小波神经网络应用于电子政务信息系统安全风险评估  

Application of Wavelet Neural Network in Risk Assessment of E-Government Information System

作　　者：孙树静[1] 刘明生[1] 尹晓华[2] 

机构地区：[1]石家庄铁道学院计算机与信息工程分院,河北石家庄050043 [2]河北建筑科学研究院质量检测中心,河北石家庄050021

出　　处：《石家庄铁道学院学报》2007年第3期69-73,共5页Journal of Shijiazhuang Railway Institute

基　　金：河北省自然科学基金资助项目(03579325A)

摘　　要：针对电子政务信息系统风险评估的复杂性和不确定性,作者提出了小波神经网络评估方法,建立了小波神经网络评估模型,最后采用Matlab7.1工具进行了仿真实验,并分别从网络的收敛速度、训练精度和训练效果上与BP神经网络算法作了对比。结果证实该方法有效克服了传统方法中人为分配权重带来的主观性,使评价结果更科学,更合理。This paper analyzes the complexity and uncertainty of the risk factors in information system, presents a Wavelet Neural Network（WNN） method which can be used to the security risk evaluation of information system, creates a corresponding model and has done simulated experiments by Matlab7.1. Besides, the author makes a comparison between WNN and BP algorithm respectively in convergent speed, training precision and effect. The study of the case shows that, with this method, subjective judgment in previous research is avoided and the results are more scientific and reasonable.

关 键 词：电子政务 风险评估 小波网络 权重 BP算法 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]