GABC: A Hybrid Approach for Feature Selection Using Artificial Bee Colony and Genetic Operators

Bindu M. G. and Sabu M. K.
Additional contact information
Bindu M. G.: Cochin University of Science and Technology, India
Sabu M. K.: Cochin University of Science and Technology, India

International Journal of Swarm Intelligence Research (IJSIR), 2021, vol. 12, issue 3, 78-95

Abstract: Feature selection is a complex pre-processing step in data mining that enhances classification accuracy by selecting the minimum number of relevant features. Artificial bee colony algorithm (ABC) is one of the successful swarm intelligent algorithms for feature selection, image processing, data analytics, protein structure prediction, etc. It simulates the honey foraging behavior of the bee swarm. But it tends to low convergence speed and local optima stagnation. Hybrid meta-heuristics can enhance the performance of existing swarm algorithms. This paper proposes a hybrid approach for the ABC algorithm by incorporating genetic operators into it. The mutation operator is used to explore the better-quality neighborhood while the crossover is used to enhance the quality of solutions by implementing diversity into them. The performance of the proposed method is evaluated using UCI data sets and compared with existing swarm algorithms for feature selection. The effectiveness of the proposed method is evident from the results.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://services.igi-global.com/resolvedoi/resolve ... 018/IJSIR.2021070104 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jsir00:v:12:y:2021:i:3:p:78-95

Access Statistics for this article

International Journal of Swarm Intelligence Research (IJSIR) is currently edited by Yuhui Shi

More articles in International Journal of Swarm Intelligence Research (IJSIR) from IGI Global
Bibliographic data for series maintained by Journal Editor ().