An improved discrete particle swarm optimization based on cooperative swarms

Yiheng Xu*, Qiangwei Wang, Jinglu Hu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

The discrete particle swarm optimization (DPSO) is a kind of particle swarm optimization (PSO) algorithm to find optimal solutions for discrete problems. This paper proposes an improved DPSO based on cooperative swarms, which partition the search space into lower dimensional subspaces. The k-means split scheme and regular split scheme are applied to split the solution vector into swarms. Then the swarms optimize the different components of the solution vector cooperatively. Some strategies are further used to improve the accuracy and convergence. Application of the proposed cooperative swarms based DPSO (CDPSO) on the traveling salesman problem (TSP) shows a significant improvement over conventional DPSOs.

Original languageEnglish
Title of host publicationProceedings - 2008 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2008
Pages79-82
Number of pages4
DOIs
Publication statusPublished - 2008 Dec 1
Event2008 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2008 - Sydney, NSW, Australia
Duration: 2008 Dec 92008 Dec 12

Publication series

NameProceedings - 2008 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2008

Conference

Conference2008 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2008
Country/TerritoryAustralia
CitySydney, NSW
Period08/12/908/12/12

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Fingerprint

Dive into the research topics of 'An improved discrete particle swarm optimization based on cooperative swarms'. Together they form a unique fingerprint.

Cite this