Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Respiratory rate is a vital physiological signal that may be useful for a multitude of clinical applications, especially if measured in the wild rather than controlled settings. In-the-wild respiratory rate monitoring is currently done using dedicated chest band sensors, but these devices are specialized, expensive and cumbersome to wear day after day. While recent works have proposed using smartwatch based accelerometer and gyroscope data for respiratory rate monitoring, current methods are unreliable and inaccurate in the presence of motion and have therefore only been applied in controlled or low-motion settings. Thus, measuring respiratory rate in the wild remains a challenge. We observe that for many applications, having fewer accurate readings is better than having more, less accurate readings. Based on this, we develop WearBreathing, a novel system for respiratory rate monitoring. WearBreathing consists of a machine learning based filter that detects and rejects sensor data that are not suitable for respiratory rate extraction and a convolutional neural network model for extracting respiratory rate from accelerometer and gyroscope data. Using a diverse, out-of-the-lab dataset that we collected, we show that WearBreathing has a 2.5 to 5.8 times lower mean absolute error (MAE) than existing approaches. We show that WearBreathing is tunable and by changing a single threshold value, it can, for example, deliver a reading every 50 seconds with a MAE of 2.05 breaths/min or a reading every 5 minutes with an MAE of 1.09 breaths/min. Finally, we evaluate power consumption and find that with some power saving measures, WearBreathing can run on a smartwatch while providing a full day's worth of battery life.
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.
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) | 0.000 | 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 | 0.000 |
| Open science | 0.001 | 0.001 |
| 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 it