A modular two-layer system for accurate and fast traffic classification

Fateme Hajikarami, Mehdi Berenjkoub, Mohammad Hossein Manshaei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

Traffic classification is the basic block of many network management and control operations such as allocating appropriate levels of quality of service to different applications, filtering and intrusion detection. Due to importance of accurately classifying large networks traffic, we have proposed a lightweight two-layer system, which is perfect for today's high-speed links. Considering the trade-off among accuracy and speed, our system is based on a modular architecture and combination of some expert's opinions. Moreover we extract the best features for each application group in order to achieve an accurate system. Experimental results indicates that our proposed system has accuracy comparable to more sophisticated system and its learning cost is 10 times less than these systems. In addition we can customize our proposed system according to the needs and goals of network administrator. Our system is robust and adaptable to network changes such as the appearance of new applications. In such a case, our system labels new flow as 'unknown' instead of misclassifying. So the administrator will notice and take necessary actions to improve the classification system.

Original languageEnglish (US)
Title of host publication2014 11th International ISC Conference on Information Security and Cryptology, ISCISC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages149-154
Number of pages6
ISBN (Electronic)9781479953837
DOIs
StatePublished - Dec 18 2014
Externally publishedYes
Event2014 11th International ISC Conference on Information Security and Cryptology, ISCISC 2014 - Tehran, Iran, Islamic Republic of
Duration: Sep 3 2014Sep 4 2014

Publication series

Name2014 11th International ISC Conference on Information Security and Cryptology, ISCISC 2014

Conference

Conference2014 11th International ISC Conference on Information Security and Cryptology, ISCISC 2014
Country/TerritoryIran, Islamic Republic of
CityTehran
Period9/3/149/4/14

Keywords

  • Combining methods
  • Machine learning
  • Modular architectur
  • Statistical features
  • Traffic classification

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Fingerprint

Dive into the research topics of 'A modular two-layer system for accurate and fast traffic classification'. Together they form a unique fingerprint.

Cite this