期刊文献+

基于集成分类器的流量识别技术研究

下载PDF
导出
摘要 本文提出的基于集成分类器的流量识别技术,由针对不同网络应用的基分类器构成,不同基分类器的判断汇总到决策模块输出最终结果,具有良好的可扩展性,便于增添针对新应用的识别模块;在每个基分类器内部,网络流量首先经过聚类形成若干个簇,在每个簇上单独训练一个分类器,分类器专注于学习簇内部的分类边界;通过增加聚类数量,可以提高集成分类的识别准确率。经实验表明,该技术可以提高单一分类方法的准确性。
作者 徐潇 黄琛
出处 《科技视界》 2015年第33期119-120,232,共3页 Science & Technology Vision
  • 相关文献

参考文献6

  • 1Snort-The de facto standard for intrusion detection/prevention[OL].http://www.snort.org,as of August 14,2007. 被引量:1
  • 2F.Baker,B.Foster,and C.Sharp,Cisco architecture for lawful intercept in IP networks,Internet Engineering Task Force,RFC 3924,2004[Z]. 被引量:1
  • 3Karagiannis T,Broido A,Brownlee N,et al.Is p2p dying or just hiding?[p2p traffic measurement][C]//Global Telecommunications Conference,2004.GLOBECOM'04.IEEE,2004,3:1532-1538. 被引量:1
  • 4Karagiannis T,Broido A,Faloutsos M.Transport layer identification of P2P traffic[C]//Proceedings of the 4th ACM SIGCOMM conference on Internet measurement.ACM,2004:121-134. 被引量:1
  • 5Sen S,Spatscheck O,Wang D.Accurate,scalable in-network identification of p2p traffic using application signatures[C]//Proceedings of the 13th international conference on World Wide Web.ACM,2004:512-521. 被引量:1
  • 6徐鹏,林森.基于C4.5决策树的流量分类方法[J].软件学报,2009,20(10):2692-2704. 被引量:171

二级参考文献17

  • 1Moore AW, Zuev D. Internet traffic classification using Bayesian analysis techniques. In: Proc. of the 2005 ACM SIGMETRICS Int'l Conf. on Measurement and Modeling of Computer Systems, Banff, 2005. 50-60. http://www.cl.cam.ac.uk/-awm22 /publications/moore2005internet.pdf. 被引量:1
  • 2Madhukar A, Williamson C. A longitudinal study of P2P traffic classification. In: Proc. of the 14th IEEE Int'l Syrup. on Modeling, Analysis, and Simulation. Monterey, 2006. http://ieeexplore.ieee.org/xpl/ffeeabs_all.jsp?arnumber=1698549. 被引量:1
  • 3Moore AW, Papagiannaki K. Toward the accurate identification of network applications. In: Dovrolis C, ed. Proc. of the PAM 2005. LNCS 3431, Heidelberg: Springer-Verlag, 2005.41-54. 被引量:1
  • 4Karagiannis T, Papagiannaki K, Faloutsos M. BLINC: Multilevel traffic classification in the dark. In: Proc. of the ACM SIGCOMM. Philadelphia, 2005. 229-240. http://conferences.sigcomm.org/sigcomm/2005/paper-KarPap.pdf. 被引量:1
  • 5Roughan M, Sen S, Spatscheck O, Dutfield N. Class-of-Service mapping for QoS: A statistical signature-based approach to IP traffic classification. In: Proc. of the ACM SIGCOMM Internet Measurement Conf. Taormina, 2004. 135-148. http://www.imconf.net/imc-2004/papers/p 135-roughan.pdf. 被引量:1
  • 6Zuev D, Moore AW. Traffic classification using a statistical approach. In: Dovrolis C, ed. Proc. of the PAM 2005. LNCS 3431, Heidelberg: Springer-Verlag, 2005. 321-324. 被引量:1
  • 7Nguyen T, Armitage G. Training on multiple sub-flows to optimise the use of Machine Learning classifiers in real-world IP networks. In: Proc. of the 31 st IEEE LCN 2006. Tampa, 2006. http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4116573. 被引量:1
  • 8Eerman J, Mahanti A, Arlitt M. Internct traffic identification using machine learning techniques. In: Proc. of the 49th IEEE GLOBECOM. San Francisco, 2006. http://pages.cpsc.ucalgary.ca/-mahanti/papers/globecom06.pdf. 被引量:1
  • 9Erman J, Arlitt M, Mahanti A. Traffic classification using clustering algorithms. In: Proc. of the ACM SIGCOMM Workshop on Mining Network Data (MineNet). Pisa, 2006. http://conferences.sigcomm.org/sigcomm/2006/papers/minenet-01.pdf. 被引量:1
  • 10Bernaille L, Teixeira R, Salamatian K. Early application identification. In: Proc. of the Conf. on Future Networking Technologies 2006 (CoNEXT 2006). Lisboa, 2006. http://portal.acm.org/citation.efm?id=1368445. 被引量:1

共引文献170

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部