Publication

Using deep learning for unobtrusive sleep stage classification

View document

Bibliographic Details
Summary:Sleep represents a fundamental role to our well-being and today, as sleep disorders become more and more common, there is a growing necessity to monitor our sleep quality daily. Unobtrusive automatic sleep stage classification has made a tremendous breakthrough in this subject allowing regular users to monitor their sleep with day-to-day wearables, such as Fitbit Charge 2 tracker, contrary to the traditional manual sleep scoring based on polysomnography (PSG). Using cardiorespiratory signals to sleep stage has attracted increased attention as these signals can be obtained through unobtrusive techniques and have potential for continuous daily application. Therefore, in this thesis, deep learning frameworks based on Long-short-memory networks (LSTMs) and Convolutional Neural Networks (CNNs) are used to sleep stage classify, either just using respiratory effort signals, for example obtained from respiratory inductance plethysmography (RIP), or using the combination of respiratory and cardiac features, often based on heart rate variability (HRV) calculated from electrocardiogram (ECG). The dataset used was the SIESTA dataset that contains a total of 294 subjects (588 PSG recordings) of which 197 are healthy subjects, 51 suffer from obstructive sleep apnea syndrome (OSA), and the remaining from a variety of sleep or sleep related disorders. The classification problem was divided in a three-class and four-class sleep stage classification problem. As for the results, it was obtained with respiratory data for three stages classification (Wake, rapid eye-movement (REM) and non-REM stages) a Cohen’s kappa () of 0.46 for the overall pool of subjects (All), 0.50 for healthy subjects and 0.34 for OSA subjects. For four stages classification (Wake, REM, light sleep (N1/N2) and deep sleep (N3/N4) stages) it was obtained a Cohen’s Kappa () of 0.40 for the subject pool containing all subjects (All), 0.44 for healthy subjects and 0.31 for OSA. With cardiorespiratory data, for four stages classification, it was obtained a of 0.40 for the overall subject pool (All), 0.44 for healthy subjects and 0.30 for OSA subjects. With three stages, a of 0.46 for All subjects, 0.51 for healthy and 0.32 for OSA subjects. These results demonstrate that, with the developed frameworks, it is possible to achieve fairly good results as they are similar, in some cases moderately higher, to the current state-of-the-art but fail to generalize well, as significant differences can be found between subject types (All, Healthy and OSA).
Main Authors:Prata, Marco André Ramos Dias
Subject:Engenharia e Tecnologia::Engenharia Médica
Year:2018
Country:Portugal
Document type:master thesis
Access type:open access
Associated institution:Universidade do Minho
Language:English
Origin:RepositóriUM - Universidade do Minho
_version_ 1867438252870336512
author Prata, Marco André Ramos Dias
author_facet Prata, Marco André Ramos Dias
author_role author
contributor_name_str_mv Novais, Paulo
Fonseca, Pedro
RepositóriUM - Universidade do Minho
country_str PT
creators_json_txt [{\"Person.name\":\"Prata, Marco André Ramos Dias\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Novais, Paulo
Fonseca, Pedro
RepositóriUM - Universidade do Minho
datacite.creators.creator.creatorName.fl_str_mv Prata, Marco André Ramos Dias
datacite.date.Accepted.fl_str_mv 2018-12-13T00:00:00Z
datacite.date.available.fl_str_mv 2022-09-30T17:11:58Z
datacite.date.embargoed.fl_str_mv 2022-09-30T17:11:58Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Engenharia e Tecnologia::Engenharia Médica
datacite.titles.title.fl_str_mv Using deep learning for unobtrusive sleep stage classification
dc.contributor.none.fl_str_mv Novais, Paulo
Fonseca, Pedro
RepositóriUM - Universidade do Minho
dc.creator.none.fl_str_mv Prata, Marco André Ramos Dias
dc.date.Accepted.fl_str_mv 2018-12-13T00:00:00Z
dc.date.available.fl_str_mv 2022-09-30T17:11:58Z
dc.date.embargoed.fl_str_mv 2022-09-30T17:11:58Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://hdl.handle.net/1822/79850
dc.language.none.fl_str_mv eng
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Engenharia e Tecnologia::Engenharia Médica
dc.title.fl_str_mv Using deep learning for unobtrusive sleep stage classification
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_bdcc
description Sleep represents a fundamental role to our well-being and today, as sleep disorders become more and more common, there is a growing necessity to monitor our sleep quality daily. Unobtrusive automatic sleep stage classification has made a tremendous breakthrough in this subject allowing regular users to monitor their sleep with day-to-day wearables, such as Fitbit Charge 2 tracker, contrary to the traditional manual sleep scoring based on polysomnography (PSG). Using cardiorespiratory signals to sleep stage has attracted increased attention as these signals can be obtained through unobtrusive techniques and have potential for continuous daily application. Therefore, in this thesis, deep learning frameworks based on Long-short-memory networks (LSTMs) and Convolutional Neural Networks (CNNs) are used to sleep stage classify, either just using respiratory effort signals, for example obtained from respiratory inductance plethysmography (RIP), or using the combination of respiratory and cardiac features, often based on heart rate variability (HRV) calculated from electrocardiogram (ECG). The dataset used was the SIESTA dataset that contains a total of 294 subjects (588 PSG recordings) of which 197 are healthy subjects, 51 suffer from obstructive sleep apnea syndrome (OSA), and the remaining from a variety of sleep or sleep related disorders. The classification problem was divided in a three-class and four-class sleep stage classification problem. As for the results, it was obtained with