Fall detection algorithm using linear prediction model

One of the health issues in elderly people is the injury from the fall. Some of these injuries might lead to deaths. Thus, a good fall detection algorithm is needed to help reducing a rescuing time for a helper. In this paper, we develop a fall detection algorithm using the linear prediction model w...

Full description

Saved in:
Bibliographic Details
Main Authors: Nathasitsophon Y., Auephanwiriyakul S., Theera-Umpon N.
Format: Conference or Workshop Item
Language:English
Published: 2014
Online Access:http://www.scopus.com/inward/record.url?eid=2-s2.0-84881631183&partnerID=40&md5=fcb17be7eeae172bbc0aa63bd71631d3
http://cmuir.cmu.ac.th/handle/6653943832/1636
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
Language: English
id th-cmuir.6653943832-1636
record_format dspace
spelling th-cmuir.6653943832-16362014-08-29T09:29:33Z Fall detection algorithm using linear prediction model Nathasitsophon Y. Auephanwiriyakul S. Theera-Umpon N. One of the health issues in elderly people is the injury from the fall. Some of these injuries might lead to deaths. Thus, a good fall detection algorithm is needed to help reducing a rescuing time for a helper. In this paper, we develop a fall detection algorithm using the linear prediction model with a tri-axis accelerometer. We test the algorithm with the data set that have 11 activities (standing, walking, jumping, falling, running, lying, sitting, getting up (from lying to standing or from sitting to standing), going down (from standing to sitting), accelerating and decelerating) from 17 subjects. The result shows that we can detect all fall activities in both training and blind test data sets with precisions of 90.72% and 93.69%, respectively. The result also shows that we can detect 89.77% and 93.27% of other activities correctly. Although, there are some false alarms, the false alarm rate is small. © 2013 IEEE. 2014-08-29T09:29:33Z 2014-08-29T09:29:33Z 2013 Conference Paper 9781467351942 10.1109/ISIE.2013.6563711 98542 85PTA http://www.scopus.com/inward/record.url?eid=2-s2.0-84881631183&partnerID=40&md5=fcb17be7eeae172bbc0aa63bd71631d3 http://cmuir.cmu.ac.th/handle/6653943832/1636 English
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
language English
description One of the health issues in elderly people is the injury from the fall. Some of these injuries might lead to deaths. Thus, a good fall detection algorithm is needed to help reducing a rescuing time for a helper. In this paper, we develop a fall detection algorithm using the linear prediction model with a tri-axis accelerometer. We test the algorithm with the data set that have 11 activities (standing, walking, jumping, falling, running, lying, sitting, getting up (from lying to standing or from sitting to standing), going down (from standing to sitting), accelerating and decelerating) from 17 subjects. The result shows that we can detect all fall activities in both training and blind test data sets with precisions of 90.72% and 93.69%, respectively. The result also shows that we can detect 89.77% and 93.27% of other activities correctly. Although, there are some false alarms, the false alarm rate is small. © 2013 IEEE.
format Conference or Workshop Item
author Nathasitsophon Y.
Auephanwiriyakul S.
Theera-Umpon N.
spellingShingle Nathasitsophon Y.
Auephanwiriyakul S.
Theera-Umpon N.
Fall detection algorithm using linear prediction model
author_facet Nathasitsophon Y.
Auephanwiriyakul S.
Theera-Umpon N.
author_sort Nathasitsophon Y.
title Fall detection algorithm using linear prediction model
title_short Fall detection algorithm using linear prediction model
title_full Fall detection algorithm using linear prediction model
title_fullStr Fall detection algorithm using linear prediction model
title_full_unstemmed Fall detection algorithm using linear prediction model
title_sort fall detection algorithm using linear prediction model
publishDate 2014
url http://www.scopus.com/inward/record.url?eid=2-s2.0-84881631183&partnerID=40&md5=fcb17be7eeae172bbc0aa63bd71631d3
http://cmuir.cmu.ac.th/handle/6653943832/1636
_version_ 1681419707412905984