A robust approach to attribute reduction based on double fuzzy consistency measure

作者：

Highlights：

• Double fuzzy consistency measure is proposed to evaluate attributes.

• The measure based reduction algorithm (DFCM) is developed to select attributes.

• Attributes selected by DFCM can ensure higher classification accuracy.

• Effectiveness and robustness of DFCM are illustrated by theory and experiment.

• This study deepens attribute reduction theory and applications of FRS.

摘要

•Double fuzzy consistency measure is proposed to evaluate attributes.•The measure based reduction algorithm (DFCM) is developed to select attributes.•Attributes selected by DFCM can ensure higher classification accuracy.•Effectiveness and robustness of DFCM are illustrated by theory and experiment.•This study deepens attribute reduction theory and applications of FRS.

论文关键词：Double fuzzy consistency measure,Attribute reduction,Fuzzy approximation,Attribute evaluation

论文评审过程：Received 28 June 2021, Revised 26 May 2022, Accepted 30 July 2022, Available online 5 August 2022, Version of Record 20 August 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109585