[논문]Network traffic classification based on transfer learning

Sun, Guanglu; Liang, Lili; Chen, Teng; Xiao, Feng; Lang, Fei

doi:10.1016/j.compeleceng.2018.03.005

Network traffic classification based on transfer learning

Computers & electrical engineering, v.69, 2018년, pp.920 - 927

Sun, Guanglu (School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, 150080, China) , Liang, Lili (School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, 150080, China) , Chen, Teng (School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, 150080, China) , Xiao, Feng (School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, 150080, China) , Lang, Fei (Research Center of Information Security & Intelligent Technology, Harbin University of Science and Technology, Harbin, 150080, China)

Abstract ▼ AI-Helper

Abstract Machine learning models used in traffic classification make the assumption that the training data and test data have independent identical distributions. However, this assumption might be violated in practical traffic classification due to changes of traffic features. The models trained by existing data will be ineffective in classifying new traffic. A transfer learning model without making the above assumption is proposed in the present study. The maximum entropy model (Maxent) was adopted as the base classifier in the transfer learning model. To examine the efficacy of the proposed method, the traffic dataset collected at the University of Cambridge was used in the condition that the training and test dataset were not identical. Experimental results showed that good classification performance was obtained based on the transfer learning model.

주제어

참고문헌 (28)

Kim 11 2008 Proceedings of the 2008 ACM CoNEXT conference Internet traffic classification demystified: myths, caveats, and the best practices
IEEE Commun Surv Tutorials Nguyen 10 4 56 2008 10.1109/SURV.2008.080406 A survey of techniques for internet traffic classification using machine learning

상세보기
IEEE Trans Parallel Distrib Syst Zhang 24 1 104 2013 10.1109/TPDS.2012.98 Network traffic classification using correlation information

상세보기
IEEE Trans Knowl Data Eng Pan 22 10 1345 2010 10.1109/TKDE.2009.191 A survey on transfer learning

상세보기
Raina 713 2006 Proceedings of the 23rd international conference on machine learning Constructing informative priors using transfer learning
Dai 193 2007 Proceedings of the 24th international conference on machine learning Boosting for transfer learning [C]
IEEE Netw Dainotti 26 1 35 2012 10.1109/MNET.2012.6135854 Issues and future directions in traffic classification

상세보기
Moore 50 2005 Internet traffic classification using Bayesian analysis techniques
ACM SIGCOMM Comput Commun Rev Williams 36 5 5 2006 10.1145/1163593.1163596 A preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification

상세보기
Comput. Netw Este 53 14 2476 2009 10.1016/j.comnet.2009.05.003 Support vector machines for TCP traffic classification

상세보기
IEEE/ACM Trans Netw Finamore 18 5 1505 2010 10.1109/TNET.2010.2044046 KISS: stochastic packet inspection classifier for UDP traffic

상세보기
IEEE/ACM Trans Netw Nguyen 20 6 1880 2012 10.1109/TNET.2012.2187305 Timely and continuous machine-learning-based classification for interactive IP traffic

상세보기
Soft Comput Ye 18 9 1815 2014 10.1007/s00500-014-1253-5 Hybrid P2P traffic classification with heuristic rules and machine learning

상세보기
Neurocomputing Li 152 322 2015 10.1016/j.neucom.2014.10.061 Network traffic classification via non-convex multi-task feature learning

상세보기
Neurocomputing Peng 156 252 2015 10.1016/j.neucom.2014.12.053 Effective packet number for early stage internet traffic identification

상세보기
McGregor 205 2004 International workshop on passive and active network measurement Flow clustering using machine learning techniques
Erman 281 2006 Proceedings of the 2006 SIGCOMM workshop on mining network data Traffic classification using clustering algorithms
Comput Networks Keralapura 54 7 1055 2010 10.1016/j.comnet.2009.10.009 A novel self-learning architecture for p2p traffic classification in high speed networks

상세보기
J Comput Syst Sci Zhang 79 5 573 2013 10.1016/j.jcss.2012.11.004 Unsupervised traffic classification using flow statistical properties and IP packet payload

상세보기
IEEE Trans Parallel Distrib Syst Wang 25 11 2932 2014 10.1109/TPDS.2013.307 Internet traffic classification using constrained clustering

상세보기
Erman 35 369 2007 Semi-supervised network traffic classification
Casas 87 2011 Proceedings of the 23rd international teletraffic congress MINETRAC: mining flows for unsupervised analysis & semi-supervised classification
IEEE Trans Netw Serv Manage Zhang 10 2 133 2013 10.1109/TNSM.2013.022713.120250 An effective network traffic classification method with unknown flow detection

상세보기
Knowledge-Based Syst Lu 80 14 2015 10.1016/j.knosys.2015.01.010 Transfer learning using computational intelligence: a survey

상세보기
IEEE Trans Image Process Yang 24 12 4701 2015 10.1109/TIP.2015.2465157 Robust and non-negative collective matrix factorization for text-to-image transfer learning

상세보기
J Comput Syst Sci Freund 55 1 119 1997 10.1006/jcss.1997.1504 A decision-theoretic generalization of on-line learning and an application to boosting

상세보기
Appl Math Comput Liu 243 767 2014 10.1016/j.amc.2014.06.016 Numeric characteristics of generalized M-set with its asymptote

상세보기
Entropy Liu 19 6 269 2017 10.3390/e19060269 A novel distance metric: generalized relative entropy

상세보기

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

Network traffic classification based on transfer learning

Abstract ▼ AI-Helper

주제어

참고문헌 (28)

이 논문을 인용한 문헌

관련 콘텐츠

연관된 기능

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트