EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

On-Device Semi-Supervised Activity Detection: A New Privacy-Aware Personalized Health Monitoring Approach

Avirup Roy iD, Hrishikesh Dutta iD, Amit Kumar Bhuyan, Subir Biswas

Sensors · 2024

DOI: 10.3390/s24144444 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Avirup Roy und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA. Hauptthemen laut MEDLINE: Algorithms, Wearable Electronic Devices. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents an on-device semi-supervised human activity detection system that can learn and predict human activity patterns in real time. The clinical objective is to monitor and detect the unhealthy sedentary lifestyle of a user. The proposed semi-supervised learning (SSL) framework uses sparsely labelled user activity events acquired from Inertial Measurement Unit sensors installed as wearable devices. The proposed cluster-based learning model in this approach is trained with data from the same target user, thus preserving data privacy while providing personalized activity detection services. Two different cluster labelling strategies, namely, population-based and distance-based strategies, are employed to achieve the desired classification performance. The proposed system is shown to be highly accurate and computationally efficient for different algorithmic parameters, which is relevant in the context of limited computing resources on typical wearable devices. Extensive experimentation and simulation study have been conducted on multi-user human activity data from the public domain in order to analyze the trade-off between classification accuracy and computation complexity of the proposed learning paradigm with different algorithmic hyper-parameters. With 4.17 h of training time for 8000 activity episodes, the proposed SSL approach consumes at most 20 KB of CPU memory space, while providing a maximum accuracy of 90% and 100% classification rates.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsWearable Electronic DevicesHumansMonitoring, PhysiologicPrivacySupervised Machine LearningHuman ActivitiesPrecision Medicine

Stichwörter der Autor:innen

health monitoringhuman activity detectionon-device learningpersonalized machine learningprivacy preservingsemi-supervised learningwearable devices

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA.

ORCID-Profile: Avirup Roy, Hrishikesh Dutta

Zitieren

APA

Roy, A., Dutta, H., Bhuyan, A. K., & Biswas, S. (2024). On-Device Semi-Supervised Activity Detection: A New Privacy-Aware Personalized Health Monitoring Approach. Sensors. https://doi.org/10.3390/s24144444

Vancouver

Roy A, Dutta H, Bhuyan AK, Biswas S. On-Device Semi-Supervised Activity Detection: A New Privacy-Aware Personalized Health Monitoring Approach. Sensors. 2024. doi:10.3390/s24144444

BibTeX
@article{Roy2024,
  author = {Roy, Avirup and Dutta, Hrishikesh and Bhuyan, Amit Kumar and Biswas, Subir},
  title = {On-Device Semi-Supervised Activity Detection: A New Privacy-Aware Personalized Health Monitoring Approach},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24144444}
}
Kostenlos starten →