MIFS-ND: A mutual information-based feature selection method

作者：

Highlights：

• We propose a greedy feature selection method using mutual information theory.

• The method uses feature–class and feature–feature mutual information.

• We use NSGA-II method to select an optimal feature subset.

• The accuracy of the proposed method is evaluated using multiple classifiers.

摘要

•We propose a greedy feature selection method using mutual information theory.•The method uses feature–class and feature–feature mutual information.•We use NSGA-II method to select an optimal feature subset.•The accuracy of the proposed method is evaluated using multiple classifiers.

论文关键词：Features,Mutual information,Relevance,Classification

论文评审过程：Available online 24 April 2014.

论文官网地址：https://doi.org/10.1016/j.eswa.2014.04.019