Feature selection method with joint maximal information entropy between features and class

作者：

Highlights：

• A new metric (joint maximal information entropy (JMIE)) is defined to measure a feature subset.

• A new feature selection method combining the joint maximal information entropy among features (FS-JMIE) and binary particle swarm optimization (BPSO) algorithm is proposed in this paper.

• Experimental results on 5 UCI datasets show the efficiency of the proposed feature selection method.

• The proposed method manifests advantage in feature selection with multiple classes.

• FS-JMIE shows higher consistency and better time-efficiency than BPSO-SVM algorithm.

摘要

•A new metric (joint maximal information entropy (JMIE)) is defined to measure a feature subset.•A new feature selection method combining the joint maximal information entropy among features (FS-JMIE) and binary particle swarm optimization (BPSO) algorithm is proposed in this paper.•Experimental results on 5 UCI datasets show the efficiency of the proposed feature selection method.•The proposed method manifests advantage in feature selection with multiple classes.•FS-JMIE shows higher consistency and better time-efficiency than BPSO-SVM algorithm.

论文关键词：BPSO,Entropy,Feature selection,Maximal information coefficient

论文评审过程：Received 16 May 2017, Revised 3 December 2017, Accepted 9 December 2017, Available online 12 December 2017, Version of Record 18 December 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.12.008