Improved density-induced support vector data description

Feng Yin, Guang-Xin Huang

Abstract: Support vector data description (SVDD) is a data description method which can give the target data set a spherically shaped description. A density-induced SVDD (D-SVDD) has been proposed to improve the SVDD. However, the dual optimization problem of the D-SVDD is not a simple optimization problem which makes the D-SVDD be not an easy data description method. This paper presents an improved density-induced SVDD. The hyper-spherically shaped boundary of our method resorts to a well-known quadratic programming problem, thus the proposed data description method improves the D-SVDD.