Fine-grained traffic classification based on functional separation

摘要: SUMMARY Current efforts to classify Internet traffic highlight accuracy. Previous studies have focused on the detection of major applications such as P2P and streaming applications. However, these can generate various types which are often considered minor ignorant portions. As network become more complex, price paid for not concentrating classes is in reduction accuracy completeness. In this context, we propose a fine-grained classification scheme its detailed method, called functional separation. Our proposal detect, according functionalities, different generated by single application should increase completeness reducing amount undetected traffic. We verify our method with real-world performance comparison against existing DPI-based frameworks shows that achieves consistently higher accuracyand Copyright © 2013 John Wiley & Sons, Ltd.