceedings of IEEE International Conference on Neural Networks, Perth, Austria, pp. 1942–1948 (1995)Google Scholar
- 15.Arabas, J., Michalewicz, Z., Mulawka, J.: Genetic algorithms with varying population size. In: Proceedings of the 1st IEEE International Conference on Evolutionary Computation, pp. 73–78 (1994)Google Scholar
- 23.Liu, J., et al.: 3D feature constrained reconstruction for low dose CT imaging. IEEE Trans. Circuits Syst. Video Technol. (2016)Google Scholar
- 24.Liu, C.L., Liu, H.W., Yang, J.Y.: A path planning method based on adaptive genetic algorithm for mobile robot. J. Inf. Comput. Sci. 8, 808–814 (2011)Google Scholar
- 29.Wang, L., Orchard, J.: Investigating the evolution of a neuroplasticity network for learning. IEEE Trans. Syst. Man Cybern. Syst. 1–13 (2017)Google Scholar
- 33.Cao, X.B., Luo, W.J., Wang, X.F.: A co–evolution pattern based on ecological population competition model. J. Softw. 12, 556–562 (2001)Google Scholar
- 34.Wang, B., Gao, Y., Xie, J.: A genetic algorithms based on global coordination and local evolution. Comput. Eng. 31, 29–31 (2005)Google Scholar
- 36.Zhao, S.Z., Liang, J.J., Suganthan, P.N., Tasgetiren, M.F.: Dynamic multi–swarm particle swarm optimizer with local search for large scale global optimization. In: Proceedings of 2008 IEEE Congress on Evolutionary Computation, Hong Kong, pp. 3845–3852 (2008)Google Scholar
- 37.Suganthan, P.N., et al.: Problem definitions and evaluation criteria for the cec 2005 special session on real–parameter optimization. Technical report, Nanyang Technological University, Singapore and KanGAL Report Number 2005005 (2005)Google Scholar