Systematic Literature Review of Hybrid Metaheuristic Algorithms for Feature Selection in Classification Tasks

Wijaya, Jabesh Nehemiah and Siswantoro, Joko (2025) Systematic Literature Review of Hybrid Metaheuristic Algorithms for Feature Selection in Classification Tasks. In: 2025 International Conference on Information Management and Technology (ICIMTech), 28-29 August 2025, Bandung, Jawa Barat, Indonesia.

	PDF Systematic_Literature_Review_of_Hybrid_Metaheuristic_Algorithms_for_Feature_Selection_in_Classification_Tasks Merged.pdf - Published Version Download (7MB)
	PDF Bukti koresponding author.pdf - Other Download (247kB)

Abstract

ng at improving model performance with a reduction in dimensionality and computational expense. Metaheuristic optimization techniques have shown promise for feature selection but are often marred by the problems of premature convergence and sensitivity to parameters. To address these challenges, hybrid metaheuristic approaches have been proposed to combine the best aspects of different algorithms in order to enhance search capabilities and solution quality. This systematic literature review discusses hybrid metaheuristic algorithms for feature selection in response to three research questions: identifying the hybrid algorithms used and their domains of application, evaluating their effectiveness, and examining existing challenges and research gaps. Following the PRISMA framework, 40 related studies appearing between 2020 and 2025 were selected and assessed. Review outcomes show that hybrid approaches always outperform standalone methods with superior classification accuracy and larger feature reduction. However, challenges such as increased complexity, limited usage, and non-uniform practice still exist. Future research must delve into developing more robust and effective hybrid algorithms and demonstrate their performance across different data sets and classifiers.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Faculty of Engineering > Department of Informatic
Depositing User:	Joko Siswantoro
Date Deposited:	10 Dec 2025 05:42
Last Modified:	10 Dec 2025 05:42
URI:	http://repository.ubaya.ac.id/id/eprint/49939

Actions (login required)

View Item