Classification of HTTP traffic based on C5.0 Machine Learning Algorithm

Author

Bujlow, Tomasz ; Riaz, Tahir ; Pedersen, Jens Myrup

Author_Institution

Dept. of Electron. Syst., Aalborg Univ., Aalborg, Denmark

fYear

2012

fDate

1-4 July 2012

Abstract

Our previous work demonstrated the possibility of distinguishing several kinds of applications with accuracy of over 99%. Today, most of the traffic is generated by web browsers, which provide different kinds of services based on the HTTP protocol: web browsing, file downloads, audio and voice streaming through third-party plugins, etc. This paper suggests and evaluates two approaches to distinguish various HTTP content: distributed among volunteers´ machines and centralized running in the core of the network. We also assess accuracy of the global classifier for both HTTP and non-HTTP traffic. We achieved accuracy of 94%, which supposed to be even higher in real-life usage. Finally, we provided graphical characteristics of different kinds of HTTP traffic.

Keywords

Internet; learning (artificial intelligence); pattern classification; transport protocols; C5.0 machine learning algorithm; HTTP content; HTTP protocol; HTTP traffic classification; Web browser; Web browsing; audio streaming; file download; global classifier; hypertext transfer protocol; nonHTTP traffic; third-party plugins; voice streaming; Accuracy; Browsers; Computer networks; Multimedia communication; Quality of service; Streaming media; Training; C5.0; HTTP traffic; Machine Learning Algorithms (MLAs); browser traffic; computer networks; performance monitoring; traffic classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Computers and Communications (ISCC), 2012 IEEE Symposium on

Conference_Location

Cappadocia

ISSN

1530-1346

Print_ISBN

978-1-4673-2712-1

Electronic_ISBN

1530-1346

Type

conf

DOI

10.1109/ISCC.2012.6249413

Filename

6249413