Improved universum twin support vector machine

Abstract

Universum based learning provides prior information about data in the optimization problem of support vector machine (SVM). Universum twin support vector machine (UTSVM) is a computationally efficient algorithm for classification problems. It solves a pair of quadratic programming problems (QPPs) to obtain the classifier. In order to include the structural risk minimization (SRM) principle in the formulation of UTSVM, we propose an improved universum twin support vector machine (IUTSVM). Our proposed IUTSVM implicitly makes the matrices non-singular in the optimization problem by adding a regularization term. Several numerical experiments are performed on benchmark real world datasets to verify the efficacy of our proposed IUTSVM. The experimental results justifies the better generalization performance of our proposed IUTSVM in comparison to existing algorithms.