Presentation 2018-06-10
A possible approach to detect a damaged position of wooden wall using neural-network classifier
Yoichiro Hashizume, Sakuya Kishi, Takashi Nakajima, Soichiro Okamura, Takahiro Yamamoto, Takayuki Kawahara, Mikio Hasegawa, Changhoon Choi, Takumi Ito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We investigated how to detect the state of the building with measuring the vibration data given by a piezoelectric sensor, and analyzing the obtained signal-informations using machine learning. Specifically, we investigated a method for finding the defection of bolts in a wooden wall. As a result, it became clear that the state of the wooden wall can be detected by the neural network classifier. Furthermore, we tested if the state detection can be performed by k-means clustering method, and we find the clustering method will useful under appropriate conditions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) IoT for Buildings / Neural Net Classifier / Wooden Wall / PVDF sensor / Vibration detector
Paper # NLP2018-40,CCS2018-13
Date of Issue 2018-06-01 (NLP, CCS)

Conference Information
Committee NLP / CCS
Conference Date 2018/6/8(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Kyoto Terrsa
Topics (in Japanese) (See Japanese page)
Topics (in English) Synchronization, Networks, etc
Chair Norikazu Takahashi(Okayama Univ.) / Mikio Hasegawa(Tokyo Univ. of Science)
Vice Chair Hiroaki Kurokawa(Tokyo University of Tech.) / Makoto Naruse(NICT) / Shigeki Shokawa(Kanagawa Inst. of Tech.)
Secretary Hiroaki Kurokawa(Hiroshima Inst. of Tech.) / Makoto Naruse(Nippon Institute of Tech.) / Shigeki Shokawa(Tokyo City Univ.)
Assistant Masayuki Kimura(Kyoto Univ.) / Yutaka Shimada(Saitama Univ.) / Yuusuke Kawakita(Kanagawa Inst. of Tech.) / Hiroyasu Ando(Univ. of Tsukuba) / Takashi Matsubara(Kobe Univ.) / Ryo Takahashi(AUT)

Paper Information
Registration To Technical Committee on Nonlinear Problems / Technical Committee on Complex Communication Sciences
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A possible approach to detect a damaged position of wooden wall using neural-network classifier
Sub Title (in English)
Keyword(1) IoT for Buildings
Keyword(2) Neural Net Classifier
Keyword(3) Wooden Wall
Keyword(4) PVDF sensor
Keyword(5) Vibration detector
1st Author's Name Yoichiro Hashizume
1st Author's Affiliation Tokyo University of Science(TUS)
2nd Author's Name Sakuya Kishi
2nd Author's Affiliation Tokyo University of Science(TUS)
3rd Author's Name Takashi Nakajima
3rd Author's Affiliation Tokyo University of Science(TUS)
4th Author's Name Soichiro Okamura
4th Author's Affiliation Tokyo University of Science(TUS)
5th Author's Name Takahiro Yamamoto
5th Author's Affiliation Tokyo University of Science(TUS)
6th Author's Name Takayuki Kawahara
6th Author's Affiliation Tokyo University of Science(TUS)
7th Author's Name Mikio Hasegawa
7th Author's Affiliation Tokyo University of Science(TUS)
8th Author's Name Changhoon Choi
8th Author's Affiliation Tokyo University of Science(TUS)
9th Author's Name Takumi Ito
9th Author's Affiliation Tokyo University of Science(TUS)
Date 2018-06-10
Paper # NLP2018-40,CCS2018-13
Volume (vol) vol.118
Number (no) NLP-75,CCS-76
Page pp.pp.69-73(NLP), pp.69-73(CCS),
#Pages 5
Date of Issue 2018-06-01 (NLP, CCS)