Study on the method of effective extraction of virus feature large joint network

DOI

10.2991/amcce-15.2015.221How to use a DOI?

Keywords

large joint network; virus feature; effective classification; game factor

Abstract

In large joint network, traditional methods cannot accurately determine the source of virus, leading to data classification of virus feature extraction model in joint network with a low convergence efficiency. A kind of virus feature extraction model for large joint network based on unconstrained clustering correlation and repeated game factor is put forward, according to the identification attribute of access data perfect it. Using unconstrained clustering correlation virus detection algorithm make accurate classification of the multi feature interference in joint network. In the classification probability calculation, constraints computational game factors are introduced. Using data game filter multi-time probabilistic contrast in the features probability matching process of joint network virus. By calculating the optimal reaction function, makes the joint network virus feature extraction to achieve optimal. Simulation results show that, the proposed model can effectively extract the characteristics of joint network virus, and the efficiency and the accuracy is better than the traditional model, has obvious optimization effect.

Copyright

© 2015, 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  - Zhihua Zhang
PY  - 2015/04
DA  - 2015/04
TI  - Study on the method of effective extraction of virus feature large joint network
BT  - Proceedings of the 2015 International Conference on Automation, Mechanical Control and Computational Engineering
PB  - Atlantis Press
SN  - 1951-6851
UR  - https://doi.org/10.2991/amcce-15.2015.221
DO  - 10.2991/amcce-15.2015.221
ID  - Zhang2015/04
ER  -