Full metadata record
DC FieldValueLanguage
dc.contributor.authorWang, Yi-Hsienen_US
dc.contributor.authorGau, Victoren_US
dc.contributor.authorBosaw, Trevoren_US
dc.contributor.authorHwang, Jenq-Nengen_US
dc.contributor.authorLippman, Alanen_US
dc.contributor.authorLieberman, Danen_US
dc.contributor.authorWu, I-Chenen_US
dc.date.accessioned2014-12-08T15:48:23Z-
dc.date.available2014-12-08T15:48:23Z-
dc.date.issued2008en_US
dc.identifier.isbn978-1-4244-2375-0en_US
dc.identifier.issn1551-2541en_US
dc.identifier.urihttp://hdl.handle.net/11536/32231-
dc.description.abstractIn this paper, we develop a peer-to-peer (P2P) traffic identifier to facilitate quality of service (QoS) control in edge routers. Currently, since P2P applications consume a great percentage of Internet bandwidth, certain network optimization strategies are needed to improve the nerwork performance. Traffic identification is the most important component that could be adopted in these optimization strategies. In this paper, we focus on developing a machine learning strategy to perform quick identification, and continuous tracking of flows associated with various P2P media streaming and file sharing applications. With the use (if Random Forests (RF) and evaluated by using 10-fold cross validation, our method achieves greater than 98% accuracy rate and 89% precision rate of identifying the P2P flows, with less than 1% false positive rate. With the help of winner-lake-all strategy, the generalization performance of using the RF built with data collected from one network to classify flows in other networks can achieve accuracy of being over 97%, with the precision being over 81% and the FP rate being below 2%.en_US
dc.language.isoen_USen_US
dc.titleGeneralization Performance Analysis of Flow-based Peer-to-Peer Traffic Identificationen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2008 IEEE WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSINGen_US
dc.citation.spage267en_US
dc.citation.epage272en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000266687900046-
Appears in Collections:Conferences Paper