On Internet Traffic Classification-A Two-Phased ML英文文献资料.pdf

Hindawi Publishing Corporation Journal of Computer Networks and Communications Volume 2016, Article ID 2048302, 21 pages /10.1155/2016/2048302 Research Article On Internet Traffic Classification: A Two-Phased Machine Learning Approach Taimur Bakhshi and Bogdan Ghita Center for Security, Communications and Network Research, University of Plymouth, Plymouth PL4 8AA, UK Correspondence should be addressed to Taimur Bakhshi; taimur.bakhshi@plymouth.ac.uk Received 26 November 2015; Revised 15 April 2016; Accepted 8 May 2016 Academic Editor: Tin-Yu Wu Copyright 漏 2016 T. Bakhshi and B. Ghita. his is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Traic classiication utilizing low measurement enables operators to perform essential network management. Flow accounting methods such as NetFlow are, however, considered inadequate for classiication requiring additional packet-level information, host behaviour analysis, and specialized hardware limiting their practical adoption. his paper aims to overcome these challenges by proposing two-phased machine learning classiication mechanism with NetFlow as input. he individual low classes are derived per application through 肀?means and are further used to train a C5.0 decision tree classiier. As part of validation, the initial unsupervised phase used low records of iteen popular Internet applications that were collected and independently subjected to 肀? means clustering to determine unique low classes generated per application. he derived low classes were aterwards used to train and test a supervised C5.0 based decision tree. he resulting classiier reported an average accuracy of 92.3