A Feature Selection Algorithm Based on Equal Interval Division and Minimal-Redundancy–Maximal-Relevance

• Published in: Neural processing letters Vol. 51; no. 2; pp. 1237 - 1263
• Main Authors: Gu, Xiangyuan, Guo, Jichang, Xiao, Lijun, Ming, Tao, Li, Chongyi
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.04.2020; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Codes; Complex Systems; Computational Intelligence; Computer Science; Feature selection; Labels; Lattice theory; Optimization algorithms; Random variables; Redundancy; Minimal-redundancy–maximal-relevance; Equal interval division; Feature selection; Mutual information
• ISSN: 1370-4621; 1573-773X
• DOI: 10.1007/s11063-019-10144-3

Minimal-redundancy–maximal-relevance (mRMR) algorithm is a typical feature selection algorithm. To select the feature which has minimal redundancy with the selected features and maximal relevance with the class label, the objective function of mRMR subtracts the average value of mutual information between features from mutual information between features and the class label, and selects the feature with the maximum difference. However, the problem is that the feature with the maximum difference is not always the feature with minimal redundancy maximal relevance. To solve the problem, the objective function of mRMR is first analyzed and a constraint condition that determines whether the objective function can guarantee the effectiveness of the selected features is achieved. Then, for the case where the objective function is not accurate, an idea of equal interval division is proposed and combined with ranking to process the interval of mutual information between features and the class label, and that of the average value of mutual information between features. Finally, a feature selection algorithm based on equal interval division and minimal-redundancy–maximal-relevance (EID–mRMR) is proposed. To validate the performance of EID–mRMR, we compare it with several incremental feature selection algorithms based on mutual information and other feature selection algorithms. Experimental results demonstrate that the EID–mRMR algorithm can achieve better feature selection performance.