Utilising wireless sensor networks towards establishing a method of sleep profiling

Andrew McDowell, Mark Donnelly, CD Nugent, Michael McGrath

Research output: Contribution to journalArticle

Abstract

Based upon current sleep actigraphy techniques, this paper discussesan alternative non-contact method of sleep profiling that is potentially moresuitable for long term monitoring than current clinically approved techniques.The passive sleep actigraphy (PSA) platform presented here utilisesstrategically positioned accelerometers fixed on a mattress to quantify therecorded movements of a bed occupant. In this work, data captured from ayoung control group is decomposed into gravitational and inertial components.These components are then translated into activity counts using numerousquantification modalities and feature extraction techniques to isolate the mostdiscriminant attributes for optimal sleep/wake classification. These attributeswere then input into a random forest classifier to determine the sleep/wake stateof each subject based on their recoded actigraphy data with an accuracyof 89%. The findings suggest that the PSA platform is a potentially viablemethod of non-contact sleep profiling hence supporting further research intothis approach.
LanguageEnglish
Pages346-363
JournalInternational Journal of Computers in Healthcare
Volume1
Issue number4
DOIs
Publication statusPublished - 2012

Fingerprint

Wireless sensor networks
Sleep
Accelerometers
Feature extraction
Classifiers
Monitoring

Keywords

  • accelerometers
  • actigraphy
  • classification
  • feature reduction
  • passive sensors
  • sleep profiling
  • smart homes
  • wireless sensor networks.

Cite this

@article{7dd790acb3b443e1be01c9d26133e54d,
title = "Utilising wireless sensor networks towards establishing a method of sleep profiling",
abstract = "Based upon current sleep actigraphy techniques, this paper discussesan alternative non-contact method of sleep profiling that is potentially moresuitable for long term monitoring than current clinically approved techniques.The passive sleep actigraphy (PSA) platform presented here utilisesstrategically positioned accelerometers fixed on a mattress to quantify therecorded movements of a bed occupant. In this work, data captured from ayoung control group is decomposed into gravitational and inertial components.These components are then translated into activity counts using numerousquantification modalities and feature extraction techniques to isolate the mostdiscriminant attributes for optimal sleep/wake classification. These attributeswere then input into a random forest classifier to determine the sleep/wake stateof each subject based on their recoded actigraphy data with an accuracyof 89{\%}. The findings suggest that the PSA platform is a potentially viablemethod of non-contact sleep profiling hence supporting further research intothis approach.",
keywords = "accelerometers, actigraphy, classification, feature reduction, passive sensors, sleep profiling, smart homes, wireless sensor networks.",
author = "Andrew McDowell and Mark Donnelly and CD Nugent and Michael McGrath",
note = "Reference text: McDowell-A10@email.ulster.ac.uk",
year = "2012",
doi = "10.1504/IJCIH.2012.051809",
language = "English",
volume = "1",
pages = "346--363",
journal = "International Journal of Computers in Healthcare",
issn = "1755-3199",
number = "4",

}

Utilising wireless sensor networks towards establishing a method of sleep profiling. / McDowell, Andrew; Donnelly, Mark; Nugent, CD; McGrath, Michael.

In: International Journal of Computers in Healthcare, Vol. 1, No. 4, 2012, p. 346-363.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Utilising wireless sensor networks towards establishing a method of sleep profiling

AU - McDowell, Andrew

AU - Donnelly, Mark

AU - Nugent, CD

AU - McGrath, Michael

N1 - Reference text: McDowell-A10@email.ulster.ac.uk

PY - 2012

Y1 - 2012

N2 - Based upon current sleep actigraphy techniques, this paper discussesan alternative non-contact method of sleep profiling that is potentially moresuitable for long term monitoring than current clinically approved techniques.The passive sleep actigraphy (PSA) platform presented here utilisesstrategically positioned accelerometers fixed on a mattress to quantify therecorded movements of a bed occupant. In this work, data captured from ayoung control group is decomposed into gravitational and inertial components.These components are then translated into activity counts using numerousquantification modalities and feature extraction techniques to isolate the mostdiscriminant attributes for optimal sleep/wake classification. These attributeswere then input into a random forest classifier to determine the sleep/wake stateof each subject based on their recoded actigraphy data with an accuracyof 89%. The findings suggest that the PSA platform is a potentially viablemethod of non-contact sleep profiling hence supporting further research intothis approach.

AB - Based upon current sleep actigraphy techniques, this paper discussesan alternative non-contact method of sleep profiling that is potentially moresuitable for long term monitoring than current clinically approved techniques.The passive sleep actigraphy (PSA) platform presented here utilisesstrategically positioned accelerometers fixed on a mattress to quantify therecorded movements of a bed occupant. In this work, data captured from ayoung control group is decomposed into gravitational and inertial components.These components are then translated into activity counts using numerousquantification modalities and feature extraction techniques to isolate the mostdiscriminant attributes for optimal sleep/wake classification. These attributeswere then input into a random forest classifier to determine the sleep/wake stateof each subject based on their recoded actigraphy data with an accuracyof 89%. The findings suggest that the PSA platform is a potentially viablemethod of non-contact sleep profiling hence supporting further research intothis approach.

KW - accelerometers

KW - actigraphy

KW - classification

KW - feature reduction

KW - passive sensors

KW - sleep profiling

KW - smart homes

KW - wireless sensor networks.

U2 - 10.1504/IJCIH.2012.051809

DO - 10.1504/IJCIH.2012.051809

M3 - Article

VL - 1

SP - 346

EP - 363

JO - International Journal of Computers in Healthcare

T2 - International Journal of Computers in Healthcare

JF - International Journal of Computers in Healthcare

SN - 1755-3199

IS - 4

ER -