Parameter Optimization of ϵ-Support Vector Machine by Genetic Algorithm

The ϵ-support vector regression machine is a promising artificial intelligence technique, in which the regression algorithm has already been used in solving the nonlinear function approach successfully. Most users select parameters for an SVM by rule of thumb, so they frequently fail to generate the optimal parameters effect for the function. This has restricted effective use of SVM to a great degree. In this paper, the authors use genetic algorithm to solve the SVM parameters optimization problem. Simulation result shows that the method has high precision and possesses certain practical application significance.