Presentation 2020-12-15
Application Identification Method with Meta-Learning
Shun Tobiyama, Bo Hu, Kazunori Kamiya, Kenji Takahashi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) With the continuous evolution of the Internet, a variety of web applications, such as video streaming, social network services, and web meeting services, are widely used, significantly increasing the amount of traffic. Classifying what types of network traffic in detail uses networks is important from the perspectives of resource management and threat analysis. Researchers has proposed methods for identifying applications from flow data using machine learning techniques. However, it is difficult to create a large amount of training data because a flow data does not contain information of application layer while existing machine learning techniques needs a large amount of training data. Thus, in this paper, we use a method called "Meta-Learning" which enables us to construct models with a small amount of data to solve this problem.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Traffic Identification / Network Flow / Meta-Learning
Paper # IN2020-40
Date of Issue 2020-12-07 (IN)

Conference Information
Committee IA / IN
Conference Date 2020/12/14(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Performance Analysis and Simulation, Robustness, Traffic and Throughput Measurement, Quality of Service (QoS) Control, Congestion Control, Overlay Network/P2P, IPv6, Multicast, Routing, DDoS, etc.
Chair Hiroyuki Osaki(Kwansei Gakuin Univ.) / Kenji Ishida(Hiroshima City Univ.)
Vice Chair Rei Atarashi(IIJ) / Toru Kondo(Hiroshima Univ.) / Hiroshi Yamamoto(Ritsumeikan Univ.) / Kunio Hato(Internet Multifeed)
Secretary Rei Atarashi(Kwansei Gakuin Univ.) / Toru Kondo(KDDI Research) / Hiroshi Yamamoto(NEC) / Kunio Hato(Hiroshima City Univ.)
Assistant Kenji Ohira(Osaka Univ.) / Daiki Nobayashi(Kyushu Inst. of Tech.) / Ryohei Banno(Kogakuin Univ.)

Paper Information
Registration To Technical Committee on Internet Architecture / Technical Committee on Information Networks
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Application Identification Method with Meta-Learning
Sub Title (in English)
Keyword(1) Traffic Identification
Keyword(2) Network Flow
Keyword(3) Meta-Learning
1st Author's Name Shun Tobiyama
1st Author's Affiliation Nippon Telegraph and Telephone Corporation(NTT)
2nd Author's Name Bo Hu
2nd Author's Affiliation Nippon Telegraph and Telephone Corporation(NTT)
3rd Author's Name Kazunori Kamiya
3rd Author's Affiliation Nippon Telegraph and Telephone Corporation(NTT)
4th Author's Name Kenji Takahashi
4th Author's Affiliation NTT Limited(NTT Ltd.)
Date 2020-12-15
Paper # IN2020-40
Volume (vol) vol.120
Number (no) IN-293
Page pp.pp.43-48(IN),
#Pages 6
Date of Issue 2020-12-07 (IN)