A fuzzy rough set-based feature selection method using representative instances

Abstract

The fuzzy rough set theory has been widely used to deal with uncertainty in real-valued or even complex data, in which one of the most concerned issues is feature selection. Since a real-world data set generally contains redundant data objects (or instances) and errors which lead to the fact that not all the instances are of equal importance, focusing on the representative instances for feature selection can not only acquire more convincing analysis results but also alleviate computational complexity in mining knowledge. At present, however, little attention has been paid on using representative instances to select features. In this paper, the issue of selecting features by using representative instances is investigated based on fuzzy rough sets and a representative instance-based feature selection approach is proposed. First, the fuzzy granular rule is employed to describe the discriminating information of an instance. Then, the representative instances are selected according to the coverage ability of the fuzzy granular rules induced by all of the instances. Furthermore, an implication relationship-preserved reduction is presented to maintain the discriminating information of the selected instances, and then a heuristic algorithm is presented to search for such a feature subset. Finally, a filter-wrapper approach is suggested to select the best subset of the features. Some numerical experiments are further conducted to show the performance of the proposed feature selection method and the results are satisfactory in terms of both efficiency and effectiveness.