Role-oriented binary grey wolf optimizer using foraging-following and Lévy flight for feature selection

Abstract

Feature selection can effectively define the feature subset, remove redundant, irrelevant, and noisy features. In order to adapt the feature selection problem, this paper adopts role-oriented modeling paradigm to make up for the defects of binary grey wolf optimizer such as premature, declining diversity, and insufficient convergence, then comes up with novel V-shaped linear transfer functions. Ultimately, a role-oriented binary grey wolf optimizer is proposed. The top grey wolves combine the foraging-following to enhance convergence, while the ordinary grey wolves integrate Lévy flight to avoid premature and improve diversity. The outstanding ability of role-oriented binary grey wolf optimizer in balance of exploitation and exploration is verified by benchmarks and the effectiveness in solving feature selection is demonstrated through feature selection tasks. The results of benchmark and feature selection task have comprehensively demonstrated the competitiveness of role-oriented modeling paradigm in improving metaheuristic algorithms.