因子分析和神经网络的信息系统风险评估模型

Information system risk assessment model based on factor analysis and neural network

风险评估是信息系统应用必不可少的一项技术,为此,提出一种因子分析和神经网络的信息系统风险评估模型。构建可有效描述信息系统风险情况的信息系统风险评估指标体系,采用因子分析法消除指标相关性、降低风险评估指标体系复杂度,获取公共评估指标;采用灰狼优化(GWO)算法优化BP神经网络,解决其收敛速度慢、容易陷入局部最优、初始化参数具备较强依赖性等问题;将所获公共指标作为GWO-BP神经网络的输入数据,建立信息系统风险评估模型,实现信息系统风险评估。在Matlab环境下完成模型仿真验证,结果表明,所提模型可有效降低风险指标相关性,提升信息系统风险评估的速率,且收敛速度快、信息系统风险评估准确性高。

Risk assessment is an essential technology in the application of information system.Therefore,an information system risk assessment model based on factor analysis and neural network is proposed.An index system of information system risk assessment is constructed,which can effectively describe the risk situation of information system.The factor analysis method is used to eliminate the correlation among the indexes,reduce the complexity of the risk assessment index system,and obtain the public assessment indexes.The grey wolf optimizer(GWO)algorithm is used to optimize the BP neural network to solve the problems of slow convergence,prone to falling into local optimization,strong dependence of initialization parameters,etc.The public index is taken as the input data of GWO-BP neural network to establish the risk assessment model of information system and realize the risk assessment of information system.The results of the model simulation experiment in Matlab environment show that the proposed model can effectively reduce the correlation among risk indicators,improve the velocity of information system risk assessment,and it also has fast convergence speed and high accuracy of information system risk assessment.