Negative Correlation Learning Enhanced Search Behavior in Backtracking Search Optimization

Zhe Xu, Zhenyu Lei, Lin Yang, Xiaosi Li, Shangce Gao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Backtracking search optimization algorithm (BSA) is new evolutionary algorithm (EA) that to solve global optimization problems. BSA is similar to evolutionary algorithm, including selection, crossover, mutation and operations. The core idea of BSA is to get guidance from the previous population and search solutions with better fitness. While BSA only evaluates the individuals based on the fitness, which could make the individuals with better exploration prospects be discarded when updating population. Thus, in this paper, we proposed a novel way to improve exploration abilities that utilize negative correlation learning enhanced search behavior in BSA to further improve its search ability. We used benchmark function suit CEC'17 to verify the proposed new algorithm and the experiment result indicates the feasibility of this hybridization.

Original languageEnglish
Title of host publicationProceedings - 2018 10th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages310-314
Number of pages5
ISBN (Electronic)9781538658369
DOIs
StatePublished - 2018/11/09
Event10th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2018 - Hangzhou, China
Duration: 2018/08/252018/08/26

Publication series

NameProceedings - 2018 10th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2018
Volume1

Conference

Conference10th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2018
Country/TerritoryChina
CityHangzhou
Period2018/08/252018/08/26

Keywords

  • Backtracking search optimization algorithm
  • computational intelligence
  • negative correlation learning
  • optimization

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Computational Mathematics
  • Control and Optimization
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Negative Correlation Learning Enhanced Search Behavior in Backtracking Search Optimization'. Together they form a unique fingerprint.

Cite this