A New Feature Extraction Based on Linear Support Vector Regression

Abstract

At first, a linear support vector regression feature extraction algorithm was introduced concisely. Then two improvements were presented in order that a simply explicit nonlinear regress function can be gotten easily by SVR feature extraction. One improvement was to decrease the dimensions of input space at the expense of regression function accuracy. Another improvement was to map the linear space to polynomial space corresponding to input features. The order of polynomial space depends on practical applications. Experimental result showed the efficiency of the improvements.