Cargando…

Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model

Activity monitoring combined with machine learning (ML) methods can contribute to detailed knowledge about daily physical behavior in older adults. The current study (1) evaluated the performance of an existing activity type recognition ML model (HARTH), based on data from healthy young adults, for...

Descripción completa

Detalles Bibliográficos
Autores principales: Ustad, Astrid, Logacjov, Aleksej, Trollebø, Stine Øverengen, Thingstad, Pernille, Vereijken, Beatrix, Bach, Kerstin, Maroni, Nina Skjæret
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006863/
https://www.ncbi.nlm.nih.gov/pubmed/36904574
http://dx.doi.org/10.3390/s23052368
_version_ 1784905376136691712
author Ustad, Astrid
Logacjov, Aleksej
Trollebø, Stine Øverengen
Thingstad, Pernille
Vereijken, Beatrix
Bach, Kerstin
Maroni, Nina Skjæret
author_facet Ustad, Astrid
Logacjov, Aleksej
Trollebø, Stine Øverengen
Thingstad, Pernille
Vereijken, Beatrix
Bach, Kerstin
Maroni, Nina Skjæret
author_sort Ustad, Astrid
collection PubMed
description Activity monitoring combined with machine learning (ML) methods can contribute to detailed knowledge about daily physical behavior in older adults. The current study (1) evaluated the performance of an existing activity type recognition ML model (HARTH), based on data from healthy young adults, for classifying daily physical behavior in fit-to-frail older adults, (2) compared the performance with a ML model (HAR70+) that included training data from older adults, and (3) evaluated the ML models on older adults with and without walking aids. Eighteen older adults aged 70–95 years who ranged widely in physical function, including usage of walking aids, were equipped with a chest-mounted camera and two accelerometers during a semi-structured free-living protocol. Labeled accelerometer data from video analysis was used as ground truth for the classification of walking, standing, sitting, and lying identified by the ML models. Overall accuracy was high for both the HARTH model (91%) and the HAR70+ model (94%). The performance was lower for those using walking aids in both models, however, the overall accuracy improved from 87% to 93% in the HAR70+ model. The validated HAR70+ model contributes to more accurate classification of daily physical behavior in older adults that is essential for future research.
format Online
Article
Text
id pubmed-10006863
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100068632023-03-12 Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model Ustad, Astrid Logacjov, Aleksej Trollebø, Stine Øverengen Thingstad, Pernille Vereijken, Beatrix Bach, Kerstin Maroni, Nina Skjæret Sensors (Basel) Article Activity monitoring combined with machine learning (ML) methods can contribute to detailed knowledge about daily physical behavior in older adults. The current study (1) evaluated the performance of an existing activity type recognition ML model (HARTH), based on data from healthy young adults, for classifying daily physical behavior in fit-to-frail older adults, (2) compared the performance with a ML model (HAR70+) that included training data from older adults, and (3) evaluated the ML models on older adults with and without walking aids. Eighteen older adults aged 70–95 years who ranged widely in physical function, including usage of walking aids, were equipped with a chest-mounted camera and two accelerometers during a semi-structured free-living protocol. Labeled accelerometer data from video analysis was used as ground truth for the classification of walking, standing, sitting, and lying identified by the ML models. Overall accuracy was high for both the HARTH model (91%) and the HAR70+ model (94%). The performance was lower for those using walking aids in both models, however, the overall accuracy improved from 87% to 93% in the HAR70+ model. The validated HAR70+ model contributes to more accurate classification of daily physical behavior in older adults that is essential for future research. MDPI 2023-02-21 /pmc/articles/PMC10006863/ /pubmed/36904574 http://dx.doi.org/10.3390/s23052368 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ustad, Astrid
Logacjov, Aleksej
Trollebø, Stine Øverengen
Thingstad, Pernille
Vereijken, Beatrix
Bach, Kerstin
Maroni, Nina Skjæret
Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model
title Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model
title_full Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model
title_fullStr Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model
title_full_unstemmed Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model
title_short Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model
title_sort validation of an activity type recognition model classifying daily physical behavior in older adults: the har70+ model
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006863/
https://www.ncbi.nlm.nih.gov/pubmed/36904574
http://dx.doi.org/10.3390/s23052368
work_keys_str_mv AT ustadastrid validationofanactivitytyperecognitionmodelclassifyingdailyphysicalbehaviorinolderadultsthehar70model
AT logacjovaleksej validationofanactivitytyperecognitionmodelclassifyingdailyphysicalbehaviorinolderadultsthehar70model
AT trollebøstineøverengen validationofanactivitytyperecognitionmodelclassifyingdailyphysicalbehaviorinolderadultsthehar70model
AT thingstadpernille validationofanactivitytyperecognitionmodelclassifyingdailyphysicalbehaviorinolderadultsthehar70model
AT vereijkenbeatrix validationofanactivitytyperecognitionmodelclassifyingdailyphysicalbehaviorinolderadultsthehar70model
AT bachkerstin validationofanactivitytyperecognitionmodelclassifyingdailyphysicalbehaviorinolderadultsthehar70model
AT maronininaskjæret validationofanactivitytyperecognitionmodelclassifyingdailyphysicalbehaviorinolderadultsthehar70model