A class-specific metaheuristic technique for explainable relevant feature selection.

Ezenkwu, Chinedu Pascal; Akpan, Uduak Idio; Stephen, Bliss Utibe-Abasi

Abstract

A significant amount of previous research into feature selection has been aimed at developing methods that can derive variables that are relevant to an entire dataset. Although these approaches have revealed substantial improvements in classification accuracy, they have failed to address the problem of explainability of outputs. This paper seeks to address this problem of identifying explainable features using a class-specific feature selection method based on genetic algorithms and the one-vs-all strategy. Our proposed method finds relevant features for each class in the dataset and uses these features to enable more accurate classification, and also interpretation of the outputs. The results of our experiments demonstrate that the proposed method provides descriptive insights into prediction outputs, and also outperforms popular global feature selection techniques in the classifications of high dimensional and noisy datasets. Since there are no known challenging benchmark datasets for evaluating class-specific feature selection algorithms, this paper also recommends an approach for combining disparate datasets for this purpose.

Citation

EZENKWU, C.P., AKPAN, U.I. and STEPHEN, B.U.-A. 2021. A class-specific metaheuristic technique for explainable relevant feature selection. Machine learning with applications [online], 6, article number 100142. Available from: https://doi.org/10.1016/j.mlwa.2021.100142

• Journal Article Type: Article
• Acceptance Date: Aug 13, 2021
• Online Publication Date: Aug 26, 2021
• Publication Date: Dec 15, 2021
• Deposit Date: Mar 29, 2024
• Publicly Available Date: Apr 25, 2024
• Journal: Machine learning with applications
• Electronic ISSN: 2666-8270
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 6
• Article Number: 100142
• DOI: https://doi.org/10.1016/j.mlwa.2021.100142
• Keywords: Artificial intelligence; Explainable artificial intelligence (XAI); Genetic algorithms; Metaheuristics
• Public URL: https://rgu-repository.worktribe.com/output/2287807