Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data

Martin Baumgartner; Manuel Grössl; Raphaela Haumer; Katharina Poimer; Flora Prantl; Katharina Weick; Markus Falgenhauer; Stefan Beyer; Andreas Ziegl; Aaron Lauschensky; Fabian Wiesmüller; Karl Kreiner; Dieter Hayn; Günter Schreier

doi:10.3233/SHTI240041

Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data

Martin Baumgartner, Manuel Grössl, Raphaela Haumer, Katharina Poimer, Flora Prantl, Katharina Weick, Markus Falgenhauer, Stefan Beyer, Andreas Ziegl, Aaron Lauschensky, Fabian Wiesmüller, Karl Kreiner, Dieter Hayn, Günter Schreier

Digital Health Information Systems

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Poster Presentation › peer-review

5 Downloads (Pure)

Abstract

BACKGROUND: This study focuses on the development of a neural network model to predict perceived sleep quality using data from wearable devices. We collected various physiological metrics from 18 participants over four weeks, including heart rate, physical activity, and both device-measured and self-reported sleep quality.

OBJECTIVES: The primary objective was to correlate wearable device data with subjective sleep quality perceptions.

METHODS: Our approach used data processing, feature engineering, and optimizing a Multi-Layer Perceptron classifier.

RESULTS: Despite comprehensive data analysis and model experimentation, the predictive accuracy for perceived sleep quality was moderate (59%), highlighting the complexities in accurately quantifying subjective sleep experiences through wearable data. Applying a tolerance of 1 grade (on a scale from 1-5), increased accuracy to 92%.

DISCUSSION: More in-depth analysis is required to fully comprehend how wearables and artificial intelligence might assist in understanding sleep behavior.

Original language	English
Title of host publication	dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health
Editors	Dieter Hayn, Bernhard Pfeifer, Günter Schreier, Martin Baumgartner
Publisher	IOS Press BV
Pages	221-227
Number of pages	7
Volume	313
ISBN (Electronic)	978-1-64368-517-5
ISBN (Print)	978-1-64368-516-8
DOIs	https://doi.org/10.3233/SHTI240041
Publication status	Published - 26 Apr 2024
Event	dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health - Apothekertrakt of Schloss Schönbrunn, Vienna, Austria Duration: 7 May 2024 → 8 May 2024 Conference number: 18 http://dhealth.at

Publication series

Name	Studies in Health Technology and Informatics
Publisher	IOS Press BV
ISSN (Print)	0926-9630

Conference

Conference	dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health
Abbreviated title	dHealth 2024
Country/Territory	Austria
City	Vienna
Period	7/05/24 → 8/05/24
Other	Conference mission and topic Since 2007, the dHealth conference is organized by AIT, ÖGBMT, OCG and UMIT. Each year, this event attracts around 300 participants from academia, industry, government, and health care organisations. In keeping with its interdisciplinary mission, the dHealth conference series provides a platform for researchers, practitioners, decision makers and vendors to discuss innovative health informatics and eHealth solutions to improve the quality and efficiency of healthcare by digital technologies. We look forward to welcoming you in Vienna for our 18th Annual Conference on Health Informatics meets Digital Health. Website: www.dHealth.at Contact: [email protected]
Internet address	http://dhealth.at

Research Field

Exploration of Digital Health

Keywords

Sleep Quality
Wearable Electronic Devices
Neural Network
Multi-Layer Perceptrons
Electronic Data Processing

Access to Document

10.3233/SHTI240041Licence: CC BY-NC

SHTI-313-SHTI240041-5Final published version, 430 KBLicence: CC BY-NC

Cite this

Baumgartner, M., Grössl, M., Haumer, R., Poimer, K., Prantl, F., Weick, K., Falgenhauer, M., Beyer, S., Ziegl, A., Lauschensky, A., Wiesmüller, F., Kreiner, K., Hayn, D., & Schreier, G. (2024). Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data. In D. Hayn, B. Pfeifer, G. Schreier, & M. Baumgartner (Eds.), dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health (Vol. 313, pp. 221-227). (Studies in Health Technology and Informatics). IOS Press BV. https://doi.org/10.3233/SHTI240041

Baumgartner, Martin ; Grössl, Manuel ; Haumer, Raphaela et al. / Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data. dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health. editor / Dieter Hayn ; Bernhard Pfeifer ; Günter Schreier ; Martin Baumgartner. Vol. 313 IOS Press BV, 2024. pp. 221-227 (Studies in Health Technology and Informatics).

@inbook{f741770216414cb5a9fdb635ff8c1b4e,

title = "Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data",

abstract = "BACKGROUND: This study focuses on the development of a neural network model to predict perceived sleep quality using data from wearable devices. We collected various physiological metrics from 18 participants over four weeks, including heart rate, physical activity, and both device-measured and self-reported sleep quality.OBJECTIVES: The primary objective was to correlate wearable device data with subjective sleep quality perceptions.METHODS: Our approach used data processing, feature engineering, and optimizing a Multi-Layer Perceptron classifier.RESULTS: Despite comprehensive data analysis and model experimentation, the predictive accuracy for perceived sleep quality was moderate (59%), highlighting the complexities in accurately quantifying subjective sleep experiences through wearable data. Applying a tolerance of 1 grade (on a scale from 1-5), increased accuracy to 92%.DISCUSSION: More in-depth analysis is required to fully comprehend how wearables and artificial intelligence might assist in understanding sleep behavior.",

keywords = "Sleep Quality, Wearable Electronic Devices, Neural Network, Multi-Layer Perceptrons, Electronic Data Processing",

