摘要
面对网络通信中的海量高维数据,为提高信息安全检测的效率、准确率,提出一种基于主成分分析(PCA)的数据降维方法。将降维后的数据作为输入,经过BP神经网络进行识别,通过Matlab仿真实验并与传统的识别方法进行比较,结果表明,这种简化数据结构的神经网络不仅提高了对已知的异常数据的识别率,而且对新出现的异常数据也有很好的识别效果。
Facing with massive high-dimensional data in network communication,information security detection methods, in order to improve the efficiency and accuracy,a data dimension reduction method based on principal component analysis PCA (principal component analysis) is proposed.The dimension-reduced data is recognized by BP neural network as input, and is simulated by Matlab.Compared with the traditional recognition method,this simplified data structure neural network not only improves the recognition rate of the known abnormal data,but also has a good recognition effect on the newly generated abnormal data.
作者
王远志
高标
陆文成
WANG Yuanzhi;GAO Biao;LU Wencheng(School of Computer&Information,Anqing Normal University,Anqing 246133,China)
出处
《安庆师范大学学报（自然科学版）》
2019年第4期40-44,共5页
Journal of Anqing Normal University(Natural Science Edition)
基金
高校优秀中青年骨干人才国外访学研修重点项目（gxfxZD2016175）
安徽高校自然科学研究重点项目（KJ2018A0359）
关键词
统计方法
主成分分析
BP神经网络
信息安全
statistical method
principal component analysis
BP neural network
information safety
