Author : Hari Krishna Mishra 1
Date of Publication :22nd May 2018
Abstract: Over the last few years, there has been a rapid increase in the variety and volume of Internet traffic. The regular method of classifying this traffic relies on known IANA assigned port numbers or inspecting the payload. However, these methods are not effective as the used port numbers can differ from well-known or official ones. Payload inspection is not effective either because applications encrypt their data before sending. A new machine learning technique for network traffic classification is proposed by us to overcome this drawbacks. Services on the Internet can be grouped into different classes. There are a number of of websites in an educational institutions. They are educational websites and non-educational. Educational services are used for learning and research purposes, whereas non-educational services include entertainment, social networking and communication. Our goal is to classify the traffic effectively and ensure optimal and fair bandwidth allocation among Internet users in the institution giving higher priority to educational services. In this paper, we have used kNN classifiers to classify the accessed services at different values of K [1]. For classification accuracy in terms of dataset, the value of K should be found. For that we have collected many results and datasets. We need good features to get better classification accuracy [2], [3].
Reference :
-
- T. Wiradinata and A. S. Paramita, “Clustering and feature selection technique for improving internet traffic classification using k-nn,” 2016
- S. Lee, K. Levanti, and H. S. Kim, “Network monitoring: Present and future,” Computer Networks, vol. 65, pp. 84–98, 2014.
- M. Joshi and T. H. Hadi, “A review of network traffic analysis and prediction techniques,” arXiv preprint arXiv:1507.05722, 2015.
- K. Singh, S. Agrawal, and B. Sohi, “A near realtime ip traffic classification using machine learning,” International Journal of Intelligent Systems and Applications, vol. 5, no. 3, p. 83, 2013.
- J. Kaur, S. Agrawal, and B. Sohi, “Internet traffic classification for educational institutions using machine learning,” International Journal of Intelligent Systems and Applications, vol. 4, no. 8, p. 37, 2012.