Presentation 2019-12-20
A Study on Image Recognition Method by Edge Device Using Wireless Narrowband Telecommunications
Natsumi Tani, Haruhisa Hasegawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) LPWA is expected to achieve IoT system which has many edge devices with low cost. It is also an important issue how to apply image recognition function using deep neural network (DNN) into IoT system. Since LPWA has very low transmission speed, it is impossible to transmit image data to the cloud from edge devices. Therefore, the image recognition function should be implemented in the edge devices. However, the edge devices does not have enough capability for image recognition. As the result, there occurs the problem that those devices are not able to process the image in real-time. In this paper, we proposed the buffer management scheme to reduce the problem. We also evaluated the scheme and how the number of DNN layers affect the performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image Recognition / IoT / LPWA / Edge Computing / CNN
Paper # IN2019-61
Date of Issue 2019-12-12 (IN)

Conference Information
Committee IN / IA
Conference Date 2019/12/19(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Satellite Campus Hiroshima
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 Takuji Kishida(NTT-AT) / Hiroyuki Osaki(Kwansei Gakuin Univ.)
Vice Chair Kenji Ishida(Hiroshima City Univ.) / Rei Atarashi(IIJ) / Toru Kondo(Hiroshima Univ.) / Hiroshi Yamamoto(Ritsumeikan Univ.)
Secretary Kenji Ishida(NTT Communications) / Rei Atarashi(NTT) / Toru Kondo(Hiroshima City Univ.) / Hiroshi Yamamoto(KDDI Research)
Assistant / Kenji Ohira(Osaka Univ.) / Daiki Nobayashi(Kyushu Inst. of Tech.) / Ryohei Banno(Tokyo Inst. of Tech.)

Paper Information
Registration To Technical Committee on Information Networks / Technical Committee on Internet Architecture
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Image Recognition Method by Edge Device Using Wireless Narrowband Telecommunications
Sub Title (in English)
Keyword(1) Image Recognition
Keyword(2) IoT
Keyword(3) LPWA
Keyword(4) Edge Computing
Keyword(5) CNN
1st Author's Name Natsumi Tani
1st Author's Affiliation Japan Women's University(Japan Women's Univ.)
2nd Author's Name Haruhisa Hasegawa
2nd Author's Affiliation Japan Women's University(Japan Women's Univ.)
Date 2019-12-20
Paper # IN2019-61
Volume (vol) vol.119
Number (no) IN-342
Page pp.pp.93-98(IN),
#Pages 6
Date of Issue 2019-12-12 (IN)