Incremental feature selection based on rough set in dynamic incomplete data

作者：

Highlights：

• An efficient computation for the tolerance classes and positive region is provided.

• Incremental computation on a positive region in dynamic incomplete data is presented.

• Incremental feature selection algorithms in dynamic incomplete data are developed.

• The efficiency of the proposed algorithms is demonstrated on UCI data sets.

摘要

Highlights•An efficient computation for the tolerance classes and positive region is provided.•Incremental computation on a positive region in dynamic incomplete data is presented.•Incremental feature selection algorithms in dynamic incomplete data are developed.•The efficiency of the proposed algorithms is demonstrated on UCI data sets.

论文关键词：Feature selection,Positive region,Rough set theory,Dynamic incomplete data

论文评审过程：Received 28 June 2013, Revised 28 May 2014, Accepted 2 June 2014, Available online 9 June 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.06.002