Mar. 25, 2009 to Mar. 27, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/UKSIM.2009.96
In recent years, Particle Swarm Optimization (PSO)has been used in data mining, feature extraction andother optimization based applications. Time to time, anumber of researchers have suggested modifications tothe basic PSO. Although this optimization techniquefinds good solutions much faster than the traditionaland evolutionary algorithms, they suffer from a majordrawback of premature convergence. In addition, ithas been found experimentally that the quality of thesolutions does not improve as the number of iterationsis increased. In this paper we discuss the reasonbehind the premature convergence. We present a newmethod based on performance-scoring for improvingthe algorithm The scoring based model is applied tothe basic and some of the modified versions of PSOmodels.
Particle Swarm Optimization ; Social network; Convergence; Constriction factor; Local best; Global best; Scoring factor
Satish Chandra, Rajesh Bhat, D.S. Chauhan, "A Score Based Method for Controlling the Convergence Behavior of Particle Swarm Optimization", UKSIM, 2009, Computer Modeling and Simulation, International Conference on, Computer Modeling and Simulation, International Conference on 2009, pp. 19-24, doi:10.1109/UKSIM.2009.96