$$\nu $$ ν -Improved nonparallel support vector machine

Abstract

Abstract In this paper, a $$\nu $$ ν -improved nonparallel support vector machine ( $$\nu $$ ν -IMNPSVM) is proposed to solve binary classification problems. In this model, we use related ideas of $$\nu $$ ν -support vector machine( $$\nu $$ ν -SVM), the parameter $$\nu $$ ν is introduced to control the limits of the support vectors percentage. In the objective function, the parameter $$\varepsilon $$ ε is increased to ensure that $$\varepsilon $$ ε -band is kept as small as possible. It has played a great role in the classification of unbalanced data sets. On the basis of maximizing the interval between two classes, $$\nu $$ ν -IMNPSVM can fully fit the distribution of data points in the class by minimizing the $$\varepsilon $$ ε -band, which enhances the generalization ability of the model. The results on the benchmark datasets testify that the proposed model has a good effect on the classification accuracy.