基于语义描述与优化的网络性能数据聚类方法  

Network performance data clustering method based on semantic description and optimization

作　　者：姜大庆[1,2] 周勇[2] 夏士雄[2] 

机构地区：[1]南通农业职业技术学院信息工程系,江苏南通226007 [2]中国矿业大学计算机科学与技术学院,江苏徐州221008

出　　处：《计算机应用》2012年第6期1522-1525,共4页journal of Computer Applications

基　　金：国家自然科学基金资助项目(50674086);江苏省教育厅"青蓝工程"基金资助项目(2008-30);南通市科技产业化计划项目(CL2010018)

摘　　要：为了从多源复杂的网络性能数据中挖掘有用模式以提高网络服务质量,研究了基于本体的网络性能监测数据聚类分析方法。阐述了网络性能监测数据的语义描述方法,提出基于语义和属性数据相融合的网络性能数据相似性度量模型,并给出基于改进k-means的NJW(Ng-Jordan-Weiss)谱聚类算法。通过在UCI数据集和校园网性能监测数据集上的实验表明,所提方法较相关比对方法具有更高的聚类准确性和区分度。In order to improve the network quality of service by mining useful model from multi-source and complicated network performance data,a clustering analytical algorithm for network performance monitoring data based on ontology was proposed.The semantic description method of network performance monitoring data was described,then a similarity measurement model of network performance data based on semantic description and property data was proposed,and an NJW（Ng-Jordan-Weiss） spectral clustering algorithm based on improved k-means algorithm was given.The experimental results based on the UCI data sets and the performance monitoring data on a campus network show that the proposed algorithm has a higher clustering accuracy and differentiation than the compared algorithms.

关 键 词：本体 语义描述 语义相似度 谱聚类 网络性能监测 

分 类 号：TP393.06[自动化与计算机技术—计算机应用技术]