System Design for Emergency Alert Triggered by Falls Using Convolutional Neural Networks

Carla Taramasco, Yoslandy Lazo, Tomás Rodenas, Paola Fuentes, Felipe Martínez, Jacques Demongeot

Resultado de la investigación: Article

Resumen

The world population ageing is on the rise, which has led to an increase in the demand for medical care due to diseases and symptoms prevalent in health centers. One of the most prevalent symptoms prevalent in older adults is falls, which affect one-third of patients each year and often result in serious injuries that can lead to death. This paper describes the design of a fall detection system for elderly households living alone using very low resolution thermal sensor arrays. The algorithms implemented were LSTM, GRU, and Bi-LSTM; the last one mentioned being that which obtained the best results at 93% in accuracy. The results obtained aim to be a valuable tool for accident prevention for those patients that use it and for clinicians who manage the data.

Idioma originalEnglish
Número de artículo50
PublicaciónJournal of Medical Systems
Volumen44
N.º2
DOI
EstadoPublished - 1 feb 2020

Huella dactilar

Sensor arrays
Health care
Emergencies
Aging of materials
Systems analysis
Health
Accident Prevention
Neural networks
Hot Temperature
Wounds and Injuries
Population

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Information Systems
  • Health Informatics
  • Health Information Management

Citar esto

Taramasco, Carla ; Lazo, Yoslandy ; Rodenas, Tomás ; Fuentes, Paola ; Martínez, Felipe ; Demongeot, Jacques. / System Design for Emergency Alert Triggered by Falls Using Convolutional Neural Networks. En: Journal of Medical Systems. 2020 ; Vol. 44, N.º 2.
@article{8d515b941a514a9b8cd78410f96edd37,
title = "System Design for Emergency Alert Triggered by Falls Using Convolutional Neural Networks",
abstract = "The world population ageing is on the rise, which has led to an increase in the demand for medical care due to diseases and symptoms prevalent in health centers. One of the most prevalent symptoms prevalent in older adults is falls, which affect one-third of patients each year and often result in serious injuries that can lead to death. This paper describes the design of a fall detection system for elderly households living alone using very low resolution thermal sensor arrays. The algorithms implemented were LSTM, GRU, and Bi-LSTM; the last one mentioned being that which obtained the best results at 93{\%} in accuracy. The results obtained aim to be a valuable tool for accident prevention for those patients that use it and for clinicians who manage the data.",
keywords = "Bi-LSTM, Elderly surveillance, Emergency monitoring, Fall detection, GRU, LSTM",
author = "Carla Taramasco and Yoslandy Lazo and Tom{\'a}s Rodenas and Paola Fuentes and Felipe Mart{\'i}nez and Jacques Demongeot",
year = "2020",
month = "2",
day = "1",
doi = "10.1007/s10916-019-1484-1",
language = "English",
volume = "44",
journal = "Journal of Medical Systems",
issn = "0148-5598",
publisher = "Springer New York",
number = "2",

}

System Design for Emergency Alert Triggered by Falls Using Convolutional Neural Networks. / Taramasco, Carla; Lazo, Yoslandy; Rodenas, Tomás; Fuentes, Paola; Martínez, Felipe; Demongeot, Jacques.

En: Journal of Medical Systems, Vol. 44, N.º 2, 50, 01.02.2020.

Resultado de la investigación: Article

TY - JOUR

T1 - System Design for Emergency Alert Triggered by Falls Using Convolutional Neural Networks

AU - Taramasco, Carla

AU - Lazo, Yoslandy

AU - Rodenas, Tomás

AU - Fuentes, Paola

AU - Martínez, Felipe

AU - Demongeot, Jacques

PY - 2020/2/1

Y1 - 2020/2/1

N2 - The world population ageing is on the rise, which has led to an increase in the demand for medical care due to diseases and symptoms prevalent in health centers. One of the most prevalent symptoms prevalent in older adults is falls, which affect one-third of patients each year and often result in serious injuries that can lead to death. This paper describes the design of a fall detection system for elderly households living alone using very low resolution thermal sensor arrays. The algorithms implemented were LSTM, GRU, and Bi-LSTM; the last one mentioned being that which obtained the best results at 93% in accuracy. The results obtained aim to be a valuable tool for accident prevention for those patients that use it and for clinicians who manage the data.

AB - The world population ageing is on the rise, which has led to an increase in the demand for medical care due to diseases and symptoms prevalent in health centers. One of the most prevalent symptoms prevalent in older adults is falls, which affect one-third of patients each year and often result in serious injuries that can lead to death. This paper describes the design of a fall detection system for elderly households living alone using very low resolution thermal sensor arrays. The algorithms implemented were LSTM, GRU, and Bi-LSTM; the last one mentioned being that which obtained the best results at 93% in accuracy. The results obtained aim to be a valuable tool for accident prevention for those patients that use it and for clinicians who manage the data.

KW - Bi-LSTM

KW - Elderly surveillance

KW - Emergency monitoring

KW - Fall detection

KW - GRU

KW - LSTM

UR - http://www.scopus.com/inward/record.url?scp=85077617956&partnerID=8YFLogxK

U2 - 10.1007/s10916-019-1484-1

DO - 10.1007/s10916-019-1484-1

M3 - Article

C2 - 31907688

AN - SCOPUS:85077617956

VL - 44

JO - Journal of Medical Systems

JF - Journal of Medical Systems

SN - 0148-5598

IS - 2

M1 - 50

ER -