2005 · 515 citations · 10 references
ComputingComputer ScienceData MiningFeature EngineeringMachine LearningFeature SelectionFlow Feature ExtractionNetwork Traffic AnalysisTraffic Flow AnalysisTraffic Flow TheoryApplication LayerApplication Traffic IdentificationFlow-based AnalysisMachine Learning For Traffic AnalysisStatistical Traffic AnalysisTraffic ClassificationTraffic Feature ExtractionUnsupervised Feature Selection
Dynamic classification of network applications is valuable for IP network engineering, but existing methods based on port numbers or protocol decoding suffer from unpredictable ports, high computational cost, and infeasibility for unknown or encrypted protocols. The study proposes an unsupervised machine learning approach for traffic classification and application identification. Flows are classified using statistical flow characteristics, with feature selection to identify an optimal set, and the method’s efficiency is evaluated on traffic traces from multiple Internet locations.
The dynamic classification and identification of network applications responsible for network traffic flows offers substantial benefits to a number of key areas in IP network engineering, management and surveillance. Currently such classifications rely on selected packet header fields (e.g. port numbers) or application layer protocol decoding. These methods have a number of shortfalls e.g. many applications can use unpredictable port numbers and protocol decoding requires a high amount of computing resources or is simply infeasible in case protocols are unknown or encrypted. We propose a novel method for traffic classification and application identification using an unsupervised machine learning technique. Flows are automatically classified based on statistical flow characteristics. We evaluate the efficiency of our approach using data from several traffic traces collected at different locations of the Internet. We use feature selection to find an optimal feature set and determine the influence of different features
10
A Comparative Study on Feature Selection in Text Categorization
Yiming Yang, Jan Pedersen · 1997 · 4.8K citations
Correlation-based Feature Selection for Machine Learning
Mark Hall · 1998 · 3.5K citations
Bayesian classification (AutoClass): theory and results
Peter Cheeseman, John Stutz · 1996 · 974 citations