Title: Traffic classification combining flow correlation and ensemble classifier

Authors: Chang Sheng Miao; Lu Meng; Chang Qing Yuan; Xing Wei Wang; Gui Ran Chang

Addresses: School of Information Science and Engineering, Northeastern University, Shenyang 110819, China ' School of Information Science and Engineering, Northeastern University, Shenyang 110819, China ' School of Information Science and Engineering, Northeastern University, Shenyang 110819, China ' School of Information Science and Engineering, Northeastern University, Shenyang 110819, China ' Computing Center, Northeastern University, Shenyang 110819, China

Abstract: Traffic classification has wide applications in network measurements, network security and quality of service. Recent research tends to apply machine learning methods based on flow statistical features to improve traffic classification performance. In this paper, we propose a novel non-parametric approach for traffic classification, which can improve the classification performance effectively by incorporating correlated information into the classification process. Meanwhile, our system employs a lightweight modular architecture, which combines a series of simple linear binary classifiers, each of which can be efficiently implemented and trained on vast amounts of flow data in parallel, to achieve scalability while attaining high accuracy. A large number of experiments are carried out on real traffic data to validate the proposed approach. The results show that the traffic classification performance can be improved significantly while meeting the scalability and stability requirements of large networks.

Keywords: traffic classification; ADStump; flow correlation; ensemble classifiers; network measurement; network security; quality of service; QoS; network traffic; large networks.

DOI: 10.1504/IJWMC.2013.057575

International Journal of Wireless and Mobile Computing, 2013 Vol.6 No.6, pp.556 - 563

Received: 13 Jun 2013
Accepted: 01 Jul 2013

Published online: 16 Oct 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article