A Study of a Multi-class Classification Algorithm of SVM Combined with ART

This paper provides a novel multi-class classification algorithm, which combines adaptive resonance theory with support vector machine principle. It improves the one-against-one classification of support vector machine. The algorithm adopts adaptive resonance theory network to fuse the classifiers´ results and does not adopt voting principle. When the outputs of classifiers approach zero and the algorithm gets the same votes, it avoids the fusing errors coming from voting principle. We use this algorithm in fault diagnosis of power line network and give accurate results of classification.