A study of falling discrimination using sound information for watching elderly people

Recently, we have faced on the problem such as increasing elderly people who have occurred accidents including solitary death and falling and so on at their houses. To deal with these problems, many researchers and companies are proposing and releasing the systems monitored by sensors for keeping th...

Full description

Bibliographic Details
Main Authors: Masashi NAKAYAMA, Shunsuke ISHIMITSU, Ryota NAKANISHI, Shiho SAKANO, Takuya SORADA, Yuki MAEDA
Format: Article
Language:Japanese
Published: The Japan Society of Mechanical Engineers 2016-11-01
Series:Nihon Kikai Gakkai ronbunshu
Subjects:
Online Access:https://www.jstage.jst.go.jp/article/transjsme/82/844/82_16-00151/_pdf/-char/en
_version_ 1828188798604804096
author Masashi NAKAYAMA
Shunsuke ISHIMITSU
Ryota NAKANISHI
Shiho SAKANO
Takuya SORADA
Yuki MAEDA
author_facet Masashi NAKAYAMA
Shunsuke ISHIMITSU
Ryota NAKANISHI
Shiho SAKANO
Takuya SORADA
Yuki MAEDA
author_sort Masashi NAKAYAMA
collection DOAJ
description Recently, we have faced on the problem such as increasing elderly people who have occurred accidents including solitary death and falling and so on at their houses. To deal with these problems, many researchers and companies are proposing and releasing the systems monitored by sensors for keeping them safety. However, conventional systems using sensors including cameras and microphones give little privacy. In order to solve the problems, we proposed and discussed the falling discrimination using sound information for watching elderly people. Proposed system expects the falling discriminations using acoustic features extracted from sound. For discrimination accurately, we focused on Spectrum gravity between subjects/things and flooring styles. The feature characterized and modeled as Spectrum ratio of delta power as dynamic parameter. Finally, experiments of two-class discriminations using feature parameters achieved to 96.83 % with dataset of unspecific conditions.
first_indexed 2024-04-12T07:55:00Z
format Article
id doaj.art-ecb469c883fa449ba5a5b4386e1529d8
institution Directory Open Access Journal
issn 2187-9761
language Japanese
last_indexed 2024-04-12T07:55:00Z
publishDate 2016-11-01
publisher The Japan Society of Mechanical Engineers
record_format Article
series Nihon Kikai Gakkai ronbunshu
spelling doaj.art-ecb469c883fa449ba5a5b4386e1529d82022-12-22T03:41:30ZjpnThe Japan Society of Mechanical EngineersNihon Kikai Gakkai ronbunshu2187-97612016-11-018284416-0015116-0015110.1299/transjsme.16-00151transjsmeA study of falling discrimination using sound information for watching elderly peopleMasashi NAKAYAMA0Shunsuke ISHIMITSU1Ryota NAKANISHI2Shiho SAKANO3Takuya SORADA4Yuki MAEDA5Graduate School of Information Sciences, Hiroshima City UniversityGraduate School of Information Sciences, Hiroshima City UniversityFaculty of Information Sciences, Hiroshima City UniversityFaculty of Information Sciences, Hiroshima City UniversityK’s CorporationK’s CorporationRecently, we have faced on the problem such as increasing elderly people who have occurred accidents including solitary death and falling and so on at their houses. To deal with these problems, many researchers and companies are proposing and releasing the systems monitored by sensors for keeping them safety. However, conventional systems using sensors including cameras and microphones give little privacy. In order to solve the problems, we proposed and discussed the falling discrimination using sound information for watching elderly people. Proposed system expects the falling discriminations using acoustic features extracted from sound. For discrimination accurately, we focused on Spectrum gravity between subjects/things and flooring styles. The feature characterized and modeled as Spectrum ratio of delta power as dynamic parameter. Finally, experiments of two-class discriminations using feature parameters achieved to 96.83 % with dataset of unspecific conditions.https://www.jstage.jst.go.jp/article/transjsme/82/844/82_16-00151/_pdf/-char/enfalling discriminationsoundzero corssdelta powersvmk-nn
spellingShingle Masashi NAKAYAMA
Shunsuke ISHIMITSU
Ryota NAKANISHI
Shiho SAKANO
Takuya SORADA
Yuki MAEDA
A study of falling discrimination using sound information for watching elderly people
Nihon Kikai Gakkai ronbunshu
falling discrimination
sound
zero corss
delta power
svm
k-nn
title A study of falling discrimination using sound information for watching elderly people
title_full A study of falling discrimination using sound information for watching elderly people
title_fullStr A study of falling discrimination using sound information for watching elderly people
title_full_unstemmed A study of falling discrimination using sound information for watching elderly people
title_short A study of falling discrimination using sound information for watching elderly people
title_sort study of falling discrimination using sound information for watching elderly people
topic falling discrimination
sound
zero corss
delta power
svm
k-nn
url https://www.jstage.jst.go.jp/article/transjsme/82/844/82_16-00151/_pdf/-char/en
work_keys_str_mv AT masashinakayama astudyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT shunsukeishimitsu astudyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT ryotanakanishi astudyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT shihosakano astudyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT takuyasorada astudyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT yukimaeda astudyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT masashinakayama studyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT shunsukeishimitsu studyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT ryotanakanishi studyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT shihosakano studyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT takuyasorada studyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople
AT yukimaeda studyoffallingdiscriminationusingsoundinformationforwatchingelderlypeople