EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Fall Detection in Indoor Environments Using FMCW Radar and Lightweight Ensemble CNN on Edge Devices

Ju-Hong Oh iD, Young-Joon Park, Seon-In Kim, Ji-Hyoung Kim iD, Jin-Yong Lee, Yogesh Shankar, Eui-Jong Kim iD

Sensors · 2026

DOI: 10.3390/s26196189 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Ju-Hong Oh und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Architectural Engineering, Pukyong National University, Busan 48513, Republic of Korea. Hauptthemen laut MEDLINE: Accidental Falls, Radar. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Falls are a leading cause of injury and mortality among the elderly, particularly indoors where privacy concerns limit real-time monitoring. This study developed a privacy-preserving, real-time fall detection system using a frequency-modulated continuous wave radar sensor and a lightweight convolutional neural network (CNN) architecture deployed on an edge device. To address the limitations of wearable and vision-based methods, the system leverages contactless radar sensing and an ensemble of two independent CNN models, namely, a base model designed to capture the entire fall sequence for high recall and a sub-model aimed at pinpointing the fall moment with high precision. The final decision is executed through a voting mechanism that triggers a fall alert only when both models agree, significantly reducing false positives. On 14 recording sessions withheld from the training of both models, the ensemble detected 13 of 14 falls (recall 92.9%, 95% CI 68.5–98.7%) without false alarms, and in a 24-trial on-device test comprising 4 falls and 20 non-fall activities it detected every fall with no false alarm. Running on a low-power microcontroller, the system indicates the feasibility of privacy-preserving on-device fall detection, while validation with older adults and in real living environments remains necessary.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Accidental FallsRadarHumansConvolutional Neural NetworksAlgorithms

Stichwörter der Autor:innen

edge computingelderly careensemble CNNfall detectionfrequency-modulated continuous wave radarmicrocontrollerprivacy

Autor:innen und Institutionen

  • Department of Architectural Engineering, Pukyong National University, Busan 48513, Republic of Korea.
  • Department of Architectural Engineering, Inha University, Inha-ro 100, Michuhol-gu, Incheon 22212, Republic of Korea.
  • Department of Smart City Engineering, Inha University, Incheon 22212, Republic of Korea.
  • Infineon Asia Pacific Area, Computing & Connectivity Technical Marketing Department, Infineon Technologies Korea, Gyeonggi-do 13595, Republic of Korea.
  • Infineon Asia Pacific Area, Computing & Connectivity Technical Marketing Department, Infineon Technologies Singapore, 8 Kallang Sector, Singapore 349282, Singapore.

ORCID-Profile: Ju-Hong Oh, Ji-Hyoung Kim, Eui-Jong Kim

Förderung

  • National Research Foundation of Korea

Zitieren

APA

Oh, J. H., Park, Y. J., Kim, S. I., Kim, J. H., Lee, J. Y., Shankar, Y., & Kim, E. J. (2026). Real-Time Fall Detection in Indoor Environments Using FMCW Radar and Lightweight Ensemble CNN on Edge Devices. Sensors. https://doi.org/10.3390/s26196189

Vancouver

Oh JH, Park YJ, Kim SI, Kim JH, Lee JY, Shankar Y, et al. Real-Time Fall Detection in Indoor Environments Using FMCW Radar and Lightweight Ensemble CNN on Edge Devices. Sensors. 2026. doi:10.3390/s26196189

BibTeX
@article{Oh2026,
  author = {Oh, Ju-Hong and Park, Young-Joon and Kim, Seon-In and Kim, Ji-Hyoung and Lee, Jin-Yong and Shankar, Yogesh and Kim, Eui-Jong},
  title = {Real-Time Fall Detection in Indoor Environments Using FMCW Radar and Lightweight Ensemble CNN on Edge Devices},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26196189}
}
Kostenlos starten →