A Novel Approach for Raising the Accuracy of SVDD

This paper presents a novel one-class classification method to improve the correct proportion by adding new outliers. General speaking, it is difficult to improve the correct proportion of the one-class classification because of few data. How to distinguish the target objects correctly from unknown samples becomes one of the most important problems. The support vector data description (SVDD) is a method proposed to solve the problem of one-class classification. It models a hyper sphere around the target set, and by the introduction of kernel functions, more flexible descriptions are obtained. In SVDD, the width parameter and the penalty parameter have to be given beforehand by the user. To automatically optimize the values for these parameters, the error on both the target and outlier data has to be estimated. Because no outlier examples are available, we propose a max-min range method for generating artificial outliers in this paper. By generating artificial outliers around the target set, the accuracy of classifiers will improve. At the last, we use four benchmark data sets: Iris, Wine, Balance-scale, and Ionosphere data base to validate the approach in this research indeed has better classification result.