author = "Martin Baumgartner and Manuel Gr{\"o}ssl and Raphaela Haumer and Katharina Poimer and Flora Prantl and Katharina Weick and Markus Falgenhauer and Stefan Beyer and Andreas Ziegl and Aaron Lauschensky and Fabian Wiesm{\"u}ller and Karl Kreiner and Dieter Hayn and G{\"u}nter Schreier",

note = "{\textcopyright} 2024 The Authors. This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0).; dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health, dHealth 2024 ; Conference date: 07-05-2024 Through 08-05-2024",

year = "2024",

month = apr,

day = "26",

doi = "10.3233/SHTI240041",

language = "English",

isbn = " 978-1-64368-516-8 ",

volume = "313",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press BV",

pages = "221--227",

editor = "Dieter Hayn and Bernhard Pfeifer and G{\"u}nter Schreier and Martin Baumgartner",

booktitle = "dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health",

address = "Netherlands",

url = "http://dhealth.at",

}

Baumgartner, M, Grössl, M, Haumer, R, Poimer, K, Prantl, F, Weick, K, Falgenhauer, M , Beyer, S, Ziegl, A, Lauschensky, A , Wiesmüller, F , Kreiner, K , Hayn, D & Schreier, G 2024, Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data. in D Hayn, B Pfeifer, G Schreier & M Baumgartner (eds), dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health. vol. 313, Studies in Health Technology and Informatics, IOS Press BV, pp. 221-227, dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health, Vienna, Austria, 7/05/24. https://doi.org/10.3233/SHTI240041

Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data. / Baumgartner, Martin; Grössl, Manuel; Haumer, Raphaela et al.
dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health. ed. / Dieter Hayn; Bernhard Pfeifer; Günter Schreier; Martin Baumgartner. Vol. 313 IOS Press BV, 2024. p. 221-227 (Studies in Health Technology and Informatics).

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Poster Presentation › peer-review

TY - CHAP

T1 - Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data

AU - Baumgartner, Martin

AU - Grössl, Manuel

AU - Haumer, Raphaela

AU - Poimer, Katharina

AU - Prantl, Flora

AU - Weick, Katharina

AU - Falgenhauer, Markus

AU - Beyer, Stefan

AU - Ziegl, Andreas

AU - Lauschensky, Aaron

AU - Wiesmüller, Fabian

AU - Kreiner, Karl

AU - Hayn, Dieter

AU - Schreier, Günter

N1 - Conference code: 18

PY - 2024/4/26

Y1 - 2024/4/26

N2 - BACKGROUND: This study focuses on the development of a neural network model to predict perceived sleep quality using data from wearable devices. We collected various physiological metrics from 18 participants over four weeks, including heart rate, physical activity, and both device-measured and self-reported sleep quality.OBJECTIVES: The primary objective was to correlate wearable device data with subjective sleep quality perceptions.METHODS: Our approach used data processing, feature engineering, and optimizing a Multi-Layer Perceptron classifier.RESULTS: Despite comprehensive data analysis and model experimentation, the predictive accuracy for perceived sleep quality was moderate (59%), highlighting the complexities in accurately quantifying subjective sleep experiences through wearable data. Applying a tolerance of 1 grade (on a scale from 1-5), increased accuracy to 92%.DISCUSSION: More in-depth analysis is required to fully comprehend how wearables and artificial intelligence might assist in understanding sleep behavior.

AB - BACKGROUND: This study focuses on the development of a neural network model to predict perceived sleep quality using data from wearable devices. We collected various physiological metrics from 18 participants over four weeks, including heart rate, physical activity, and both device-measured and self-reported sleep quality.OBJECTIVES: The primary objective was to correlate wearable device data with subjective sleep quality perceptions.METHODS: Our approach used data processing, feature engineering, and optimizing a Multi-Layer Perceptron classifier.RESULTS: Despite comprehensive data analysis and model experimentation, the predictive accuracy for perceived sleep quality was moderate (59%), highlighting the complexities in accurately quantifying subjective sleep experiences through wearable data. Applying a tolerance of 1 grade (on a scale from 1-5), increased accuracy to 92%.DISCUSSION: More in-depth analysis is required to fully comprehend how wearables and artificial intelligence might assist in understanding sleep behavior.

KW - Sleep Quality

KW - Wearable Electronic Devices

KW - Neural Network

KW - Multi-Layer Perceptrons

KW - Electronic Data Processing

U2 - 10.3233/SHTI240041

DO - 10.3233/SHTI240041

M3 - Conference Proceedings with Poster Presentation

C2 - 38682534

SN - 978-1-64368-516-8

VL - 313

T3 - Studies in Health Technology and Informatics

SP - 221

EP - 227

BT - dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health

A2 - Hayn, Dieter

A2 - Pfeifer, Bernhard

A2 - Schreier, Günter

A2 - Baumgartner, Martin

PB - IOS Press BV

T2 - dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health

Y2 - 7 May 2024 through 8 May 2024

ER -

Baumgartner M, Grössl M, Haumer R, Poimer K, Prantl F, Weick K et al. Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data. In Hayn D, Pfeifer B, Schreier G, Baumgartner M, editors, dHealth 2024 - 18th Annual Conference on Health Informatics meets Digital Health. Vol. 313. IOS Press BV. 2024. p. 221-227. (Studies in Health Technology and Informatics). doi: 10.3233/SHTI240041

Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data

Abstract

Publication series

Conference

Research Field

Keywords

Access to Document

Fingerprint

Cite this