BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Machine Learning Approach for Efficient Traffic Classification -
  Wei Li: University of Cambridge
DTSTART:20071018T153000Z
DTEND:20071018T163000Z
UID:TALK8484@talks.cam.ac.uk
CONTACT:Eiko Yoneki
DESCRIPTION:Online traffic classification continues to be of longterm inte
 rest to the networking community. It serves as the input for application m
 odeling and practical solutions such as network monitoring\, quality-of-se
 rvice and intrusion-detection. In this paper we present a machine-learning
  approach that accurately classifies internet traffic using\nC4.5 decision
  tree. Accuracy is not our only concern\; the latency and throughput are a
 lso of extreme importance. Without inspecting packet payload\, our method 
 can identify traffic of different types of applications with 99.8% total a
 ccuracy\, by collecting 12 features at the start of the flows.\n
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR