EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Office Posture Detection Using Ceiling-Mounted Ultra-Wideband Radar and Attention-Based Modality Fusion

Wei Lu iD, Christopher Bird iD, Moid Sandhu iD, David Silvera-Tawil iD

Sensors · 20.08.2025 · 25 (16) · 5164

DOI: 10.3390/s25165164 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 20.08.2025. Verfasst von Wei Lu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Australian e-Health Research Centre, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Brisbane, QLD 4029, Australia. Hauptthemen laut MEDLINE: Radar, Posture, Attention. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Future Science Platforms, CSIRO.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Prolonged sedentary behavior in office environments is a key risk factor for musculoskeletal disorders and metabolic health issues. While workplace stretching interventions can mitigate these risks, effective monitoring solutions are often limited by privacy concerns and constrained sensor placement. This study proposes a ceiling-mounted ultra-wideband (UWB) radar system for privacy-preserving classification of working and stretching postures in office settings. In this study, data were collected from ten participants in five scenarios: four posture classes (seated working, seated stretching, standing working, standing stretching), and empty environment. Distance and Doppler information extracted from the UWB radar signals was transformed into modality-specific images, which were then used as inputs to two classification models: ConcatFusion, a baseline model that fuses features by concatenation, and AttnFusion, which introduces spatial attention and convolutional feature integration. Both models were evaluated using leave-one-subject-out cross-validation. The AttnFusion model outperformed ConcatFusion, achieving a testing accuracy of 90.6% and a macro F1-score of 90.5%. These findings demonstrate the effectiveness of a ceiling-mounted UWB radar combined with attention-based modality fusion for unobtrusive office posture monitoring. The approach offers a privacy-preserving solution with potential applications in real-time ergonomic assessment and integration into workplace health and safety programs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadarPostureAttentionHumansWorkplaceAdultMaleFemale

Stichwörter der Autor:innen

human activity recognitionmachine learningmultimodal fusionoffice ergonomicssignal processingultra-wideband radar

Autor:innen und Institutionen

  • Australian e-Health Research Centre, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Brisbane, QLD 4029, Australia.
  • School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, QLD 4072, Australia.
  • School of Biomedical Sciences, The University of Queensland, Brisbane, QLD 4072, Australia.
  • School of Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia.
  • International Centre for Future Health Systems, University of New South Wales, Sydney, NSW 2052, Australia.

ORCID-Profile: Wei Lu, Christopher Bird, Moid Sandhu, David Silvera-Tawil

Förderung

  • Future Science Platforms, CSIRO

Zitieren

APA

Lu, W., Bird, C., Sandhu, M., & Silvera-Tawil, D. (2025). Office Posture Detection Using Ceiling-Mounted Ultra-Wideband Radar and Attention-Based Modality Fusion. Sensors, 25(16), 5164. https://doi.org/10.3390/s25165164

Vancouver

Lu W, Bird C, Sandhu M, Silvera-Tawil D. Office Posture Detection Using Ceiling-Mounted Ultra-Wideband Radar and Attention-Based Modality Fusion. Sensors. 2025;25(16):5164. doi:10.3390/s25165164

BibTeX
@article{Lu2025,
  author = {Lu, Wei and Bird, Christopher and Sandhu, Moid and Silvera-Tawil, David},
  title = {Office Posture Detection Using Ceiling-Mounted Ultra-Wideband Radar and Attention-Based Modality Fusion},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {16},
  pages = {5164},
  doi = {10.3390/s25165164}
}
Kostenlos starten →