The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMMUNICATIONS
Transactions ID Number: 42-284
Full Name: Chengjie Gu
Position: Ph.D. Candidate
Age: ON
Sex: Male
Address: Institute of Information networks Technology,Nanjing University of Posts and Telecommunications ,No.66 Xin Mofan Road, Nanjing ,CHINA
Country: CHINA
Tel:
Tel prefix:
Fax:
E-mail address: jackiee.gu@gmail.com
Other E-mails: 07122279@bjtu.edu.cn
Title of the Paper: multi-stages traffic classification methodology using machine learning
Authors as they appear in the Paper: Chengjie Gu; Shunyi Zhang
Email addresses of all the authors: jackiee.gu@gmail.com,dirzsy@njupt.edu.cn
Number of paper pages: 10
Abstract: Classifying Internet traffic with high efficiency and accuracy is very important for network tendency analysis, dynamic access control, routing decision, anomaly detection and QoS provisioning. However, with many newly emerged P2P applications using dynamic port numbers, masquerading techniques, and payload encryption to avoid detection. In this paper, we propose a novel multi-stages traffic classification methodology that brings together the benefits of port mapping, signature matching and flow character classification techniques, motivated by variety of network activities and their requirements of traffic. Experiment results illustrate that this methodology can achieve high accuracy, early detection, low overheads, robust, and real-time to accommodate both unknown and encrypted applications.
Keywords: Traffic classification; Internet protocol; Peer-to-Peer; Machine learning
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 218.2.216.117