Title :
A Novel Dynamic Particle Swarm Optimization Algorithm Based on Chaotic Mutation
Author :
Yang, Min ; Huang, Huixian ; Guizhi Xiao
Author_Institution :
Coll. of Inf. Eng., Xiangtan Univ., Xiangtan
Abstract :
A novel dynamic particle swarm optimization algorithm based on chaotic mutation (DCPSO) is proposed to solve the problem of the premature and low precision of the common PSO. Combined with linear decreasing inertia weight, a kind of convergence factor is proposed based on the variance of the populationpsilas fitness in order to adjust ability of the local search and global search; The chaotic mutation operator is introduced to enhance the performance of the local search ability and to improve the search precision of the new algorithm. The experimental results show finally that the new algorithm is not only of greater advantage of convergence precision, but also of much faster convergent speed than those of common PSO (CPSO) and linear inertia weight PSO (LPSO).
Keywords :
chaos; convergence; particle swarm optimisation; search problems; PSO; chaotic mutation operator; convergence factor; convergence precision; dynamic particle swarm optimization algorithm; linear decreasing inertia weight; linear inertia weight; local search ability; Chaos; Convergence; Data engineering; Data mining; Educational institutions; Genetic mutations; Knowledge engineering; Particle swarm optimization; Particle tracking; chaotic mutation; convergence factor; dynamic inertia weight; particle swarm optimization;
Conference_Titel :
Knowledge Discovery and Data Mining, 2009. WKDD 2009. Second International Workshop on
Conference_Location :
Moscow
Print_ISBN :
978-0-7695-3543-2
DOI :
10.1109/WKDD.2009.142