Quasi-reflection learning arithmetic optimization algorithm firefly search for feature selection

Nebojsa Bacanin; Nebojsa Budimirovic; K Venkatachalam; Hothefa Shaker Jassim; Miodrag Zivkovic; S S Askar; Mohamed Abouhawwash

doi:10.1016/j.heliyon.2023.e15378

Quasi-reflection learning arithmetic optimization algorithm firefly search for feature selection

Heliyon. 2023 Apr 6;9(4):e15378. doi: 10.1016/j.heliyon.2023.e15378. eCollection 2023 Apr.

Authors

Nebojsa Bacanin¹, Nebojsa Budimirovic¹, K Venkatachalam², Hothefa Shaker Jassim³, Miodrag Zivkovic¹, S S Askar⁴, Mohamed Abouhawwash^{5

6}

Affiliations

¹ Singidunum University, Danijelova 32, 11000 Belgrade, Serbia.
² Department of Applied Cybernetics, Faculty of Science, University of Hradec Králové, 50003 Hradec Králové, Czech Republic.
³ Modern College of Business and Science, AL-Khuwair 133, Muscat, Oman.
⁴ Department of Statistics and Operations Research, College of Science, King Saud University, P.O. Box 2455, Riyadh 11451, Saudi Arabia.
⁵ Department of Mathematics, Faculty of Science, Mansoura University, Mansoura 35516, Egypt.
⁶ Department of Computational Mathematics, Science and Engineering (CMSE), Michigan State University, East Lansing, MI 48824, USA.

Abstract

With the whirlwind evolution of technology, the quantity of stored data within datasets is rapidly expanding. As a result, extracting crucial and relevant information from said datasets is a gruelling task. Feature selection is a critical preprocessing task for machine learning to reduce the excess data in a set. This research presents a novel quasi-reflection learning arithmetic optimization algorithm - firefly search, an enhanced version of the original arithmetic optimization algorithm. Quasi-reflection learning mechanism was implemented for enhancement of population diversity, while firefly algorithm metaheuristics were used to improve the exploitation abilities of the original arithmetic optimization algorithm. The aim of this wrapper-based method is to tackle a specific classification problem by selecting an optimal feature subset. The proposed algorithm is tested and compared with various well-known methods on ten unconstrained benchmark functions, then on twenty-one standard datasets gathered from the University of California, Irvine Repository and Arizona State University. Additionally, the proposed approach is applied to the Corona disease dataset. The experimental results verify the improvements of the presented method and their statistical significance.

Keywords: Aritmetic optimisation algorithm; Feature selection; Firefly algorithm; Metaheuristics; Quasi-reflection-based learning.