A Feature Analysis Approach to Network Traffic in Communication Networks

DOI

10.2991/ceie-16.2017.83How to use a DOI?

Keywords

Network Traffic; Feature Analysis; Time-Frequency Analysis; Feature Extraction

Abstract

Network traffic holds the highlighting dynamic features. How to accurately characterize the hidden properties of network traffic has an important impact on network activities, such as anomaly detection and performance analysis. This paper proposes a feature analysis approach to describe network traffic. Firstly, the wavelet packet transformation is used to extract the multi-scale feature of network traffic. Then the principal component analysis method is exploited to refine the hidden features of network traffic in the time-frequency domain. Finally, to validate our feature analysis method, an anomaly detection test is conducted. Simulation results show that our approach is promising.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Honghao Zhao
AU  - Hongyu Dong
AU  - Xiaohui Zhang
AU  - Qing Ye
AU  - Fanbo Meng
AU  - Xinyu Sun
AU  - Ying Cao
PY  - 2016/10
DA  - 2016/10
TI  - A Feature Analysis Approach to Network Traffic in Communication Networks
BT  - Proceedings of the International Conference on Communication and Electronic Information Engineering (CEIE 2016)
PB  - Atlantis Press
SP  - 648
EP  - 655
SN  - 2352-5401
UR  - https://doi.org/10.2991/ceie-16.2017.83
DO  - 10.2991/ceie-16.2017.83
ID  - Zhao2016/10
ER  -