A multi-strategy driven reinforced hierarchical operator in the grey wolf optimizer for feature selection

In this study, a multi-strategy driven reinforced hierarchical operator for a grey wolf optimizer (RHGWO) is proposed to solve the feature selection (FS) problem, whereby tedious data are converted into information and often modeled as a combinatorial optimization problem. First, a multi-strategy mechanism is proposed to provide the GWO algorithm with exploration capabilities, including memory-based diversity and Lévy flight-based extension search. Next, a hierarchical segmentation technique is proposed to allocate exploration and exploitation, thereby providing exploration capability for superior wolves to search diverse regions and exploitation capability for inferior wolves to converge to the promising area. Subsequently, a chaotic elite learning strategy is designed for leaders to prevent misdirection. Finally, a more rational nonlinear parameter transformation is designed. Multiple experiments validate the adaptability and versatility of the proposed RHGWO algorithm.