Efficient embedded sleep wake classification for open-source actigraphy

Abstract This study presents a thorough analysis of sleep/wake detection algorithms for efficient on-device sleep tracking using wearable accelerometric devices. It develops a novel end-to-end algorithm using convolutional neural network applied to raw accelerometric signals recorded by an open-sour...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Tommaso Banfi, Nicolò Valigi, Marco di Galante, Paola d’Ascanio, Gastone Ciuti, Ugo Faraguna
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/bc563d4fe26d448399528de23fc2ff5b
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:bc563d4fe26d448399528de23fc2ff5b
record_format dspace
spelling oai:doaj.org-article:bc563d4fe26d448399528de23fc2ff5b2021-12-02T14:01:35ZEfficient embedded sleep wake classification for open-source actigraphy10.1038/s41598-020-79294-y2045-2322https://doaj.org/article/bc563d4fe26d448399528de23fc2ff5b2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-79294-yhttps://doaj.org/toc/2045-2322Abstract This study presents a thorough analysis of sleep/wake detection algorithms for efficient on-device sleep tracking using wearable accelerometric devices. It develops a novel end-to-end algorithm using convolutional neural network applied to raw accelerometric signals recorded by an open-source wrist-worn actigraph. The aim of the study is to develop an automatic classifier that: (1) is highly generalizable to heterogenous subjects, (2) would not require manual features’ extraction, (3) is computationally lightweight, embeddable on a sleep tracking device, and (4) is suitable for a wide assortment of actigraphs. Hereby, authors analyze sleep parameters, such as total sleep time, waking after sleep onset and sleep efficiency, by comparing the outcomes of the proposed algorithm to the gold standard polysomnographic concurrent recordings. The relatively substantial agreement (Cohen’s kappa coefficient, median, equal to 0.78 ± 0.07) and the low-computational cost (2727 floating-point operations) make this solution suitable for an on-board sleep-detection approach.Tommaso BanfiNicolò ValigiMarco di GalantePaola d’AscanioGastone CiutiUgo FaragunaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Tommaso Banfi
Nicolò Valigi
Marco di Galante
Paola d’Ascanio
Gastone Ciuti
Ugo Faraguna
Efficient embedded sleep wake classification for open-source actigraphy
description Abstract This study presents a thorough analysis of sleep/wake detection algorithms for efficient on-device sleep tracking using wearable accelerometric devices. It develops a novel end-to-end algorithm using convolutional neural network applied to raw accelerometric signals recorded by an open-source wrist-worn actigraph. The aim of the study is to develop an automatic classifier that: (1) is highly generalizable to heterogenous subjects, (2) would not require manual features’ extraction, (3) is computationally lightweight, embeddable on a sleep tracking device, and (4) is suitable for a wide assortment of actigraphs. Hereby, authors analyze sleep parameters, such as total sleep time, waking after sleep onset and sleep efficiency, by comparing the outcomes of the proposed algorithm to the gold standard polysomnographic concurrent recordings. The relatively substantial agreement (Cohen’s kappa coefficient, median, equal to 0.78 ± 0.07) and the low-computational cost (2727 floating-point operations) make this solution suitable for an on-board sleep-detection approach.
format article
author Tommaso Banfi
Nicolò Valigi
Marco di Galante
Paola d’Ascanio
Gastone Ciuti
Ugo Faraguna
author_facet Tommaso Banfi
Nicolò Valigi
Marco di Galante
Paola d’Ascanio
Gastone Ciuti
Ugo Faraguna
author_sort Tommaso Banfi
title Efficient embedded sleep wake classification for open-source actigraphy
title_short Efficient embedded sleep wake classification for open-source actigraphy
title_full Efficient embedded sleep wake classification for open-source actigraphy
title_fullStr Efficient embedded sleep wake classification for open-source actigraphy
title_full_unstemmed Efficient embedded sleep wake classification for open-source actigraphy
title_sort efficient embedded sleep wake classification for open-source actigraphy
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/bc563d4fe26d448399528de23fc2ff5b
work_keys_str_mv AT tommasobanfi efficientembeddedsleepwakeclassificationforopensourceactigraphy
AT nicolovaligi efficientembeddedsleepwakeclassificationforopensourceactigraphy
AT marcodigalante efficientembeddedsleepwakeclassificationforopensourceactigraphy
AT paoladascanio efficientembeddedsleepwakeclassificationforopensourceactigraphy
AT gastoneciuti efficientembeddedsleepwakeclassificationforopensourceactigraphy
AT ugofaraguna efficientembeddedsleepwakeclassificationforopensourceactigraphy
_version_ 1718392165766266880