A semi-supervised learning approach for model selection based on class-hypothesis testing

作者：

Highlights：

• A model selection method is proposed by hypothesis testing and feature extraction.

• Partial least squares is applied to obtain the extended datasets.

• The model selection is performed by means of a Likelihood ratio test.

• Experiments were carried out on several databases yielding a clear improvement.

摘要

•A model selection method is proposed by hypothesis testing and feature extraction.•Partial least squares is applied to obtain the extended datasets.•The model selection is performed by means of a Likelihood ratio test.•Experiments were carried out on several databases yielding a clear improvement.

论文关键词：Statistical learning and decision theory,Semi-supervised learning,Support vector machines (SVM),Hypothesis testing,Partial least squares

论文评审过程：Received 3 April 2017, Revised 13 July 2017, Accepted 1 August 2017, Available online 5 August 2017, Version of Record 10 August 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.08.006