An improved rough margin-based ν-twin bounded support vector machine

作者：

Highlights：

• A new binary classifier (I rough v-TBSM) is proposed.

• Different penalties according to the samples’ positions are given in I rough v-TBSM.

• The structural risk minimization principle is implemented in I rough v-TBSM.

• I rough v-TBSM skillfully avoids the matrix inverse operation.

• The nonlinear I rough v-TBSM with linear kernel can degenerate to linear case directly.

摘要

•A new binary classifier (I rough v-TBSM) is proposed.•Different penalties according to the samples’ positions are given in I rough v-TBSM.•The structural risk minimization principle is implemented in I rough v-TBSM.•I rough v-TBSM skillfully avoids the matrix inverse operation.•The nonlinear I rough v-TBSM with linear kernel can degenerate to linear case directly.

论文关键词：TSVM,Rough ν-TSVM,Structural risk minimization,Matrix inverse operation,Classification

论文评审过程：Received 17 October 2016, Revised 11 March 2017, Accepted 5 May 2017, Available online 6 May 2017, Version of Record 25 May 2017.

论文官网地址：https://doi.org/10.1016/j.knosys.2017.05.004