小波支持向量机的计算机网络安全态势分析  被引量:7

Computer network security situation analysis based on waveletsupport vector machine

在线阅读下载全文

作  者:尚永强[1] SHANG Yongqiang(Xinyang Agriculture and Forestry University,Xinyang 464000,China)

机构地区:[1]信阳农林学院,河南信阳464000

出  处:《现代电子技术》2020年第21期68-71,75,共5页Modern Electronics Technique

基  金:国家自然科学基金(61873160);河南省重点研发与推广专项项目(182102210131)。

摘  要:分析计算机网络安全态势问题时,由于计算机网络存在混沌性、非线性等特征,致使计算机网络安全态势分析误差较大,未能保障计算机网络安全。由此,构建一种基于小波支持向量机的计算机网络安全态势分析模型,获取计算机网络流量的原始变动轨迹,保障支持向量机的和为0;对预处理后的计算机网络流量,采用基于小波分解和支持向量机的网络流量预测模型,实现计算机网络安全态势分析。以某学校计算机网络为例,将该模型的最优时延值与最小嵌入维数依次设成4与7,基于该设定,使用该模型对其安全态势分析后可知,该模型的分析结果和实际情况十分吻合,分析精度较高,且应用该模型后,计算机网络安全性大大提升。When the security situation of computer network is analyzed,there is a large error existing in security situation analysis of computer network because of the chaos and non⁃linearity of computer network,which may reduce the security of computer network.Therefore,a computer network security situation analysis model based on wavelet support vector machine is constructed.The original change trajectory of the computer network traffic is obtained to guarantee the sum of support vector machine to be 0.For the pretreated computer network traffic,the network traffic prediction model based on wavelet decomposition and support vector machine is adopted to realize the computer network security situation analysis.Taking a school′s computer network as an example,the optimal delay value and the minimum embedding dimension of the model are set as 4 and 7 respectively.According to the setting values,after security situation of the model is analyzed with the model,it can be seen that the analysis results of the model are very consistent with the actual situation,and its analysis accuracy is high.Moreover,the computer network security is greatly improved after the application of the model.

关 键 词:安全态势分析 计算机网络 网络流量预处理 模型构建 支持向量机 时延设定 

分 类 号:TN915.08-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象