EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Energy Expenditure Prediction from Accelerometry Data Using Long Short-Term Memory Recurrent Neural Networks

Martin Vibæk, Abdolrahman Peimankar iD, Uffe Kock Wiil iD, Daniel Arvidsson, Jan Christian Brønd iD

Sensors · 14.04.2024 · 24 (8) · 2520

DOI: 10.3390/s24082520 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.04.2024. Verfasst von Martin Vibæk und 4 weiteren Autor:innen. Beteiligte Einrichtung: SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, 5230 Odense, Denmark. Hauptthemen laut MEDLINE: Accelerometry, Neural Networks, Computer, Energy Metabolism. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Swedish Research Council for Health Working Life and Welfare, University of Southern Denmark, Swedish Research Council for Health, Working Life and Welfare.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accurate estimation of energy expenditure from simple objective accelerometry measurements provides a valuable method for investigating the effect of physical activity (PA) interventions or population surveillance. Methods have been evaluated previously, but none utilize the temporal aspects of the accelerometry data. In this study, we investigated the energy expenditure prediction from acceleration measured at the subjects’ hip, wrist, thigh, and back using recurrent neural networks utilizing temporal elements of the data. The acceleration was measured in children (N = 33) performing a standardized activity protocol in their natural environment. The energy expenditure was modelled using Multiple Linear Regression (MLR), stacked long short-term memory (LSTM) networks, and combined convolutional neural networks (CNN) and LSTM. The correlation and mean absolute percentage error (MAPE) were 0.76 and 19.9% for the MLR, 0.882 and 0.879 and 14.22% for the LSTM, and, with the combined LSTM-CNN, the best performance of 0.883 and 13.9% was achieved. The prediction error for vigorous intensities was significantly different (p < 0.01) from those of the other intensity domains: sedentary, light, and moderate. Utilizing the temporal elements of movement significantly improves energy expenditure prediction accuracy compared to other conventional approaches, but the prediction error for vigorous intensities requires further investigation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AccelerometryNeural Networks, ComputerEnergy MetabolismHumansMaleFemaleChildExerciseLinear Models

Stichwörter der Autor:innen

LSTMaccelerometrychildrendeep learningenergy expenditure

Autor:innen und Institutionen

  • SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, 5230 Odense, Denmark.
  • Center for Health and Performance, Department of Food and Nutrition, and Sport Science, Faculty of Education, University of Gothenburg, 405 30 Gothenburg, Sweden.
  • Department of Sport Science and Clinical Biomechanics, University of Southern Denmark, 5230 Odense, Denmark.

ORCID-Profile: Abdolrahman Peimankar, Uffe Kock Wiil, Jan Christian Brønd

Förderung

  • Swedish Research Council for Health Working Life and Welfare
  • University of Southern Denmark
  • Swedish Research Council for Health, Working Life and Welfare

Zitieren

APA

Vibæk, M., Peimankar, A., Wiil, U. K., Arvidsson, D., & Brønd, J. C. (2024). Energy Expenditure Prediction from Accelerometry Data Using Long Short-Term Memory Recurrent Neural Networks. Sensors, 24(8), 2520. https://doi.org/10.3390/s24082520

Vancouver

Vibæk M, Peimankar A, Wiil UK, Arvidsson D, Brønd JC. Energy Expenditure Prediction from Accelerometry Data Using Long Short-Term Memory Recurrent Neural Networks. Sensors. 2024;24(8):2520. doi:10.3390/s24082520

BibTeX
@article{Vibk2024,
  author = {Vibæk, Martin and Peimankar, Abdolrahman and Wiil, Uffe Kock and Arvidsson, Daniel and Brønd, Jan Christian},
  title = {Energy Expenditure Prediction from Accelerometry Data Using Long Short-Term Memory Recurrent Neural Networks},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {8},
  pages = {2520},
  doi = {10.3390/s24082520}
}
Kostenlos starten →