Simultaneous Feature Selection and SVM Parameter By Using Artificial Bee Colony Algorithm

Support vector machine (SVM) is one of the most successful classifiers in data mining. The performance of SVM is mainly affected by the parameters and features used. Some approaches have been put forward to ensure the best performance of SVM, which usually utilized evolutionary computation algorithms or swarm intelligence algorithm to learn the optimal parameters or select the best subset for SVM. However, these procedures are conducted separately, which made it difficult to obtain the global optimal SVM classifier as features and parameters are interacted each other. In this paper, it proposes to simultaneously determine the parameters and accomplish feature selection for SVM by using Artificial Bee Colony Algorithm, which might acquire the overall optimal SVM classifier to the largest extent. The proposed method has been run on some UCI data set, as well, particle swarm optimization algorithm (PSO) and genetic algorithm (GA) are utilized to optimize SVM in the same way. Experimental results show that the proposed method has good adaptability and the classification accuracy, it can simultaneously obtain the optimal SVM classifier, which is better than PSO and GA in the term of optimization ability.