A real-time falls detection system for elderly

Shumei Zhang, Hongjuan Li, PJ McCullagh, CD Nugent, Huiru Zheng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

A real-time fall detection system is proposed to distinguish various falls during daily activities. Falls are detected in two steps: first a hierarchical algorithm is used to classify the motion and motionless postures such as lying, sit-tilted, sit-upright, standing and walking; it then analyzes whether the current lying or sit-tilted postures are normal or abnormal, based on posture transition and users' current position. If an abnormal lying or sit-tilted posture is determined, a fall alert will be delivered immediately; if a possible fall is raised (such as normal lying but on the ground), then a music based alert starts playing, and a fall or normal lying will be determined according to whether the user stops the alert music. The advantages of the approach are that it can distinguish various falls efficiently (in real-time within a smart phone), and can also significantly improve the “true positives” for the slow falls with a sit-tilted posture, as well as the “true negatives” for the normal lying compared to the existed fall detection algorithms.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages51-56
Number of pages6
DOIs
Publication statusPublished - 17 Sep 2013
EventComputer Science and Electronic Engineering Conference (CEEC), 2013 5th - Colchester
Duration: 17 Sep 2013 → …

Conference

ConferenceComputer Science and Electronic Engineering Conference (CEEC), 2013 5th
Period17/09/13 → …

Cite this

Zhang, Shumei ; Li, Hongjuan ; McCullagh, PJ ; Nugent, CD ; Zheng, Huiru. / A real-time falls detection system for elderly. Unknown Host Publication. 2013. pp. 51-56
@inproceedings{a9c1813c5803441da6892f18ba467771,
title = "A real-time falls detection system for elderly",
abstract = "A real-time fall detection system is proposed to distinguish various falls during daily activities. Falls are detected in two steps: first a hierarchical algorithm is used to classify the motion and motionless postures such as lying, sit-tilted, sit-upright, standing and walking; it then analyzes whether the current lying or sit-tilted postures are normal or abnormal, based on posture transition and users' current position. If an abnormal lying or sit-tilted posture is determined, a fall alert will be delivered immediately; if a possible fall is raised (such as normal lying but on the ground), then a music based alert starts playing, and a fall or normal lying will be determined according to whether the user stops the alert music. The advantages of the approach are that it can distinguish various falls efficiently (in real-time within a smart phone), and can also significantly improve the “true positives” for the slow falls with a sit-tilted posture, as well as the “true negatives” for the normal lying compared to the existed fall detection algorithms.",
author = "Shumei Zhang and Hongjuan Li and PJ McCullagh and CD Nugent and Huiru Zheng",
year = "2013",
month = "9",
day = "17",
doi = "10.1109/CEEC.2013.6659444",
language = "English",
pages = "51--56",
booktitle = "Unknown Host Publication",

}

Zhang, S, Li, H, McCullagh, PJ, Nugent, CD & Zheng, H 2013, A real-time falls detection system for elderly. in Unknown Host Publication. pp. 51-56, Computer Science and Electronic Engineering Conference (CEEC), 2013 5th, 17/09/13. https://doi.org/10.1109/CEEC.2013.6659444

A real-time falls detection system for elderly. / Zhang, Shumei; Li, Hongjuan; McCullagh, PJ; Nugent, CD; Zheng, Huiru.

Unknown Host Publication. 2013. p. 51-56.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A real-time falls detection system for elderly

AU - Zhang, Shumei

AU - Li, Hongjuan

AU - McCullagh, PJ

AU - Nugent, CD

AU - Zheng, Huiru

PY - 2013/9/17

Y1 - 2013/9/17

N2 - A real-time fall detection system is proposed to distinguish various falls during daily activities. Falls are detected in two steps: first a hierarchical algorithm is used to classify the motion and motionless postures such as lying, sit-tilted, sit-upright, standing and walking; it then analyzes whether the current lying or sit-tilted postures are normal or abnormal, based on posture transition and users' current position. If an abnormal lying or sit-tilted posture is determined, a fall alert will be delivered immediately; if a possible fall is raised (such as normal lying but on the ground), then a music based alert starts playing, and a fall or normal lying will be determined according to whether the user stops the alert music. The advantages of the approach are that it can distinguish various falls efficiently (in real-time within a smart phone), and can also significantly improve the “true positives” for the slow falls with a sit-tilted posture, as well as the “true negatives” for the normal lying compared to the existed fall detection algorithms.

AB - A real-time fall detection system is proposed to distinguish various falls during daily activities. Falls are detected in two steps: first a hierarchical algorithm is used to classify the motion and motionless postures such as lying, sit-tilted, sit-upright, standing and walking; it then analyzes whether the current lying or sit-tilted postures are normal or abnormal, based on posture transition and users' current position. If an abnormal lying or sit-tilted posture is determined, a fall alert will be delivered immediately; if a possible fall is raised (such as normal lying but on the ground), then a music based alert starts playing, and a fall or normal lying will be determined according to whether the user stops the alert music. The advantages of the approach are that it can distinguish various falls efficiently (in real-time within a smart phone), and can also significantly improve the “true positives” for the slow falls with a sit-tilted posture, as well as the “true negatives” for the normal lying compared to the existed fall detection algorithms.

U2 - 10.1109/CEEC.2013.6659444

DO - 10.1109/CEEC.2013.6659444

M3 - Conference contribution

SP - 51

EP - 56

BT - Unknown Host Publication

ER -