Threshold Binary Grey Wolf Optimizer Based on Multi-Elite Interaction for Feature Selection

Abstract

The traditional grey wolf algorithm is widely used for feature selection. However, within complex feature multi-dimensional problems, the grey wolf algorithm is prone to reach locally optimal solutions and premature convergence. In this paper, a threshold binary grey wolf optimizer based on multi-elite interaction for feature selection (MTBGWO) is proposed. Firstly, the multi-population topology is adopted to enhance the population's diversity for improving search space utilization. Secondly, an information interaction learning strategy is adopted for the update of sub-population elite wolf position (optimal position) via learning better position from other elite wolves; in order to improve the local exploitation ability of the sub-population. At the same time, the command of β and δ wolves (second and third best positions) for population position updates is removed. Finally, a threshold approach is employed to convert the continuous position of grey wolf individuals into binary one to apply in the feature selection problem. Further, The MTBGWO algorithm proposed in this paper is compared with the traditional binary grey wolf algorithm (BGWO), binary whale algorithm (BWOA), as well as some recently developed novel algorithms to exhibit its superiority and robustness. Totally 16 classification datasets, from the UCI Machine Learning Repository, are chosen for comparison. The Wilcoxon's rank-sum non-parametric statistical test is carried out at 5% significance level to evaluate whether the results of the proposed algorithms significantly differs from those of the other algorithms. In the experimental results for all datasets, the overall average accuracy of the MTBGWO algorithm is 94.7%, while the highest of the other algorithms is 92.8% and the selected feature subset is 25% of the total dataset, while the GWO and WOA algorithms are twice as high as MTBGWO. In terms of computational efficiency, the overall processing time of MTBGWO is 24.2 seconds, whereas HSGW is 44.1 seconds. The results reveal that the MTBGWO has shown its superiority in solving the feature selection problem.INDEX TERMS Grey wolf optimizer, feature selection, binary optimizer, elite interaction strategy

Feature Selection Problem and Metaheuristics: A Systematic Literature Review about Its Formulation, Evaluation and Applications

“…The color of the name of the author is related to the count Zhang et al [21] Zhang et al [24] Arora et al [23] Sayed et al [22] Abdel-Basset et al [25] Xue et al [26] Tubishat et al [27] Arora and Anand [29] Al-Tashi et al [28] Sayed et al [ On the other hand, when analyzing the contributions by country, we found that China 159 presents the most significant number of published papers related to the feature selection problem. 160 This data is in accordance with the contributions by authors, where five of the ten most active 161 authors represent China, four represent Malaysia, and one represent Australia. Note that the 162 three countries represented by the ten most contributing authors in the area are among the ten 163 countries that present the most significant number of publications.…”

“…The rise in articles employing multiple classifiers, including five classifiers [117], underscores a dynamic approach to optimization challenges. • 2023: The number of articles decreases, and the distribution reverts to a focus on single classifiers [40,70,143,145,146,[148][149][150]160,184,185], while a minimal presence of two and four classifiers persists.…”

“…This metaheuristic is the most used by the authors in [22,27,28,30,32,35,36,38,39,45,54,65,69,77,79,80,83,87,100,127,138,153,155,161,168,174,186]. The second most used metaheuristic is the grey wolf optimizer, a population metaheuristic based on the hunting behavior of grey wolves [195] and used in [51,71,84,87,88,95,101,105,128,134,137,157,160,170,173]. The other metaheuristic used in more than ten studies is the genetic algorithm, a population metaheuristic inspired by Darwin's laws of evolution [196] and used in [31,32,41,…”