A preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification
Top Cited Papers
- 10 October 2006
- journal article
- Published by Association for Computing Machinery (ACM) in ACM SIGCOMM Computer Communication Review
- Vol. 36 (5) , 5-16
- https://doi.org/10.1145/1163593.1163596
Abstract
The identification of network applications through observation of associated packet traffic flows is vital to the areas of network management and surveillance. Currently popular methods such as port number and payload-based identification exhibit a number of shortfalls. An alternative is to use machine learning (ML) techniques and identify network applications based on per-flow statistics, derived from payload-independent features such as packet length and inter-arrival time distributions. The performance impact of feature set reduction, using Consistency-based and Correlation-based feature selection, is demonstrated on Naive Bayes, C4.5, Bayesian Network and Naive Bayes Tree algorithms. We then show that it is useful to differentiate algorithms based on computational performance rather than classification accuracy alone, as although classification accuracy between the algorithms is similar, computational performance can differ significantlyKeywords
This publication has 8 references indexed in Scilit:
- Traffic classification on the flyACM SIGCOMM Computer Communication Review, 2006
- BLINCPublished by Association for Computing Machinery (ACM) ,2005
- Internet traffic classification using bayesian analysis techniquesPublished by Association for Computing Machinery (ACM) ,2005
- Automated traffic classification and application identification using machine learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Class-of-service mapping for QoSPublished by Association for Computing Machinery (ACM) ,2004
- Flow Clustering Using Machine Learning TechniquesPublished by Springer Nature ,2004
- Consistency-based search in feature selectionArtificial Intelligence, 2003
- A Comparison of Prediction Accuracy, Complexity, and Training Time of Thirty-Three Old and New Classification AlgorithmsMachine Learning, 2000