Edge Computing Transformers for Fall Detection in Older Adults

The global trend of increasing life expectancy introduces new challenges with far-reaching implications. Among these, the risk of falls among older adults is particularly significant, affecting individual health and quality of life, and placing an additional burden on healthcare systems. Existing fa...

Descripción completa

Detalles Bibliográficos
Autores: Fernández-Bermejo Ruiz, Jesús, Martínez del Rincón, Jesús, Dorado Chaparro, Javier, Toro García, Xavier del, Santofimia Romero, María José, López López, Juan Carlos
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universidad de Castilla-La Mancha
Repositorio:RUIdeRA. Repositorio Institucional de la UCLM
OAI Identifier:oai:dnet:ruidera_____::a48af3481101465338d56129d71f69d2
Acceso en línea:https://doi.org/10.1142/S0129065724500266
https://hdl.handle.net/10578/48282
Access Level:acceso abierto
Palabra clave:Deep Learning
Fall detection
Inertial Measurement Unit
Older adults
Transformer Neural Network
id ES_10230c7ce7cfd668d61173ff84c8d89c
oai_identifier_str oai:dnet:ruidera_____::a48af3481101465338d56129d71f69d2
network_acronym_str ES
network_name_str España
repository_id_str
spelling Edge Computing Transformers for Fall Detection in Older AdultsFernández-Bermejo Ruiz, JesúsMartínez del Rincón, JesúsDorado Chaparro, JavierToro García, Xavier delSantofimia Romero, María JoséLópez López, Juan CarlosDeep LearningFall detectionInertial Measurement UnitOlder adultsTransformer Neural NetworkThe global trend of increasing life expectancy introduces new challenges with far-reaching implications. Among these, the risk of falls among older adults is particularly significant, affecting individual health and quality of life, and placing an additional burden on healthcare systems. Existing fall detection systems often have limitations, including delays due to continuous server communication, high false-positive rates, low adoption rates due to wearability and comfort issues, and high costs. In response to these challenges, this work presents a reliable, wearable, and cost-effective fall detection system. The proposed system consists of a fit-for-purpose device, with an embedded algorithm and an Inertial Measurement Unit (IMU), enabling real-time fall detection. The algorithm combines a Threshold Based Algorithm (TBA) and a neural network with low number of parameters based on a transformer architecture. This system demonstrates notable performance with 95.29% accuracy, 93.68% specificity and 96.66% sensitivity, while only using a 0.38% of the trainable parameters used by the next approach.World Scientific Publishing Company202620262024info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://doi.org/10.1142/S0129065724500266https://hdl.handle.net/10578/48282reponame:RUIdeRA. Repositorio Institucional de la UCLMinstname:Universidad de Castilla-La ManchaEspañolinfo:eu-repo/semantics/openAccessoai:dnet:ruidera_____::a48af3481101465338d56129d71f69d22026-05-27T07:36:41Z
dc.title.none.fl_str_mv Edge Computing Transformers for Fall Detection in Older Adults
title Edge Computing Transformers for Fall Detection in Older Adults
spellingShingle Edge Computing Transformers for Fall Detection in Older Adults
Fernández-Bermejo Ruiz, Jesús
Deep Learning
Fall detection
Inertial Measurement Unit
Older adults
Transformer Neural Network
title_short Edge Computing Transformers for Fall Detection in Older Adults
title_full Edge Computing Transformers for Fall Detection in Older Adults
title_fullStr Edge Computing Transformers for Fall Detection in Older Adults
title_full_unstemmed Edge Computing Transformers for Fall Detection in Older Adults
title_sort Edge Computing Transformers for Fall Detection in Older Adults
dc.creator.none.fl_str_mv Fernández-Bermejo Ruiz, Jesús
Martínez del Rincón, Jesús
Dorado Chaparro, Javier
Toro García, Xavier del
Santofimia Romero, María José
López López, Juan Carlos
author Fernández-Bermejo Ruiz, Jesús
author_facet Fernández-Bermejo Ruiz, Jesús
Martínez del Rincón, Jesús
Dorado Chaparro, Javier
Toro García, Xavier del
Santofimia Romero, María José
López López, Juan Carlos
author_role author
author2 Martínez del Rincón, Jesús
Dorado Chaparro, Javier
Toro García, Xavier del
Santofimia Romero, María José
López López, Juan Carlos
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Deep Learning
Fall detection
Inertial Measurement Unit
Older adults
Transformer Neural Network
topic Deep Learning
Fall detection
Inertial Measurement Unit
Older adults
Transformer Neural Network
description The global trend of increasing life expectancy introduces new challenges with far-reaching implications. Among these, the risk of falls among older adults is particularly significant, affecting individual health and quality of life, and placing an additional burden on healthcare systems. Existing fall detection systems often have limitations, including delays due to continuous server communication, high false-positive rates, low adoption rates due to wearability and comfort issues, and high costs. In response to these challenges, this work presents a reliable, wearable, and cost-effective fall detection system. The proposed system consists of a fit-for-purpose device, with an embedded algorithm and an Inertial Measurement Unit (IMU), enabling real-time fall detection. The algorithm combines a Threshold Based Algorithm (TBA) and a neural network with low number of parameters based on a transformer architecture. This system demonstrates notable performance with 95.29% accuracy, 93.68% specificity and 96.66% sensitivity, while only using a 0.38% of the trainable parameters used by the next approach.
publishDate 2024
dc.date.none.fl_str_mv 2024
2026
2026
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://doi.org/10.1142/S0129065724500266
https://hdl.handle.net/10578/48282
url https://doi.org/10.1142/S0129065724500266
https://hdl.handle.net/10578/48282
dc.language.none.fl_str_mv Español
language_invalid_str_mv Español
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv World Scientific Publishing Company
publisher.none.fl_str_mv World Scientific Publishing Company
dc.source.none.fl_str_mv reponame:RUIdeRA. Repositorio Institucional de la UCLM
instname:Universidad de Castilla-La Mancha
instname_str Universidad de Castilla-La Mancha
reponame_str RUIdeRA. Repositorio Institucional de la UCLM
collection RUIdeRA. Repositorio Institucional de la UCLM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403492984029184
score 15,81155

Similares en LA Referencia