Automatic flow classification using machine learning Export

@inproceedings{citeulike:2340736, abstract = {Network standards are moving toward the Quality-of-Service (QoS) networking. Differentiated Services (DiffServ) QoS model is adopted by many recent and upcoming networks standard. Applications running on these networks can specify suitable service classes to their connections or flows. The flows are then treated according to their service classes. However, current Internet applications are still designed based on besteffort scheme and, therefore, cannot benefit from QoS support from the network. An automatic flow classification framework, which can automatically classify non QoS-aware flows or legacy flows, has been proposed in our earlier work [2]. In this paper, we extend our framework by introducing new features that can be effectively used to classify legacy flows. The simplicity of these features allows the data to be collected in real-time. No packetlevel data are required. Furthermore, the framework is evaluated using multiple data sets from different users. The results show that our framework works extremely well in general and it can be operated independently from any applications, networks or even machine learning algorithms. Average correctness up to 98.82\% is achieved when the framework is used to learn and classify unseen flows from the same user. Cross-user classifications yield average correctness up to 74.15\%.}, author = {Anantavrasilp, Isara and Scholer, Thorsten}, booktitle = {Software, Telecommunications and Computer Networks, 2007. SoftCOM 2007. 15th International Conference on}, citeulike-article-id = {2340736}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/SOFTCOM.2007.4446129}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4446129}, doi = {10.1109/SOFTCOM.2007.4446129}, journal = {Software, Telecommunications and Computer Networks, 2007. SoftCOM 2007. 15th International Conference on}, keywords = {behaviors-detection, decision-making, legacy-application, network, networking, qos}, pages = {1--6}, posted-at = {2008-02-06 11:46:32}, priority = {5}, title = {Automatic flow classification using machine learning}, url = {http://dx.doi.org/10.1109/SOFTCOM.2007.4446129}, year = {2007} }

TY - CONF ID - citeulike:2340736 L3 - citeulike-article-id:2340736 N2 - Network standards are moving toward the Quality-of-Service (QoS) networking. Differentiated Services (DiffServ) QoS model is adopted by many recent and upcoming networks standard. Applications running on these networks can specify suitable service classes to their connections or flows. The flows are then treated according to their service classes. However, current Internet applications are still designed based on besteffort scheme and, therefore, cannot benefit from QoS support from the network. An automatic flow classification framework, which can automatically classify non QoS-aware flows or legacy flows, has been proposed in our earlier work [2]. In this paper, we extend our framework by introducing new features that can be effectively used to classify legacy flows. The simplicity of these features allows the data to be collected in real-time. No packetlevel data are required. Furthermore, the framework is evaluated using multiple data sets from different users. The results show that our framework works extremely well in general and it can be operated independently from any applications, networks or even machine learning algorithms. Average correctness up to 98.82% is achieved when the framework is used to learn and classify unseen flows from the same user. Cross-user classifications yield average correctness up to 74.15%. JF - Software, Telecommunications and Computer Networks, 2007. SoftCOM 2007. 15th International Conference on EP - 6 TI - Automatic flow classification using machine learning T2 - Software, Telecommunications and Computer Networks, 2007. SoftCOM 2007. 15th International Conference on SP - 1 KW - behaviors-detection KW - decision-making KW - legacy-application KW - network KW - networking KW - qos AU - Anantavrasilp, Isara AU - Scholer, Thorsten PY - 2007/// UR - http://dx.doi.org/10.1109/SOFTCOM.2007.4446129 ER -