NN C+SVM: An empirical study for fast classification

This paper proposes a hybrid learning method to speed up classification procedure of Support Vector Machines (SVM). Comparing most algorithms trying to decrease the support vectors in an SVM classifier, we focus on reducing the data points that need SVM for classification, and reduce the number of support vectors for each SVM classification. The system uses a nearest neighbor classifier(NNC) to treat data points attentively. In the training phase, the NNC selects data near partial decision boundary, and then train sub SVMs for each prototype pair. For classification, most non-boundary data points are classified by NNC directly, while remaining boundary data points are passed to an expert SVMs, which is much simpler than a general SVM. Experimental results show that the proposed method significantly accelerates the testing speed on several generated data sets.