SVM Classification Model Parameters Optimized by Improved Genetic Algorithm

SVM classification model has been widely applied to mechanical equipment fault diagnosis and material defects classification. It is difficult to choose the optimal value of penalty factor C and kernel function parameter for SVM model. Therefore, an improved genetic algorithm to optimize SVM parameters is put forward, which improves crossover and mutation operators and enhances convergence properties by using the best individual retention strategy. UCI data set is used to verify the algorithm. The testing results show that the algorithm can quickly and effectively select optimal SVM parameters and improve SVM classification accuracy.