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 payload–based 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.

1. IANA, “Internet Assigned Numbers Authority", http://www.iana.org/assignments/port-numbers.
2. Massih-Reza Amini, Patrick Gallinari, “The Use of Unlabeled Data to Improve Supervised Learning for Text Summarization”, SIGIR’02, August 11-15, 2002, Tampere, Finland.
3. Jeffrey Erman, Martin Arlitt, Anirban Mahanti SIGCOMM?06 Workshops September 1115, 2006, Pisa , Italy. Traffic Classification Using Clustering Algorithms.
4. Sugato Basu, Mikhail Bilenko, Raymond J. Mooney, “A Probabilistic Framework for Semi-supervised Clustering”, Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining KDD-2004).
5. Automated Traffic Classification and Application Identification using Machine Learning Sebastian Zander, Thuy Nguyen, Grenville Armitage Centre for Advanced Internet Architectures Swinburne University of Technology
6. Tom Auld, Andrew W. Moore, Member, Bayesian Neural Networks for Internet Traffic Classification , IEEE, and Stephen F. Gull , IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 18, NO. 1, JANUARY 2007
7. Byte Me: A Case for Byte Accuracy in Traffic Classification Jeffrey Erman, Anirban Mahanti, Martin Arlitt International Journal of Computer Applications (0975 – 8887) Volume *– No.*, ___________ 2011 5
8. Identifying and Discriminating Between Web and Peer-to-Peer Traffic in the Network Core Jeffrey Erman Anirban Mahanti Martin Arlitt Carey Williamson
9. A. Jain, M. Murty, and P. Flynn, “Data clustering: A review,” ACM Comput. Surv., vol. 31, no. 3, pp. 264–323, 1999.
10. A. K. Jain and R. C. Dubes. Algorithms for Clustering Data. Prentice Hall, Englewood Cliffs, USA, 1988.
11. I. H. Witten and E. Frank. (2005) Data Mining: Pratical MachineLearning Tools and Techniques. Morgan Kaufmann, San Francisco,2nd edition, 2005.
12. M. Ester, H. Kriegel, J. Sander, and X. Xu. A Density-based Algorithm for Discovering Clusters in Large Spatial Databases withNoise. In 2nd Int. Conf. on Knowledge Discovery and Data Mining(KDD 96), Portland, USA, 1996.
13. P. Cheeseman and J. Strutz. Bayesian classification (AutoClass): Theory and Results. In Advances in Knowledge Discovery and Data Mining, AAI/MIT Press, USA, 1996.
14. A. P. Dempster, N. M. Paird, and D. B. Rubin. Maximum likelihood from incomeplete data via the EM algorithm. Journal of the Royal Statistical Society, 39(1):1–38, 1977.
15. Evaluating Machine Learning Algorithms for Automated Network Application Identification Nigel Williams, Sebastian Zander, Grenville Armitage
16. A. Moore and K. Papagiannaki, “Toward the accurate identification of network applications,” in Proc. Passive and Active Measurement Workshop (PAM2005), Boston, MA, USA, March/April 2005.
17. A. Madhukar and C. Williamson, “A longitudinal study of P2P traffic classification,” in 14th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, September 2006.
18. S. Sen, O. Spatscheck, and D. Wang, “Accurate, scalable in network identification of P2P traffic using application signatures,” in WWW2004, New York, NY, USA, May 2004.

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