Deakin home > Deakin University Library > Deakin Research Online > Internet traffic classification using machine learning : a token-based approach

Internet traffic classification using machine learning : a token-based approach

Wang, Yu, Xiang, Yang and Yu, Shunzheng 2011, Internet traffic classification using machine learning : a token-based approach, in CSE 2011 : Proceedings of the 14th IEEE International Conference on Computational Science and Engineering, IEEE, [Dalian, China], pp. 285-289.

Attached Files (Some files may be inaccessible until you login with your Deakin Research Online credentials)
Name Description MIMEType Size Downloads

Title Internet traffic classification using machine learning : a token-based approach
Author(s) Wang, Yu
Xiang, Yang
Yu, Shunzheng
Conference name International Conference on Computational Science and Engineering (14th : 2011 : Dalian, China)
Conference location Dalian, China
Conference dates 24-26 Aug. 2011
Title of proceedings CSE 2011 : Proceedings of the 14th IEEE International Conference on Computational Science and Engineering
Editor(s) [Unknown]
Publication date 2011
Conference series International Conference on Computational Science and Engineering
Start page 285
End page 289
Publisher IEEE
Place of publication [Dalian, China]
Keyword(s) common substrings
feature selection
internet traffic classification
machine learning
Summary Due to the increasing unreliability of traditional port-based methods, Internet traffic classification has attracted a lot of research efforts in recent years. Quite a lot of previous papers have focused on using statistical characteristics as discriminators and applying machine learning techniques to classify the traffic flows. In this paper, we propose a novel machine learning based approach where the features are extracted from packet payload instead of flow statistics. Specifically, every flow is represented by a feature vector, in which each item indicates the occurrence of a particular token, i.e.; a common substring, in the payload. We have applied various machine learning algorithms to evaluate the idea and used different feature selection schemes to identify the critical tokens. Experimental result based on a real-world traffic data set shows that the approach can achieve high accuracy with low overhead.
ISBN 9780769544779
9781457709746
Language eng
Field of Research 080503 Networking and Communications
Socio Economic Objective 890201 Application Software Packages (excl. Computer Games)
HERDC Research category E1 Full written paper - refereed
HERDC collection year 2011
Copyright notice ©2011, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30042194

Document type: Conference Paper
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in Deakin Research Online is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 50 Abstract Views, 5 File Downloads  -  Detailed Statistics
Created: Tue, 14 Feb 2012, 15:13:46 EST