Structural regularized projection twin support vector machine for data classification

Projection twin support vector machine (PTSVM) seeks two projection directions for two classes by solving two smaller-sized quadratic programming problems (QPPs), such that the projected samples of one class are well separated from those of the other one in its respective subspace. However, it only simply considers the prior class-based structural information in the optimization problems. In this paper, a structural regularized PTSVM (SRPTSVM) classifier for binary classification is presented. This proposed SRPTSVM focuses on the cluster-based structural information of the corresponding class in each optimization problem, which is vital for designing a good classifier in different real-world problems. This SRPTSVM is extended to a nonlinear version by the kernel trick. Experimental results demonstrate that SRPTSVM is superior in generalization performance to other classifiers.