A novel weighted combination technique for traffic classification

Accurate classification of traffic flows is highly beneficial for network management and security monitoring. Nowadays, many researchers have proposed machine learning techniques (i.e., decision tree, SVM, BayesNet and Naïve Bayes) for traffic classification. However, none of these classification techniques can achieve the highest accuracy for all traffic classification tasks. Recently, more and more researchers tried to combine multiple classifiers to obtain better performance. In this paper, we propose a weighted combination technique for traffic classification. The weighted combination approach first takes advantage of the confidence values inferred by each individual classifier; then assigns weight for each classifier according to its prediction accuracy on a validation traffic dataset. Experimental results on two different traffic traces demonstrate that our new weighted multi-classification framework is able to obtain satisfactory results.