Binary Jaya algorithm based on binary similarity measure for feature selection

Abstract

Feature selection (FS) has become an indispensable data preprocessing task because of the huge amount of high dimensional data being generated by current technologies. These high dimensional data contains irrelevant, redundant, and noisy features that deteriorate classification accuracy. FS reduces dimensionality by removing the unwanted features thus improves classification accuracy. FS can be considered as a binary optimization problem. In order to solve this problem, this work proposes a new wrapper feature selection technique based on the Jaya algorithm. Three binary variants of the Jaya algorithm are proposed, the first and second ones are based on transfer functions namely BJaya-S and BJaya-V. The third variant (BJaya-JS) explores the search space on the basis of the Jaccard Similarity index. In addition, a probability-based local search technique, namely Neighbourhood Search is proposed to balance the exploration and exploitation. The variants of Jaya algorithm are evaluated and the best variant is selected. The best variant is further compared with six state-of-the-art feature selection techniques. All the performances are tested on 18 high dimensional standard UCI datasets. Experimental result comparison shows that the proposed feature selection technique performs better than other competitors.