Presentation 2021-01-21
A Study of Learning Data Generation for a Sound-based Life Activity Estimation System Using Video Images
Kentaro Matsuda, Ken Tsutsuguchi, Manabu Okamoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The number of HIKIKOMORI has been increasing year by year, and the number of households that cannot make ends meet has been increasing, which has become a problem. This paper proposes a system to watch over such households. The system assumes the state of a HIKIKOMORI from the definition of a it, and uses a neural network to determine the state of life from sound information. Since sound data is difficult to label, we use LSTM to investigate whether it is possible to identify data using video data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) life log / life activity / neural network / video image analysis
Paper # ICM2020-36,LOIS2020-24
Date of Issue 2021-01-14 (ICM, LOIS)

Conference Information
Committee ICM / LOIS
Conference Date 2021/1/21(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Practical Use of Lifelog, Office Information System, Business Management, etc.
Chair Kazuhiko Kinoshita(Tokushima Univ.) / Toru Kobayashi(Nagasaki Univ.)
Vice Chair Yoichi Sato(OSL) / Haruo Ooishi(NTT) / Hiroyuki Toda(NTT)
Secretary Yoichi Sato(NTT) / Haruo Ooishi(Bosco) / Hiroyuki Toda(NTT)
Assistant Tetsuya Uchiumi(Fujitsu Lab.) / Shigeru Fujimura(NTT)

Paper Information
Registration To Technical Committee on Information and Communication Management / Technical Committee on Life Intelligence and Office Information Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study of Learning Data Generation for a Sound-based Life Activity Estimation System Using Video Images
Sub Title (in English)
Keyword(1) life log
Keyword(2) life activity
Keyword(3) neural network
Keyword(4) video image analysis
1st Author's Name Kentaro Matsuda
1st Author's Affiliation Sojo University(Sojo Univ)
2nd Author's Name Ken Tsutsuguchi
2nd Author's Affiliation Sojo University(Sojo Univ)
3rd Author's Name Manabu Okamoto
3rd Author's Affiliation Sojo University(Sojo Univ)
Date 2021-01-21
Paper # ICM2020-36,LOIS2020-24
Volume (vol) vol.120
Number (no) ICM-323,LOIS-324
Page pp.pp.10-14(ICM), pp.10-14(LOIS),
#Pages 5
Date of Issue 2021-01-14 (ICM, LOIS)