Robust one-class support vector machine with rescaled hinge loss function. (December 2018)

• Record Type: Journal Article
• Authors: Xing, Hong-Jie; Ji, Man
• Is Part Of: Pattern recognition. Volume 84(2018:Dec.)
• Page Start: 152
• Page End: 164
• Publication Date: 2018-12
• Subjects: One-class classification -- One-class support vector machine -- Hinge loss function -- Half-quadratic optimization; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.07.015
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A novel robust one-class support vector machine (OCSVM) based on the rescaled hinge loss function is proposed; The optimization problem of the proposed robust OCSVM is iteratively solved by the half-quadratic optimization technique; The generalization performance of robust OCSVM is analyzed from the theoretical analysis; The robustness of robust OCSVM is explained from the weighted viewpoint. Abstract: In this paper, a novel robust one-class support vector machine (OCSVM) based on the rescaled hinge loss function is proposed to enhance the robustness of the conventional OCSVM against outliers. The optimization problem of the proposed robust OCSVM can be iteratively solved by the half-quadratic optimization technique. Compared to OCSVM, robust OCSVM may achieve higher generalization performance from the theoretical analysis. Moreover, the robustness of robust OCSVM against outliers is explained from the weighted viewpoint. Experimental results on the synthetic and benchmark data sets demonstrate that the proposed robust OCSVM is superior to the conventional OCSVM and the other two related approaches.