Unsupervised feature selection using an improved version of Differential Evolution

In this article, an unsupervised feature selection algorithm is proposed using an improved version of a recently developed Differential Evolution technique called MoDE. The proposed algorithm produces an optimal feature subset while optimizing three criteria, namely, the average standard deviation of the selected feature subset, the average dissimilarity of the selected features, and the average similarity of non-selected features with respect to their first nearest neighbor selected features. Normalized mutual information score is employed for computing both the similarity as well as the dissimilarity measures. The experimental results confirm the superiority of the proposed algorithm over the other state-of-the-art unsupervised feature selection algorithms for eight different kinds of datasets with the number of points ranging from 80 to 6238 and the number of dimensions ranging from 30 to 649.