Mahidol University Logo
Faculty of ICT, Mahidol University
 

Admissions

Printable Version

 

WEB TRAFFIC CLASSIFICATION

 

TITLE WEB TRAFFIC CLASSIFICATION
AUTHOR SAMRUAY KAOPRAKHON
DEGREE MASTER OF SCIENCE PROGRAMME IN COMPUTER SCIENCE
FACULTY FACULTY OF SCIENCE
ADVISOR VASAKA VISOOTTIVISETH
CO-ADVISOR SUDSANGUAN NGAMSURIYAROJ
SIWARUK SIWAMOGSATHAM
 
ABSTRACT
A wide use of the Internet introduces various online services such as online games, radio, music, TV and video clips, which communicate over Hyper Text Transfer Protocol (HTTP). These services maybe consume a large bandwidth. Therefore, if there are some employees using these services, the misuse could directly impact network bandwidth consumption. In this work, we aim to classify web traffic into three types: audio, video and normal web traffic. We propose a classification method based on the information flow. Our classification use a combination of keyword matching techniques and statistical behavior profiles. Keywords are pre- defined by observing from both audio and video traffic. Behavior profiles consist of three attributes, which are the average received packet size, a ratio of the number of server-client packets, and the flow duration. Each attribute has an independent threshold of mean (u) and standard deviation (o). The experimental results show that our method can classify audio, video and normal web traffic with high precision and recall.
KEYWORD WEB TRAFFIC CLASSIFICATION /VIDEO TRAFFIC/AUDIO TRAFFIC/KEYWORD MATCHING/BEHAVIOR PROFILE MATCHING/FLOW BASED CLASSIFICATION

 

 

Go to Top

 

ICT Building, Mahidol University, 999 Phuttamonthon 4 Road, Salaya, Nakhonpathom 73170 Tel. +66 02 441-0909 Fax. +66 02 849-6099
Mahidol University Computing Center, The Faculty of ICT, Mahidol University , Rama 6 Road, Rajathevi, Bangkok 10400 Tel. +66 02 354-4333 Fax. +66 02 354-7333