Expected margin–based pattern selection for support vector machines

作者：

Highlights：

• This study proposes expected margin-based pattern selection (EMPS) for SVMs.

• EMPS selects support vector candidates based on the estimated margin of SVMs.

• EMPS reduces the training time complexity of SVMs.

• The effectiveness was demonstrated on benchmark datasets and a real-world problem.

摘要

•This study proposes expected margin-based pattern selection (EMPS) for SVMs.•EMPS selects support vector candidates based on the estimated margin of SVMs.•EMPS reduces the training time complexity of SVMs.•The effectiveness was demonstrated on benchmark datasets and a real-world problem.

论文关键词：Support vector machines,Pattern selection,Training complexity,Large data,Semiconductor manufacturing

论文评审过程：Received 26 November 2018, Revised 4 August 2019, Accepted 6 August 2019, Available online 6 August 2019, Version of Record 10 August 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112865