Parameters Optimization of SVM using the Dual Population ACO

摘要

The support vector machine (SVM) parameters optimization of previous lacks of theoretical guidance. The algorithm is easy to fall into local optimum. The dual population ant colony algorithm is helpful to SVM parameters optimization in ability. The independent solution and exchange of two population information and the change of pheromone can avoid the stagnation of the algorithm or get into local optimum, and find the global optimal solution. The accuracy of SVM classification is used as the objective function. And the experimental results show that the algorithm improves the accuracy of the classification of support vector machine parameters.