Parameter Optimization for Support Vector Machine Classifier with IO-GA

The Support Vector Machine method has a good learning and generalization ability. Unfortunately, there are no comprehensive theories to guide the parameter selection of the SVM, which largely limits its application. In order to get the optimal parameters automatically, researchers have tried a variety of methods. Using genetic algorithms to optimize parameters of an SVM Classifier has become one of the favorite methods in recent years. In this paper, we explain how the Standard Genetic Algorithm (SGA) causes the problem of premature convergence and limits the accuracy of the SVM. We also put forward a new genetic algorithm with improved genetic operators (IO-GA) to optimize the SVM classifier´s parameters. Experimental results show that the parameters obtained by this method can greatly improve the classification performance of SVM. We therefore conclude that this method is effective.