respiratory data for three stages classification (Wake, rapid eye-movement (REM) and non-REM stages) a Cohen’s kappa () of 0.46 for the overall pool of subjects (All), 0.50 for healthy subjects and 0.34 for OSA subjects. For four stages classification (Wake, REM, light sleep (N1/N2) and deep sleep (N3/N4) stages) it was obtained a Cohen’s Kappa () of 0.40 for the subject pool containing all subjects (All), 0.44 for healthy subjects and 0.31 for OSA. With cardiorespiratory data, for four stages classification, it was obtained a of 0.40 for the overall subject pool (All), 0.44 for healthy subjects and 0.30 for OSA subjects. With three stages, a of 0.46 for All subjects, 0.51 for healthy and 0.32 for OSA subjects. These results demonstrate that, with the developed frameworks, it is possible to achieve fairly good results as they are similar, in some cases moderately higher, to the current state-of-the-art but fail to generalize well, as significant differences can be found between subject types (All, Healthy and OSA).
dirty 0
eu_rights_str_mv openAccess
format masterThesis
fulltext.url.fl_str_mv https://repositorium.uminho.pt/bitstreams/4cd6c836-ed85-4805-9bbb-c62e5496dc49/download
id rum_4e8cb2ffd81f3231048c5e07ea1bb402
identifier.url.fl_str_mv https://hdl.handle.net/1822/79850
instacron_str repositorium
institution Universidade do Minho
instname_str Universidade do Minho
language eng
network_acronym_str rum
network_name_str RepositóriUM - Universidade do Minho
oai_identifier_str oai:repositorium.uminho.pt:1822/79850
organization_str_mv urn:organizationAcronym:repositorium
person_str_mv Prata, Marco André Ramos Dias
publishDate 2018
reponame_str RepositóriUM - Universidade do Minho
repository_id_str urn:repositoryAcronym:rum
service_str_mv urn:repositoryAcronym:rum
spelling engporSleep represents a fundamental role to our well-being and today, as sleep disorders become more and more common, there is a growing necessity to monitor our sleep quality daily. Unobtrusive automatic sleep stage classification has made a tremendous breakthrough in this subject allowing regular users to monitor their sleep with day-to-day wearables, such as Fitbit Charge 2 tracker, contrary to the traditional manual sleep scoring based on polysomnography (PSG). Using cardiorespiratory signals to sleep stage has attracted increased attention as these signals can be obtained through unobtrusive techniques and have potential for continuous daily application. Therefore, in this thesis, deep learning frameworks based on Long-short-memory networks (LSTMs) and Convolutional Neural Networks (CNNs) are used to sleep stage classify, either just using respiratory effort signals, for example obtained from respiratory inductance plethysmography (RIP), or using the combination of respiratory and cardiac features, often based on heart rate variability (HRV) calculated from electrocardiogram (ECG). The dataset used was the SIESTA dataset that contains a total of 294 subjects (588 PSG recordings) of which 197 are healthy subjects, 51 suffer from obstructive sleep apnea syndrome (OSA), and the remaining from a variety of sleep or sleep related disorders. The classification problem was divided in a three-class and four-class sleep stage classification problem. As for the results, it was obtained with respiratory data for three stages classification (Wake, rapid eye-movement (REM) and non-REM stages) a Cohen’s kappa () of 0.46 for the overall pool of subjects (All), 0.50 for healthy subjects and 0.34 for OSA subjects. For four stages classification (Wake, REM, light sleep (N1/N2) and deep sleep (N3/N4) stages) it was obtained a Cohen’s Kappa () of 0.40 for the subject pool containing all subjects (All), 0.44 for healthy subjects and 0.31 for OSA. With cardiorespiratory data, for four stages classification, it was obtained a of 0.40 for the overall subject pool (All), 0.44 for healthy subjects and 0.30 for OSA subjects. With three stages, a of 0.46 for All subjects, 0.51 for healthy and 0.32 for OSA subjects. These results demonstrate that, with the developed frameworks, it is possible to achieve fairly good results as they are similar, in some cases moderately higher, to the current state-of-the-art but fail to generalize well, as significant differences can be found between subject types (All, Healthy and OSA).application/pdfporUsing deep learning for unobtrusive sleep stage classificationPrata, Marco André Ramos DiasNovais, PauloFonseca, PedroHostingInstitutionOrganizationalRepositóriUM - Universidade do Minhoe-mailmailto:repositorium@usdb.uminho.ptrepositorium@usdb.uminho.ptTID2030111802022-09-30T17:11:58Z2018-12-132018-102018-12-13T00:00:00ZHandlehttps://hdl.handle.net/1822/79850http://purl.org/coar/access_right/c_abf2open accesshttp://www.oecd.org/science/inno/38235147.pdfFields of Science and Technology (FOS)Engenharia e Tecnologia::Engenharia Médica1492433 bytesliteraturehttp://purl.org/coar/resource_type/c_bdccmaster thesishttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://repositorium.uminho.pt/bitstreams/4cd6c836-ed85-4805-9bbb-c62e5496dc49/download
spellingShingle Using deep learning for unobtrusive sleep stage classification
Prata, Marco André Ramos Dias
Engenharia e Tecnologia::Engenharia Médica
status SINGLETON
subject.other.fl_str_mv Engenharia e Tecnologia::Engenharia Médica
title Using deep learning for unobtrusive sleep stage classification
title_full Using deep learning for unobtrusive sleep stage classification
title_fullStr Using deep learning for unobtrusive sleep stage classification
title_full_unstemmed Using deep learning for unobtrusive sleep stage classification
title_short Using deep learning for unobtrusive sleep stage classification
title_sort Using deep learning for unobtrusive sleep stage classification
topic Engenharia e Tecnologia::Engenharia Médica
topic_facet Engenharia e Tecnologia::Engenharia Médica
url https://hdl.handle.net/1822/79850
visible 1