FRPS: A Fuzzy Rough Prototype Selection method

作者：

Highlights：

• Prototype Selection selects high-quality instances to improve k NN classification.

• State-of-the-art prototype are accurate but generally slow.

• We propose a Prototype Selection method based on fuzzy rough set theory.

• Experimental results show that this method is fast and significantly more accurate.

摘要

•Prototype Selection selects high-quality instances to improve k NN classification.•State-of-the-art prototype are accurate but generally slow.•We propose a Prototype Selection method based on fuzzy rough set theory.•Experimental results show that this method is fast and significantly more accurate.

论文关键词：Classification,Fuzzy rough sets,Instance selection,k NN,Prototype Selection

论文评审过程：Received 29 February 2012, Revised 26 February 2013, Accepted 5 March 2013, Available online 14 March 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.03.004