Early traffic classification using support vector machines

摘要: Internet traffic classification is an essential task for managing large networks. Network design, routing optimization, quality of service management, anomaly and intrusion detection tasks can be improved with a good knowledge the traffic.Traditional methods based on transport port analysis have become inappropriate modern applications. Payload using pattern searching privacy concerns are usually slow expensive in computational cost.In recent years, statistical properties flows has relevant topic. In this work we analyze size firsts packets both directions flow as fingerprint. This fingerprint enough accurate so useful early identification real time.This proposes use supervised machine learning clustering method Support Vector Machines. We compare our accuracy more classical centroid approach, obtaining promising results.