Wrist-to-Back Signal Reconstruction for Real-World Gait Monitoring via Frequency-Domain Modelling
Bibliographic record
Abstract
Wearable accelerometers are commonly used for gait analysis in healthcare and rehabilitation, providing objective, continuous, real-world data. While lower-back sensors are widely used for capturing gait features, however, their long-term use is limited by discomfort and impracticality. Wrist-worn sensors are more user-friendly but less accurate for specific gait metrics. This study presents a novel, proof-ofconcept method to reconstruct lower-back accelerometer signals using only wrist-based data, via a frequency-domain transfer function approach. Using a two-day naturalistic, freeliving dataset from multiple participants wearing accelerometers on both the wrist and lower back, gait bouts were detected and clustered to extract representative gait cycles. A spectral transfer function modelled the wrist-lower back relationship. The proposed method achieved high intraindividual accuracy (Pearson correlation <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$=0.9141$</tex>; RMSE =0.4351) and maintained robust performance across individuals (mean Pearson correlation <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$=0.827$</tex>; RMSE <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$=0.604$</tex>), demonstrating its potential to generalize across demographic variability. Unlike prior deep learning-based models, our approach is interpretable, computationally efficient, and does not require large training datasets, making it well-suited for real-world applications. These findings highlight the feasibility of replacing Lower back sensors with wrist-worn devices, making it suitable for long-term, passive gait monitoring in clinical and consumer health 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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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 teacher head, 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".