EUVIMEDEUVIMED entdecken
Crossref

SmartFallMM: A Multimodal Dataset for Fall Detection Using Commodity Devices

Syed Tousiful Haque, Awatif Yasmin, Minakshi Debnath, Jianyuan Ni, Sana Alamgeer, Joshua T. Chang, Anne Hee Hiong Ngu

IEEE Sensors Journal · 2026-09 · 26 (18) · 27973-27983

DOI: 10.1109/jsen.2026.3720563 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, 2026-09. Verfasst von Syed Tousiful Haque und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: U.S. National Science Foundation-Smart Health and Biomedical Research in the Era of Artificial Intelligence and Advanced Data Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wearable sensor-based fall detection systems that rely solely on inertial measurement unit (IMU) data are prone to high false-positive rates, particularly for subtle ”soft falls.” While incorporating multimodal data can substantially improve detection accuracy, existing multimodal datasets typically depend on specialized, lab-grade IMU sensors and often lack demographic diversity, limiting their applicability to real-world deployment in commodity wearable devices and generalizability across age groups. To bridge this gap, we present SmartFallMM, a multimodal dataset collected using a combination of commodity and specialized hardware: smartwatches, smartphones, Kinect motion cameras, and Meta sensors. The dataset captures synchronized skeletal motion (32 joint positions), accelerometer and gyroscope readings from 51 participants spanning two distinct age groups (20–30 and 60–93), performing 14 activities encompassing both falls and activities of daily living (ADLs). Since multimodal models are too computationally demanding for edge devices, we propose modality-aware knowledge distillation (MAKD), a cross-modal approach that distills multimodal knowledge into an IMU-only model. MAKD improves F1-score by up to 7.85% on SmartFallMM and 8.65% on the UP-Fall dataset over IMU-only baselines, showing the practical value of SmartFallMM and the effectiveness of cross-modal knowledge transfer.

Förderung

  • U.S. National Science Foundation-Smart Health and Biomedical Research in the Era of Artificial Intelligence and Advanced Data Science

Zitieren

APA

Haque, S. T., Yasmin, A., Debnath, M., Ni, J., Alamgeer, S., Chang, J. T., & Ngu, A. H. H. (2026). SmartFallMM: A Multimodal Dataset for Fall Detection Using Commodity Devices. IEEE Sensors Journal, 26(18), 27973-27983. https://doi.org/10.1109/jsen.2026.3720563

Vancouver

Haque ST, Yasmin A, Debnath M, Ni J, Alamgeer S, Chang JT, et al. SmartFallMM: A Multimodal Dataset for Fall Detection Using Commodity Devices. IEEE Sensors Journal. 2026;26(18):27973-27983. doi:10.1109/jsen.2026.3720563

BibTeX
@article{Haque2026,
  author = {Haque, Syed Tousiful and Yasmin, Awatif and Debnath, Minakshi and Ni, Jianyuan and Alamgeer, Sana and Chang, Joshua T. and Ngu, Anne Hee Hiong},
  title = {SmartFallMM: A Multimodal Dataset for Fall Detection Using Commodity Devices},
  journal = {IEEE Sensors Journal},
  year = {2026},
  volume = {26},
  number = {18},
  pages = {27973--27983},
  doi = {10.1109/jsen.2026.3720563}
}
Kostenlos starten →