Full metadata record
DC FieldValueLanguage
dc.contributorDepartment of Computingen_US
dc.creatorZhang, Qi-
dc.identifier.urihttps://theses.lib.polyu.edu.hk/handle/200/4332-
dc.languageEnglishen_US
dc.publisherHong Kong Polytechnic University-
dc.rightsAll rights reserveden_US
dc.titleOnline game traffic classificationen_US
dcterms.abstractOnline games are increasing becoming popular in recent years. Especially, multiplayer online games have received much attention in the last few years. There are, however, the characteristics of the online game traffic including browser game, massively multiplayer online game (MMOG), and other type games are understood poorly. The dissertation presents a study on the characteristics of online browser-based game traffics and compares their traffic behavior with web surfing traffic. Furthermore, the identification of game traffic in the Internet is very useful for network to meet Quality of Service (QoS) requirements. Previous traffic identification techniques, such as port-based classification and payload-based classification, are all no longer accurate. Therefore, the newest approach is to use Machine Learning (ML) to classify network applications automatically. In this work, I choose several classifier and clustering machine learning algorithms to identify sixe different types game traffics. They are Mahjong, FashsionDash, ClubMarian, Globulos, Spine World and Card games. Both chosen classifier and cluster algorithms have good performance on identifying traffics. In particular, the highest accuracy is 87% by using C4.5 decision tree algorithm and other algorithms accuracy are all over 77%. And k-means clustering algorithm also has a higher accuracy, about over 81%.en_US
dcterms.extentix, 73 leaves : ill. ; 30 cm.en_US
dcterms.isPartOfPolyU Electronic Thesesen_US
dcterms.issued2009en_US
dcterms.educationalLevelAll Masteren_US
dcterms.educationalLevelM.Sc.en_US
dcterms.LCSHHong Kong Polytechnic University -- Dissertations.en_US
dcterms.LCSHComputer games.en_US
dcterms.LCSHInternetworking (Telecommunication)en_US
dcterms.LCSHMachine learning.en_US
dcterms.accessRightsrestricted accessen_US

Files in This Item:
File Description SizeFormat 
b22661839.pdfFor All Users (off-campus access for PolyU Staff & Students only)3.13 MBAdobe PDFView/Open


Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.

By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

Show simple item record

Please use this identifier to cite or link to this item: https://theses.lib.polyu.edu.hk/handle/200/4332