Simultaneous feature selection and heterogeneity control for SVM classification: An application to mental workload assessment

作者：

Highlights：

• Novel SVM-based approach for binary classification.

• Procedure pools information across users in a single optimization problem.

• Sources of information are penalized using a group penalty function.

• The proposal is successfully applied in a mental-workload assessment task.

摘要

•Novel SVM-based approach for binary classification.•Procedure pools information across users in a single optimization problem.•Sources of information are penalized using a group penalty function.•The proposal is successfully applied in a mental-workload assessment task.

论文关键词：Support vector machines,Feature selection,Heterogeneity control,Mental workload,Group penalty functions

论文评审过程：Received 3 September 2018, Revised 4 September 2019, Accepted 26 September 2019, Available online 27 September 2019, Version of Record 31 October 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112988