A GA-based feature selection and parameters optimization for support vector regression

Abstract

The regression analysis is a method in mathematical statistics to solve many practical problem. Support Vector Regression (SVR) is an effective method for resolving regression problem. However, the traditional SVR impose many of the limitations, the SVR parameters need optimizing, but there is not a mature theoretic for choosing the parameters of SVR, which causes much discommodity to the appliance of SVR. This paper proposes and investigates the use of a genetic algorithm approach for simultaneously select an optimal feature subset and optimize SVR parameters.