Real-Time Fall Detection in Indoor Environments Using FMCW Radar and Lightweight Ensemble CNN on Edge Devices
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.
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)
Stichwörter der Autor:innen
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}
}
EUVIMED