Optimization of a Hybrid Traffic Identification Model Based on DPI

DOI

10.2991/icmeit-17.2017.15How to use a DOI?

Keywords

Traffic identification, DPI, Machine Learning

Abstract

In recent years, Internet Service Providers (ISPs) provide increasingly extensive services, and a large number of applications came into being. These applications provide users a lot of convenience, lead to the network traffic flow increasing, and make the complexity of flow components increasing. In this paper, we design a new DPI module based on OpenDPI. The experiments show that the hybrid model has been achieved the precision of >96%.

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  - Wenbei Duan
AU  - Yuanli Wang
AU  - Xiu Xiong
PY  - 2017/05
DA  - 2017/05
TI  - Optimization of a Hybrid Traffic Identification Model Based on DPI
BT  - Proceedings of the 2nd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2017)
PB  - Atlantis Press
SP  - 77
EP  - 80
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmeit-17.2017.15
DO  - 10.2991/icmeit-17.2017.15
ID  - Duan2017/05
ER  -