Presentation 2015-04-22
Multi-flow-based Traffic Analysis for Behavior Identification
Yusuke Iemura, Yuichi Kumano, Nobuyuki Nakamura, Shingo Ata, Ikuo Oka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, application identification methods are attracted as an important role for network management which enables application-oriented traffic control. However, current methods of application identification mostly focus on individual flow (i.e., individual TCP connection), while many applications generate a large number of flows simulteneously to improve end users' experience. In such case, application identification for a single flow does not contribute to improve QoE (Quality of Experience) to end users in whole. In this paper, we propose a method to analyze network traffic from the perspective of end user's behavior, rather than application. Here we record a history of behavior for an end user and packets generated by his/her terminal, and then we associate a behavior with statistics of monitored traffic. Through numerical results, we show that typical user behaviors can be classified by a set of traffic characteristics.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Behavior / Application identification / Traffic analysis / Flow statistics / User experience
Paper # CQ2015-10
Date of Issue 2015-04-14 (CQ)

Conference Information
Committee CQ / CS
Conference Date 2015/4/21(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Fukuoka Institute of Technology
Topics (in Japanese) (See Japanese page)
Topics (in English) Application for 5G, Programmability of Network, SDN (Software-Defined Networking), NFV(Network Functions. Virtualization),Cloud, Network Virtualization, Service Quality, Contents Delivery, etc
Chair Akira Takahashi(NTT) / Toshinori Tsuboi(Tokyo Univ. of Tech.)
Vice Chair Eizaburo Itakura(Sony) / Kyoko Yamori(Asahi Univ.) / Tetsuya Yokotani(Mitsubishi Electric)
Secretary Eizaburo Itakura(Nippon Inst. of Tech.) / Kyoko Yamori(NEC) / Tetsuya Yokotani(NTT)
Assistant Masahiro Yamamoto(OKI) / Bo GU(Waseda Univ.)

Paper Information
Registration To Technical Committee on Communication Quality / Technical Committee on Communication Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Multi-flow-based Traffic Analysis for Behavior Identification
Sub Title (in English)
Keyword(1) Behavior
Keyword(2) Application identification
Keyword(3) Traffic analysis
Keyword(4) Flow statistics
Keyword(5) User experience
1st Author's Name Yusuke Iemura
1st Author's Affiliation Osaka City University(Osaka City Univ)
2nd Author's Name Yuichi Kumano
2nd Author's Affiliation Osaka City University(Osaka City Univ)
3rd Author's Name Nobuyuki Nakamura
3rd Author's Affiliation Oki Electric Industry(OKI)
4th Author's Name Shingo Ata
4th Author's Affiliation Osaka City University(Osaka City Univ)
5th Author's Name Ikuo Oka
5th Author's Affiliation Osaka City University(Osaka City Univ)
Date 2015-04-22
Paper # CQ2015-10
Volume (vol) vol.115
Number (no) CQ-11
Page pp.pp.51-56(CQ),
#Pages 6
Date of Issue 2015-04-14 (CQ)