EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sleep Posture Detection via Embedded Machine Learning on a Reduced Set of Pressure Sensors

Giacomo Peruzzi iD, Alessandra Galli iD, Giada Giorgi iD, Alessandro Pozzebon iD

Sensors · 14.01.2025 · 25 (2) · 458

DOI: 10.3390/s25020458 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.01.2025. Verfasst von Giacomo Peruzzi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Engineering, University of Padova, 35122 Padova, Italy. Hauptthemen laut MEDLINE: Machine Learning, Posture, Sleep. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission, European Union’s Horizon Europe research and innovation programme.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sleep posture is a key factor in assessing sleep quality, especially for individuals with Obstructive Sleep Apnea (OSA), where the sleeping position directly affects breathing patterns: the side position alleviates symptoms, while the supine position exacerbates them. Accurate detection of sleep posture is essential in assessing and improving sleep quality. Automatic sleep posture detection systems, both wearable and non-wearable, have been developed to assess sleep quality. However, wearable solutions can be intrusive and affect sleep, while non-wearable systems, such as camera-based approaches and pressure sensor arrays, often face challenges related to privacy, cost, and computational complexity. The system in this paper proposes a microcontroller-based approach exploiting the execution of an embedded machine learning (ML) model for posture classification. By locally processing data from a minimal set of pressure sensors, the system avoids the need to transmit raw data to remote units, making it lightweight and suitable for real-time applications. Our results demonstrate that this approach maintains high classification accuracy (i.e., 0.90 and 0.96 for the configurations with 6 and 15 sensors, respectively) while reducing both hardware and computational requirements.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPostureSleepHumansPressureWearable Electronic DevicesAlgorithmsSleep Apnea, Obstructive

Stichwörter der Autor:innen

artificial intelligenceembedded machine learninginternet of thingsobstructive sleep apneapressure sensorssensor selectionsleep posture recognitionsupport vector machine

Autor:innen und Institutionen

  • Department of Information Engineering, University of Padova, 35122 Padova, Italy.
  • Department of Electrical Engineering, Eindhoven University of Technology, 5612 AZ Eindhoven, The Netherlands.

ORCID-Profile: Giacomo Peruzzi, Alessandra Galli, Giada Giorgi, Alessandro Pozzebon

Förderung

  • European Commission
  • European Union’s Horizon Europe research and innovation programme

Zitieren

APA

Peruzzi, G., Galli, A., Giorgi, G., & Pozzebon, A. (2025). Sleep Posture Detection via Embedded Machine Learning on a Reduced Set of Pressure Sensors. Sensors, 25(2), 458. https://doi.org/10.3390/s25020458

Vancouver

Peruzzi G, Galli A, Giorgi G, Pozzebon A. Sleep Posture Detection via Embedded Machine Learning on a Reduced Set of Pressure Sensors. Sensors. 2025;25(2):458. doi:10.3390/s25020458

BibTeX
@article{Peruzzi2025,
  author = {Peruzzi, Giacomo and Galli, Alessandra and Giorgi, Giada and Pozzebon, Alessandro},
  title = {Sleep Posture Detection via Embedded Machine Learning on a Reduced Set of Pressure Sensors},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {2},
  pages = {458},
  doi = {10.3390/s25020458}
}
Kostenlos starten →