计算机科学 ›› 2017, Vol. 44 ›› Issue (Z6): 270-273.doi: 10.11896/j.issn.1002-137X.2017.6A.062

• 网络与通信 • 上一篇    下一篇

WF-C4.5:WiFi环境下基于C4.5决策树的手持终端流量识别方法

石志凯,朱国胜   

  1. 湖北大学计算机与信息工程学院 武汉430062,湖北大学计算机与信息工程学院 武汉430062;湖北省教育信息化工程技术研究中心 武汉430062
  • 出版日期:2017-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受赛尔网络下一代互联网技术创新项目(NGII20150101)资助

WF-C4.5:Handheld Terminal Traffic Identification Method Based on C4.5 Decision Tree in WiFi Environment

SHI Zhi-kai and ZHU Guo-sheng   

  • Online:2017-12-01 Published:2018-12-01

摘要: 目前移动数据流量已占全球IP流量的47%,其中WiFi流量已占整个移动数据流量的90%以上。WiFi环境下移动终端流量的识别对互联网流量管理具有重要意义。传统基于HTTP用户代理(User Agent,UA)的流量识别方法存在识别率不高的问题。分析了WiFi环境下移动终端连接持续时间、数据包大小、有效载荷大小等流量特征,提出一种WiFi环境下基于C4.5决策树的手持终端设备流量识别方法WF-C4.5,通过计算各属性值的信息增益率构建决策树模型,实现手持终端与非手持终端流量的区分。实验表明,相比UA方法65%的准确率,所提方法的准确率高达95%。

关键词: 无线局域网,C4.5决策树,移动终端,流量识别

Abstract: It was reported that mobile terminals account for about 47% global IP traffic while WiFi traffic account for over 90% mobile traffic.Identification of mobile terminal traffic is important for efficient network traffic management.In order to solve the low identification rate problem of traditional HTTP user agent (UA) method,we analyzed the features of mobile terminal traffic in WiFi environment,including the connection persist time,packet size and payload size,etc.We proposed WF-C4.5:a handheld terminal traffic identification method based on C4.5 decision tree in WiFi environment.The method distinguishes handheld terminal traffic from non-handheld traffic by decision tree model which is created by calculating the information gain ratio of each attribute value.The experiments show that the identification rate of WF-C4.5 can reach 95%,while the identification rate of UA is about 65%.

Key words: WiFi WLAN,C4.5 decision tree,Mobile terminal,Traffic identification

[1] 中国互联网络信息中心.第38次中国互联网络发展状况统计报告[EB/OL].[2016-08-01].http://www.cnnic.net.cn/hlwfzyj/hlwxzbg/hlwtjbg/201608/P020160803367337470363.pdf.
[2] Cisco Visual Networking Index:Global Mobile Data Traffic Fo-recast Update,2015-2020 White Paper.http://www.cisco.com/c/en/us/solutions/service-provider/visual-networking-index-vni/index.html#~mobile-forecast.2015.
[3] MAIER G,SCHNEIDER F,FELDMANN A.A first look atmobile hand-held device traffic[C]∥International Conference on Passive and Active Network Measurement.Springer Berlin Heidelberg,2010:161-170.
[4] CHEN X,JIN R,SUH K,et al.Network performance of smart mobile handhelds in a university campus WiFi network[C]∥Proceedings of the 2012 ACM Conference on Internet Measurement Conference.ACM,2012:315-328.
[5] GEMBER A,ANAND A,AKELLA A.A comparative study of handheld and non-handheld traffic in campus Wi-Fi networks[C]∥International Conference on Passive and Active Network Measurement.Springer Berlin Heidelberg,2011:173-183.
[6] GEMBER A,ANAND A,AKELLA A.Handheld vs non-handheld traffic:Implications for campus wifi networks[EB/OL].[2016-08-06].http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.391.4705&rep=rep1&type=pdf.
[7] ZyTrax:Mobile browser id strings.http://zytrax.com/te-ch/web/mobile_ids.html.
[8] 关晓蔷.基于决策树的分类算法研究[D].太原:山西大学,2006.
[9] 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.
[10] DAI Q,ZHANG C,WU H.Research of Decision Tree Classification Algorithm in Data Mining[J].International Journal of Database Theory and Application,2016,9(5):1-8.
[11] The Bro Network Security Monitor.http://www.bro.org.
[12] SELLY D,TROELSEN A.Expert ASP .NET 2.0 Advanced Application Design[M].John Wiley & Sons,2006:29-63.
[13] MARKOV Z,RUSSELL I.An introduction to the WEKA data mining system[J].ACM SIGCSE Bulletin,2006,8(3):367-368.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!