An Automated On-line Traffic Flow Classification Scheme

Traffic classifications based on Statistics methods and Machine Learning techniques have attracted a great deal of interest. One challenging issue is that most of supervised algorithms need traffic application information and training data sets to generate classification model offline, which is infeasible to cope with the fast growing number of new applications and online traffic classifications. Cluster algorithms are promising methods. How to identify the feature subset suitable for cluster algorithm is a critical question in our proposed online traffic classification architecture. Two feature selection algorithms Wrapper Search Approach and Correlation-Based Filter Approach are evaluated to find an optimal feature subset. The experiment results demonstrate that Wrapper Search Approach outperforms Correlation-Based Filter Approach in the automated classification architecture.