期刊名称：International Journal of Computer Science and Security (IJCSS)
电子版ISSN：1985-1553
出版年度：2009
卷号：3
期号：2
页码：146-153
出版社：Computer Science Journals
摘要：Abstract The evolution of the Internet into a large complex service-based network has posed tremendous challenges for network monitoring and control in terms of how to collect the large amount of data in addition to the accurate classification of new emerging applications such as peer to peer, video streaming and online gaming. These applications consume bandwidth and affect the performance of the network especially in a limited bandwidth networks such as university campuses causing performance deterioration of mission critical applications. Some of these new emerging applications are designed to avoid detection by using dynamic port numbers (port hopping), port masquerading (use http port 80) and sometimes encrypted payload. Traditional identification methodologies such as port-based signature-based are not efficient for today's traffic. In this work machine learning algorithms are used for the classification of traffic to their corresponding applications. Furthermore this paper uses our own customized made training data set collected from the campus, The effect on the amount of training data set has been considered before examining, the accuracy of various classification algorithms and selecting the best. Our findings show that random tree, IBI, IBK, random forest respectively provide the top 4 highest accuracy in classifying flow based network traffic to their corresponding application among thirty algorithms with accuracy not less than 99.33%.
关键词：NetFlow; machine learning; classification; accuracy; video streaming; peer to peer.
