Study on the Network Traffic Abnormal Detection Based on EEMD

DOI

10.2991/ameii-16.2016.191How to use a DOI?

Keywords

Network Traffic, Abnormal Detection, EEMD, RBF neural network

Abstract

Network traffic abnormal directly reflects the health status of the network and real time detection of network traffic abnormal is very important. Hereby a method of network traffic abnormal detection method based on ensemble empirical mode decomposition (EEMD) was proposed. The historical network traffic data was collected and analysis by EEMD and the radial basis function (RBF) neural network prediction model is established for network traffic abnormal detection. The historical network traffic data removes the abnormal data by analysis of intrinsic mode function (IMF), which is used as the input of the RBF neural network for prediction. If the error between prediction value and the actual value is larger than a threshold, then this point of network traffic can be judged as an abnormal data. The proposed method takes advantages of network traffic prediction and EEMD analysis, which can implement real time detection of network traffic abnormal.

Copyright

© 2016, 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  - Zhigang Zhao
PY  - 2016/04
DA  - 2016/04
TI  - Study on the Network Traffic Abnormal Detection Based on EEMD
BT  - Proceedings of the 2nd International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 2016)
PB  - Atlantis Press
SP  - 1001
EP  - 1005
SN  - 2352-5401
UR  - https://doi.org/10.2991/ameii-16.2016.191
DO  - 10.2991/ameii-16.2016.191
ID  - Zhao2016/04
ER  -