JCSE, vol. 11, no. 4, pp.130-141, 2017

DOI: http://dx.doi.org/10.5626/JCSE.2017.11.4.130

Feature Selection Based on Bi-objective Differential Evolution

Sunanda Das, Chi-Chang Chang, Asit Kumar Das, and Arka Ghosh
Neotia Institute of Technology, Management and Science, Diamond Harbour, West Bengal, India Indian Institute of Engineering Science and Technology, Howrah, West Bengal, India School of Medical Informatics, Chung-Shan Medical University, Taichung, Taiwan; Biomedical Industry Research Centre and IT Office, Chung-Shan Medical University Hospital, Taichung, Taiwan Indian Institute of Engineering Science and Technology, Howrah, West Bengal, India

Abstract: Feature selection is one of the most challenging problems of pattern recognition and data mining. In this paper, a feature selection algorithm based on an improved version of binary differential evolution is proposed. The method simultaneously optimizes two feature selection criteria, namely, set approximation accuracy of rough set theory and relational algebra based derived score, in order to select the most relevant feature subset from an entire feature set. Superiority of the proposed method over other state-of-the-art methods is confirmed by experimental results, which is conducted over seven publicly available benchmark datasets of different characteristics such as a low number of objects with a high number of features, and a high number of objects with a low number of features.

Keyword: Feature selection; Rough set theory; Differential evolution; Classification

Full Paper:   411 Downloads, 1384 View