Presentation 2015-01-16
Life sound discrimination algorithm using Neural network
Hiroyuki Nishi, Kin Kin, Yoshimasa Kimura, Toshio Kakinoki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In an aging society, the death of elderly people living alone has become a serious social problem. Conventional observation services for elderly people have faults on privacy protection and user interface. Authors are studying observation systems using acoustic information for avoiding the problems of conventional systems. In this study, a new method for discriminating life sound of elderly people using neural network is proposed. As the parameters of the experiment, frame length of analysis, number of dimensions of the hidden layer and number of learning are evaluated. As the result, in case that frame length is 32 ms, number of dimensions are 15, and number of learning is 100, the discrimination accuracy was the best(96.4%).
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Elderly people / Observation / Life sound / Neural network / Pattern Recognition
Paper # ICM2014-43,LOIS2014-50
Date of Issue

Conference Information
Committee ICM
Conference Date 2015/1/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Information and Communication Management(ICM)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Life sound discrimination algorithm using Neural network
Sub Title (in English)
Keyword(1) Elderly people
Keyword(2) Observation
Keyword(3) Life sound
Keyword(4) Neural network
Keyword(5) Pattern Recognition
1st Author's Name Hiroyuki Nishi
1st Author's Affiliation Faculty of Information Sciences, Sojo University()
2nd Author's Name Kin Kin
2nd Author's Affiliation Faculty of Information Sciences, Sojo University
3rd Author's Name Yoshimasa Kimura
3rd Author's Affiliation Faculty of Information Sciences, Sojo University
4th Author's Name Toshio Kakinoki
4th Author's Affiliation Faculty of Information Sciences, Sojo University
Date 2015-01-16
Paper # ICM2014-43,LOIS2014-50
Volume (vol) vol.114
Number (no) 389
Page pp.pp.-
#Pages 5
Date of Issue