A hybrid filter-based feature selection method via hesitant fuzzy and rough sets concepts

Abstract

<span class="fontstyle0">High dimensional microarray datasets are difficult to classify since they have many features with small number of<br />instances and imbalanced distribution of classes. This paper proposes a filter-based feature selection method to improve<br />the classification performance of microarray datasets by selecting the significant features. Combining the concepts of<br />rough sets, weighted rough set, fuzzy rough set and hesitant fuzzy sets for developing an effective algorithm is the main<br />contribution of this paper. The mentioned method has two steps, in the first step, four discretization approaches are<br />applied to discretize continuous datasets and selects a primary subset of features by combining of weighted rough set<br />dependency degree and information gain via hesitant fuzzy aggregation approach. In the second step, a significance<br />measure of features (defined by fuzzy rough concepts) is employed to remove redundant features from primary set.<br />The Wilcoxon Signed Ranked tes (A Non-parametric statistical test) is conducted for comparing the presented method<br />with ten feature selection methods across seven datasets. The results of experiments show that the proposed method<br />is able to select a significant subset of features and it is an effective method in the literature in terms of classification<br />performance and simplicity.</span><br /><br />