<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Luigi Grimaudo</style></author><author><style face="normal" font="default" size="100%">Marco Mellia</style></author><author><style face="normal" font="default" size="100%">Elena Baralis</style></author><author><style face="normal" font="default" size="100%">Ram Keralapura</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">SeLeCT: Self-Learning Classifier for Internet Traffic</style></title><secondary-title><style face="normal" font="default" size="100%">IEEE Transactions on Network and Service Management</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">clustering</style></keyword><keyword><style  face="normal" font="default" size="100%">self-seeding</style></keyword><keyword><style  face="normal" font="default" size="100%">Traffic Classification</style></keyword><keyword><style  face="normal" font="default" size="100%">unsupervised machine learning</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2014</style></year><pub-dates><date><style  face="normal" font="default" size="100%">06/2014</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">11</style></volume><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Network visibility is a critical part of traffic engineering, network management, and security. The most popular&amp;nbsp;current solutions - Deep Packet Inspection (DPI) and statistical&amp;nbsp;classification, deeply rely on the availability of a training set.&amp;nbsp;Besides the cumbersome need to regularly update the signatures,&amp;nbsp;their visibility is limited to classes the classifier has been trained&amp;nbsp;for. Unsupervised algorithms have been envisioned as a viable&amp;nbsp;alternative to automatically identify classes of traffic. However,&amp;nbsp;the accuracy achieved so far does not allow to use them for traffic&amp;nbsp;classification in practical scenario.&lt;/p&gt;&lt;p&gt;To address the above issues, we propose SeLeCT, a Self-Learning Classifier for Internet Traffic. It uses unsupervised algorithms along with an adaptive seeding approach to automatically&amp;nbsp;let classes of traffic emerge, being identified and labeled. Unlike&amp;nbsp;traditional classifiers, it requires neither a-priori knowledge of&amp;nbsp;signatures nor a training set to extract the signatures. Instead,&amp;nbsp;SeLeCT automatically groups flows into pure (or homogeneous)&amp;nbsp;clusters using simple statistical features. SeLeCT simplifies label&amp;nbsp;assignment (which is still based on some manual intervention) so&amp;nbsp;that proper class labels can be easily discovered. Furthermore,&amp;nbsp;SeLeCT uses an iterative seeding approach to boost its ability to&amp;nbsp;cope with new protocols and applications.&lt;/p&gt;&lt;p&gt;We evaluate the performance of SeLeCT using traffic traces&amp;nbsp;collected in different years from various ISPs located in 3&amp;nbsp;different continents. Our experiments show that SeLeCT achieves&amp;nbsp;excellent precision and recall, with overall accuracy close to 98%.&amp;nbsp;Unlike state-of-art classifiers, the biggest advantage of SeLeCT&amp;nbsp;is its ability to discover new protocols and applications in an&amp;nbsp;almost automated fashion.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">2</style></issue><section><style face="normal" font="default" size="100%">144</style></section></record></records></xml>