Multi level statistical classification of network traffic

Network Traffic Classification is the crucial phase of network monitoring. The network traffic once categorized per application it can be imposed with appropriate security policies to improve the performance of the network. The port and payload based traffic classification techniques used in the past decade relapsed owing to new techniques of encryption and tunneling emerging day-by-day. Recently, the statistical classification employing data mining techniques and analyzing the attributes for characterization of network traffic proved high efficiency. This proposed work characterized the network traffic based on semi-supervised machine learning approach. It initially clustered the auxiliary and content flow of application to precisely track the footprint of the application using improved k-means clustering which in turn is fed into C5.0 classifier to construct the classifier model. This system is designed to classify the network traffic accurately that resulted in high F-Score value of 0.993.