计算机应用研究2011，Vol.28Issue(7)：2750-2753,4.DOI:10.3969/j.issn.1001-3695.2011.07.099
基于优化SVM的P2P协议识别
Novel P2P protocol identification algorithm based on optimized SVM
摘要
Abstract
To overcome the shortcomings of P2P application, this paper proposed a new P2P identification algorithm which used DFI deep flow analysis by extracting the various properties of P2P data stream characteristics, using support vector machine which was optimized by Grid Search, generation algorithm and particle swarm optimization to assort the network data streams. Experimental results of the P2P and non-P2P classification show that the classifier by SVM has a high accuracy over 90% , and the highest can be 97%.关键词
粒子群算法/遗传算法/支持向量机/P2P/协议识别Key words
PSO/ GA/ SVM/ P2P/ protocol identification分类
信息技术与安全科学引用本文复制引用
毛灵,陈兴蜀,吴仲光,谭骏,杜敏..基于优化SVM的P2P协议识别[J].计算机应用研究,2011,28(7):2750-2753,4.基金项目
国家“973”计划重点基础研究发展资助项目(2007CB311106) （2007CB311106）
国防重点实验室基金资助项目(NEUL20090101) （NEUL20090101）
