Universum least squares twin parametric-margin support vector machine

Abstract

Universum based algorithms involve universum samples in the classification problem to improve the generalization performance. In order to provide prior information about data, we utilized universum data to propose a novel classification algorithm. In this paper, a novel parametric model for universum based twin support vector machine is presented for classification problems. The proposed model is termed as universum least squares twin parametric-margin support vector machine (ULSTPMSVM). The solution of ULSTPMSVM involves a system of linear equations. This makes the ULSTPMSVM efficient w.r.t. training time. In order to verify the performance of the proposed model, various experiments are carried out on real world benchmark datasets. Statistical tests are performed to verify the significance of the proposed method. The proposed ULSTPMSVM performed better than existing algorithms in terms of classification accuracy and training time for most of the datasets. Moreover, an application of proposed ULSTPMSVM is presented for classification of Alzheimer's disease data.