A binary Sine Cosine-Modified Whale Optimization Algorithm for Feature Selection

Abstract

The increase of many pillars within the dataset makes it needed to pick the best part of features. The feature selection approach directly influences the performance of the style in terms of integrity and computational information. The wrapper feature choice version deals with the function set to improve the category reliability. In this paper, a new wrapper feature selection binary formula is intended based upon the Sine Cosine Algorithm (SCA) and a modified Whale Optimization Algorithm (MWOA). This algorithm (Binary SC-MWOA) was associated with obtaining unassociated characteristics and selecting the optimum features. The proposed formula's attractive outcomes reveal the algorithm's performance for picking the best features. Ten different UCI Repository datasets are checked in the experiments.