Improving exploration property of velocity-based artificial bee colony algorithm using chaotic systems

Moradi, P, Imanian, N, Nasih Qader, N and Jalili, M 2018, 'Improving exploration property of velocity-based artificial bee colony algorithm using chaotic systems', Information Sciences, vol. 465, pp. 130-143.


Document type: Journal Article
Collection: Journal Articles

Title Improving exploration property of velocity-based artificial bee colony algorithm using chaotic systems
Author(s) Moradi, P
Imanian, N
Nasih Qader, N
Jalili, M
Year 2018
Journal name Information Sciences
Volume number 465
Start page 130
End page 143
Total pages 14
Publisher Elsevier Inc.
Abstract Artificial Bee Colony (ABC) is an effective swarm optimization method featured with higher global search ability, less control parameters and easier implementation compared to other population-based optimization methods. Although ABC works well at exploration, its main drawback is poor exploitation affecting the convergence speed in some cases. In this paper, an efficient ABC-based optimization method is proposed to deal with high dimensional optimization tasks. The proposed method performs two modifications to the original ABC in order to improve its performance. First, it employs a chaos system to generate initial individuals, which are fully diversified in the search space. A chaos-based search method is used to find new solutions during ABC search process to enhance the exploitation capability of the algorithm and avoid premature convergence. Second, it incorporates a new search mechanism to improve the exploration ability of ABC. Experimental results performed on benchmark functions reveals superiority of the proposed method over state-of-the-art methods.
Subject Pattern Recognition and Data Mining
Information Systems Management
Keyword(s) Artificial bee colony
Continuous optimization
Chaos theory
Logistic maps
Population initialization
Exploration property
DOI - identifier 10.1016/j.ins.2018.06.064
Copyright notice © 2018 Elsevier Inc. All rights reserved.
ISSN 0020-0255
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 2 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 12 Abstract Views  -  Detailed Statistics
Created: Tue, 23 Oct 2018, 16:00:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us