Earticle

In this paper, a fast bounded parametric margin V -support vector machine (BP-V- SVM) for classification is proposed. Different from the parametric margin V -support vector machine (par-V -SVM), the BP-V -SVM maximizes a bounded parametric margin, and consequently the successive overrelaxation (SOR) technique could be used to solve our dual problem as opposed solving the standard quadratic programming problem (QPP) in par-V -SVM. Numerical experiments on several benchmark data sets and NDC data sets demonstrate the feasibility and effectiveness of the proposed algorithm.