A Quantitative Prediction Method of Network Security Situation Based on Wavelet Neural Network

Author

Jibao, Lai ; Huiqiang, Wang ; Xiaowu, Liu ; Ying, Liang

Author_Institution

Harbin Eng. Univ., Harbin

fYear

2007

fDate

1-3 Nov. 2007

Firstpage

197

Lastpage

202

Abstract

In order to predict the network security situation, a quantitative prediction method of network security situation based on wavelet neural network (WNN) was proposed. After analyzing the past and the current network security situation in detail, we built the WNN architecture of network security situation prediction and adopted it to forecast the non-linear time series of network security situation. Simulation experiments proved that the proposed method had advantages over a back propagation neural network method (BPNN) with the same architecture in the convergence speed, functional approximation and prediction accuracy.

Keywords

computer networks; neural nets; telecommunication security; time series; wavelet transforms; back propagation neural network method; network security situation; nonlinear time series; quantitative prediction method; wavelet neural network; Computer science; Computer security; Data engineering; Data security; Educational institutions; Information security; National security; Neural networks; Prediction methods; Time series analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Data, Privacy, and E-Commerce, 2007. ISDPE 2007. The First International Symposium on

Conference_Location

Chengdu

Print_ISBN

978-0-7695-3016-1

Type

conf

DOI

10.1109/ISDPE.2007.36

Filename

4402673