Benchmarking Accelerometer and CNN-Based Vision Systems for Sleep Posture Classification in Healthcare Applications
Sensors · 2025
DOI: 10.3390/s25123816 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Minh Long Hoang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy. Hauptthemen laut MEDLINE: Neural Networks, Computer, Posture, Sleep, Accelerometry. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of University and Research in the framework of PNC “DARE—Digital lifelong prevention project”.
Abstract (Originalsprache)
Sleep position recognition plays a crucial role in diagnosing and managing various health conditions, such as sleep apnea, pressure ulcers, and musculoskeletal disorders. Accurate monitoring of body posture during sleep can provide valuable insights for clinicians and support the development of intelligent healthcare systems. This research presents a comparative analysis of sleep position recognition using two distinct approaches: image-based deep learning and accelerometer-based classification. There are five classes: prone, supine, right side, left side, and wake up. For the image-based method, the Visual Geometry Group 16 (VGG16) convolutional neural network was fine-tuned with data augmentation strategies including rotation, reflection, scaling, and translation to enhance model generalization. The image-based model achieved an overall accuracy of 93.49%, with perfect precision and recall for “right side” and “wakeup” positions, but slightly lower performance for “left side” and “supine” classes. In contrast, the accelerometer-based method employed a feedforward neural network trained on features extracted from segmented accelerometer data, such as signal sum, standard deviation, maximum, and spike count. This method yielded superior performance, reaching an accuracy exceeding 99.8% across most sleep positions. The “wake up” position was particularly easy to detect due to the absence of body movements such as heartbeat or respiration when the person is no longer in bed. The results demonstrate that while image-based models are effective, accelerometer-based classification offers higher precision and robustness, particularly in real-time and privacy-sensitive scenarios. Further comparisons of the system characteristics, data size, and training time are also carried out to offer crucial insights for selecting the appropriate technology in clinical, in-home, or embedded healthcare monitoring applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy.
ORCID-Profile: Minh Long Hoang, Guido Matrella, Paolo Ciampolini
Förderung
- Ministry of University and Research in the framework of PNC “DARE—Digital lifelong prevention project”
Zitieren
APA
Hoang, M. L., Matrella, G., Giannetto, D., Craparo, P., & Ciampolini, P. (2025). Benchmarking Accelerometer and CNN-Based Vision Systems for Sleep Posture Classification in Healthcare Applications. Sensors. https://doi.org/10.3390/s25123816
Vancouver
Hoang ML, Matrella G, Giannetto D, Craparo P, Ciampolini P. Benchmarking Accelerometer and CNN-Based Vision Systems for Sleep Posture Classification in Healthcare Applications. Sensors. 2025. doi:10.3390/s25123816
BibTeX
@article{Hoang2025,
author = {Hoang, Minh Long and Matrella, Guido and Giannetto, Dalila and Craparo, Paolo and Ciampolini, Paolo},
title = {Benchmarking Accelerometer and CNN-Based Vision Systems for Sleep Posture Classification in Healthcare Applications},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25123816}
}
EUVIMED