• Feb 07, 2023 News!JACN will adopt Article-by-Article Work Flow. The benefit of article-by-article workflow is that a delay with one article may not delay the entire issue. Once a paper steps into production, it will be published online soon.   [Click]
  • May 30, 2022 News!JACN Vol.10, No.1 has been published with online version.   [Click]
  • Dec 24, 2021 News!Volume 9 No 1 has been indexed by EI (inspec)!   [Click]
General Information
    • ISSN: 1793-8244 (Print)
    • Abbreviated Title:  J. Adv. Comput. Netw.
    • Frequency: Semiyearly
    • DOI: 10.18178/JACN
    • Editor-in-Chief: Professor Haklin Kimm
    • Executive Editor: Ms. Cherry Chan
    • Abstracting/ Indexing: EBSCO, ProQuest, and Google Scholar.
    • E-mail: jacn@ejournal.net
    • APC: 500USD
Professor Haklin Kimm
East Stroudsburg University, USA
I'm happy to take on the position of editor in chief of JACN. We encourage authors to submit papers on all aspects of computer networks.

JACN 2020 Vol.8(2): 36-43 ISSN: 1793-8244
DOI: 10.18178/JACN.2020.8.2.278

Improve the DFI-based Network Traffic Classification Performance by Using QoS Metrics

Yongcheng Zhou and Anguo Zhang

Abstract—Network traffic classification methods based on network flow characteristics and machine learning classifiers have received extensive attention in academia. However, in actual industrial applications, the current mainstream flow identification engines, especially commercial engines, still mainly adopt port-based and deep packet inspection (DPI)-based network traffic dentification methods, deep flow inspection (DFI) has not been officially promoted yet. In addition to the fact that causal reasoning of general machine learning classifiers is difficult to analyze, another big reason is that the machine learning classifiers in most of the current research results are difficult to work well in different Internet network situations after training on a training set. Through experiments, we found that the basic QoS parameters of the network, such as packet loss rate, transmission delay, throughput rate and network jitter, in addition to being able to describe the performance state of the current network, will further affect some DFI features of the network flow. In this paper, we do not try to come up with completely new traffic classification features or completely new classifiers, but rather try to make some small improvements on the existing DFI methods so that the DFI classifiers can work precisely and robustly under different network topologies and network QoS parameters. Experimental results in different network environments show that these additional QoS parameters can significantly improve the robustness of the existing DFI machine learning classifiers.

Index Terms—Network traffic classification, network QoS metrics, deep flow inspection.

Zhou Yongcheng is with Ruijie Networks Co., Ltd, Fuzhou 350002, China (e-mail: zhouyongcheng_024@163.com). Zhang Anguo is with College of Physics and information Engineering, Fuzhou University, Fuzhou 350108, China, and the Key Laboratory of Medical Instrumentation and Pharmaceutical Technology of Fujian Province, Fuzhou 350116, China (Corresponding author, e-mail: anguo.zhang@hotmail.com).


Cite:Yongcheng Zhou and Anguo Zhang, "Improve the DFI-based Network Traffic Classification Performance by Using QoS Metrics," Journal of Advances in Computer Networks vol. 8, no. 2, pp. 36-43, 2020.

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
First page
Last page
Copyright © 2008-2024. Journal of Advances in Computer Networks.  All rights reserved.
E-mail: jacn@ejournal.net