Time-Varying Hierarchical Chains of Salps with Random Weight Networks for Feature Selection

Feature selection (FS) is considered asone of the most common and challenging tasks in MachineLearning. FScanbeconsideredasanoptimizationproblemthatrequiresanefficient optimization algorithm to find its optimal set of features. This paper proposes a wrapper FS method that combines a time-varying number of leaders and followers binary Salp Swarm Algorithm (called TVBSSA) with Random Weight Network (RWN). In this approach, the TVBSSA is used as a search strategy, while RWN is utilized as an induction algorithm. The objective function is formulated in a manner to aggregate three objectives: maximizing the classification accuracy, maximizing the reduction rate of the selected features, and minimizing the complexity of generated RWN models. To assess the performance of the proposed approach, 20 well-known UCI datasets and a number of existing FS methods are employed. The comparative results show the ability of the proposed approach in outperforming similar algorithms in the literature and its merits to be used in systems that require FS.