2026-07-20T11:16:34Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:2958 2024-03-06T10:28:49Z ddc:004 open_access

Improving Markov-based TCP Traffic Classification Münz, Gerhard Heckmüller, Stephan Braun, Lothar Carle, Georg Markov model TCP Traffic Classification network This paper presents an improved variant of our Markov-based TCP traffic classifier and demonstrates its performance using traffic captured in a university network. Payload length, flow direction, and position of the first data packets of a TCP connection are reflected in the states of the Markov models. In addition, we integrate a new "end of connection" state to further improve the classification accuracy. Using 10-fold cross validation, we identify appropriate settings for the payload length intervals and the number of data packets considered in the models. Finally, we discuss the classification results for the different applications. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Gerhard Münz and Stephan Heckmüller and Lothar Braun and Georg Carle 2011 Is Part Of OASIcs, Volume 17, 17th GI/ITG Conference on Communication in Distributed Systems (KiVS 2011) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.KiVS.2011.61 urn:nbn:de:0030-drops-29582 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.KiVS.2011.61 eng https://creativecommons.org/licenses/by-nc-nd/3.0/legalcode