Internet traffic classification using C4.5 decision tree

Abstract

In recent years, Internet traffic classification using machine learning has become a new direction in network measurement. Being simple and efficient Naïve Bayes and its improved methods have been widely used in this area. But these methods depend too much on probability distribution of sample spacing, so they have connatural instability. To handle this problem, a new method based on C4.5 decision tree is proposed in this paper. This method builds a classification model using information entropy in training data and classifies flows just by a simple search of the decision tree. The theoretical analysis and experimental results show that there are obvious advantages in classification stability when C4.5 decision tree method is used to classify Internet traffic. © by Institute of Software, the Chinese Academy of Sciences. All rights reserved.