Continuous Well-Being assessment and actionable feedback using explainable regression for Edge-Enabled wearable devices
Bibliographic record
Abstract
As the utilization of wearable devices in health monitoring continues to expand, there is a pressing need for intelligent system designs that can not only collect physiological data but also transform it into results that are comprehensible, meaningful, and practical. The application of current models in real-world digital well-being measurement is limited by their inability to provide continuous feedback or personalized recommendations. In the paper, we propose a regression-based model that is both technically stable and interpretable, and that is used to estimate the well-being score using data from ubiquitous sensors. The system employs a Ridge Regression model with counterfactual reasoning to provide high-fidelity score predictions (R 2 = 0.9996, MSE = 0.0275, RMSE = 0.166), as well as human-interpretable behavioral advice. The well-being score is expected to fall within the range of 34 to 80, with a higher score indicating exceptional well-being and a lower value indicating a deterioration in physical or mental status. One of the decision statuses is assigned to each result. Scores of 75 and more are reasons to continue the same behaviour and strengthen the positive routines, and scores of 40 and less are signs of critical levels of well-being. It is better to take some rest, practice mindfulness, or find clinical support. This interpretability degree will allow real-time and personalized decision support to both the user and the linked wearable systems. The proposed framework will be designed to operate in wearable technologies with minimal power and be deployed on-device, in contrast to other literature works that are either not transparent or do not produce actionable feedback. In contrast to other previous works that were not transparent or rationally based, this one involves precise predictions, interpretability, and personalized guidelines. It offers a comprehensive solution for smart health monitoring by converting sensor data into meaningful scores and proactive well-being management recommendations.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".