Embedded TinyML Approach for Fall Detection in Geriatric Care
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".