A second-order cone programming formulation for nonparallel hyperplane support vector machine

作者：

Highlights：

• Novel robust SVM approach based on second-order cone programming.

• An extension for the method Nonparallel Hyperplane SVM is proposed.

• A geometrically grounded method based on the concept of ellipsoids.

• Superior classification performance is achieved in experiments on benchmark datasets.

摘要

•Novel robust SVM approach based on second-order cone programming.•An extension for the method Nonparallel Hyperplane SVM is proposed.•A geometrically grounded method based on the concept of ellipsoids.•Superior classification performance is achieved in experiments on benchmark datasets.

论文关键词：Support vector classification,Nonparallel hyperplane SVM,Second-order cone programming

论文评审过程：Received 20 June 2015, Revised 22 January 2016, Accepted 23 January 2016, Available online 1 February 2016, Version of Record 16 February 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.01.044