Academic Journals Database
Disseminating quality controlled scientific knowledge

State Of Art Survey of Network Traffic Classification

ADD TO MY LIST
 
Author(s): Sheetal S. Shinde | Sandeep P. Abhang

Journal: International Journal of Computer Applications
ISSN 0975-8887

Volume: iccia;
Issue: 7;
Date: 2012;
Original page

Keywords: TCP | Traffic Classification | Machine Learning (ML) | unsupervised clustering | supervised learning | semi-supervised learning

ABSTRACT
This is a review paper of Network Traffic Classification Techniques. The survey looks at network traffic classification methods used by researchers as well as emerging research into the application of Machine Learning (ML) techniques to IP traffic classification. Current popular methods such as port numbers and payloadbased identification exhibit a number of shortfalls, an alternative is to use ML techniques. It is also required to detect network applications based on flow statistics. The paper also take a review of clustering algorithms as well as various important approaches to semi-supervised learning The survey concludes that the K-means is a fastest algorithm as compared to DBSCAN and AutoClass. Another conclusion is the semi-supervised approach is a best classification approach for network traffic classification as compared with other techniques.

Tango Rapperswil
Tango Rapperswil

     Save time & money - Smart Internet Solutions