Learning for accurate classification of real-time traffic

Accurate network traffic classification is an important task. We intend to develop an intelligent classification system by learning the types of service inside a network flow using machine learning techniques. Previous work used Bayesian methods for traffic classification. In this paper we propose a further plan to identify a fine-grained traffic classification scheme through combining a series of techniques. Categories and Subject Descriptors I.5.1 [Computing Methodologies]: Pattern Recognition Models; C.2.3 [Computer Communications-Networks]: Network Operations, Network Monitoring General Terms Measurement, Algorithms Keywords Traffic Classification, Statistical Classification, Machine Learning.

• Type: Conference
• Year: 2006
• Where: CONEXT
• Authors: Wei Li, Andrew W. Moore
• Keywords: Computer Networks, CONEXT 2006, Fine-grained Traffic Classification, Network Traffic Classification, Traffic Classification