A Classification Algorithm for Network Traffic based on Improved Support Vector Machine

An algorithm to classify the network traffic based on improved support vector machine (SVM) is presented in this paper. Each feature of the traditional support vector machine (SVM) algorithm has the same effect on classification rather than considering its practical effect. To improve the classification accuracy of SVM, the probabilistic distributing area of a feature in a kind of network traffic is obtained from the real network traffic. Then the overlapped degree of the feature’s probabilistic distributing area between two different kinds of network traffic is calculated to obtain the feature’s contribution degree, and the corresponding weight value of the feature is derived from its contribution degree. Thus each feature has different effect on the classification according to its weight value. Considering the feature’s probabilistic distributing area is affected by the outliers or noises intensively, the data space is mapped to high dimension feature space, and the Gustafson-Kessel clustering algorithm is employed to deal with the outliers or noises existing in the input samples. The experimental results show that the method presented in this paper has a higher classification accuracy.