全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于流统计特性的网络流量分类算法

DOI: 10.13190/jbupt.200802.15.linp, PP. 15-19

Keywords: 网络流量分类,,统计特征,多项逻辑斯谛回归

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对传统基于单个流统计特性的网络流量分类算法识别率低、分类算法复杂的问题,在分析各类应用协议的基础上,发现了一组易于获取、可有效区分不同业务的网络流量特征。将这一组特征应用于网络流量分类,可以有效解决以往对等网络(P2P)业务识别率低下的问题;同时利用该组特征仅需采用多项逻辑斯谛回归算法即可实现网络流量的分类,较传统流量分类算法有较低的复杂度。实验结果表明,该组特征用于分类还具有较好的泛化特性,只需较少量训练样本即可在在较长时间内保持较高的识别率。

References

[1]  Logg C. Characterization of the traffic between SLAC and the Internet. .
[2]  Moore D, Keys K, Koga R, et al. Claffy CoralReef software suite as a tool for system and network administrators//Burgess M. Proceedings of the LISA 2001 15th Systems Administration Conference. San Diego: USENIX, 2001: 133-144.
[3]  San S, Spatscheck O, Wang D. Accurate, scalable in-network identification of P2P traffic using application signatures//Proceeding of the 13th Internation World Wide Web Conference. NY: ACM Press, 2004: 512-521.
[4]  Haffner P, Sen S, Spatscheck O, et al. ACAS: automated construction of application signatures//ACM SIGCOMM Workshop on MineNet 2005. Philadelphia: ACM Press, 2005: 197-202.
[5]  Cisco IOS Documentation. Network-based application recognition and distributed network-based application recognition. .
[6]  Moore A W, Zuev D. Internet traffic classification using Bayesian analysis techniques//ACM SIGMETRICS. New York: ACM Press, 2005: 50-60.
[7]  Auld T, Moore A W, Gull S F. Bayesian neural networks for Internet traffic classification[J]. IEEE Trans on Neural Network, 2007, 18(1):223-239.
[8]  Okabe T, Kitamura T, Shizuno T. Statistical traffic identification method based on flow-level behavior for fair VoIP service//IEEE Workshop on VoIP Management and Security. Vancouver: IEEE Press, 2006: 35-40.
[9]  Karagiannis T, Papagiannaki K, Faloutsos M. BLINC: multilevel traffic classification in the dark//ACM SIGCOMM 2005. Philadelphia: ACM Press, 2005: 229-240.
[10]  Webb A R. Statistical pattern recognition[M]. 2nd ed. England: Wiley, 2004: 161-162.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133