A framework for cost-based feature selection

作者：

Highlights：

• A new framework for cost-based feature selection is proposed.

• Two representative filters are modified to perform cost-based feature selection.

• We test the framework over a heterogeneous set of 17 datasets.

• A SVM is chosen to evaluate the performance of the proposed approach.

• The cost is minimized without compromising the classification error.

摘要

Highlights•A new framework for cost-based feature selection is proposed.•Two representative filters are modified to perform cost-based feature selection.•We test the framework over a heterogeneous set of 17 datasets.•A SVM is chosen to evaluate the performance of the proposed approach.•The cost is minimized without compromising the classification error.

论文关键词：Cost-based feature selection,Machine learning,Filter methods

论文评审过程：Received 19 July 2012, Revised 15 November 2013, Accepted 21 January 2014, Available online 28 January 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.01.008