Fuzzy rough classifiers for class imbalanced multi-instance data

作者：

Highlights：

• We propose a new type of classifier for imbalanced multi-instance data.

• Our classification method is based on fuzzy rough set theory.

• We develop a framework consisting of two classifier families.

• Our proposal is experimentally shown to outperform the state-of-the-art.

摘要

Highlights•We propose a new type of classifier for imbalanced multi-instance data.•Our classification method is based on fuzzy rough set theory.•We develop a framework consisting of two classifier families.•Our proposal is experimentally shown to outperform the state-of-the-art.

论文关键词：Multi-instance learning,Fuzzy rough set theory,Imbalanced data

论文评审过程：Received 29 April 2015, Revised 22 October 2015, Accepted 3 December 2015, Available online 12 December 2015, Version of Record 8 February 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.12.002