Feature selection by integrating two groups of feature evaluation criteria

作者：

Highlights：

• A hybrid feature selection method based on information theory is proposed.

• Our method integrates two groups of feature evaluation criteria.

• The proposed method adopts two types of feature redundancy.

• Our method outperforms seven extremely competitive methods in terms of accuracy.

摘要

•A hybrid feature selection method based on information theory is proposed.•Our method integrates two groups of feature evaluation criteria.•The proposed method adopts two types of feature redundancy.•Our method outperforms seven extremely competitive methods in terms of accuracy.

论文关键词：Feature selection,Information theory,Classification,Class-independent feature redundancy,Class-dependent feature redundancy

论文评审过程：Received 14 September 2017, Revised 3 February 2018, Accepted 27 May 2018, Available online 28 May 2018, Version of Record 1 June 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.05.029