A locality correlation preserving support vector machine

作者：

Highlights：

• We propose a novel support vector machine like classification algorithm LCPSVM.

• LCPSVM combines the idea of margin maximization between classes and local correlation preservation of class data.

• It is shown that SVM and other related algorithms can be obtained as special cases of LCPSVM.

• Experiments under different conditions are performed, and the results are discussed.

摘要

Highlights•We propose a novel support vector machine like classification algorithm LCPSVM.•LCPSVM combines the idea of margin maximization between classes and local correlation preservation of class data.•It is shown that SVM and other related algorithms can be obtained as special cases of LCPSVM.•Experiments under different conditions are performed, and the results are discussed.

论文关键词：Support vector machine,Kernel methods,Locality correlation preservation,Fuzzy membership

论文评审过程：Received 17 March 2013, Revised 13 November 2013, Accepted 1 April 2014, Available online 13 April 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.04.004