Embedded TinyML Approach for Fall Detection in Geriatric Care
Abdelrahman Abdou, Quentin Mascret, Dharmendra Gurve, Benoit J. Gosselin, Sridhar Krishnan · 2025
Falls are among leading causes of injuries in the elderly, especially in senior care facilities. Injuries caused by falls burden the healthcare system and are costly. Wearable monitoring devices are being developed to detect and mitigate the risk of falling. In this study, we aimed to develop an embedded TinyML algorithm for fall detection on a wrist-worn wearable. Methods: Machine learning (ML) approaches are useful in detecting falls but often use too much energy and memory to be implemented on wearable devices. We present a low energy, low memory supervised ML model based on support vector machines (SVM) and implement it on a wearable to detect falls in real-time. Results: The proposed SVM model has a falldetection accuracy of 99.7% when tested on the SiSFall Public Dataset and 96.4% on ten subjects in an simulated experimental setting. The model uses 56 temporal features extracted from data collected by a 6-axis inertial module (3-axis acceleration, 3 axis rotation) and are computed onboard a vital sign monitoring wristband device's microcontroller unit. The optimized model uses different microcontroller components (flash memory, RAM, and bus networks). The embedded ML model developed use 0.85% of the device's RAM with a latency of 131.8ms for real-time fall detection and an average of 10.4 mAh power consumption. Conclusion: Through its on-chip computing capabilities, this SVM hardware implementation to detect falls inscribes itself in the growing body of TinyML applications.