Hierarchical RBF Neural Network Using for Early Stage Internet Traffic Identification

Identifying network traffics at their early stages accurately is very important for network management and security. Recent years, more and more studies have devoted to find effective machine learning models to identify traffics with the few packets at the early stage. In this paper, we design a Hierarchical Radial Basis Function network (HRBF) model based on our previous works, and then we apply the HRBF model for early stage traffic identification. Three network traffic data sets including two open data sets are used for the study, and six widely used classifiers are employed as the comparing methods in the identification experiments. Accuracy and area under curve (AUC) are applied to evaluate the performances of compared methods. HRBF outperforms the other methods for most cases in the identification experiments, and it behaves very well for both of accuracy and AUC. Thus, HRBF is effective for early stage traffic identification.