In-Ear Audio Wearable: Measurement of Heart and Breathing Rates for Health and Safety Monitoring
Bibliographic record
Abstract
OBJECTIVE: This paper examines the integration of a noninvasive vital sign monitoring feature into the workers' hearing protection devices (HPDs) by using a microphone positioned within the earcanal under the HPD. METHODS: 25 test-subjects were asked to breathe at various rhythms and intensities and these realistic sound events were recorded in the earcanal. Digital signal processing algorithms were then developed to assess heart and breathing rates. Finally, to test the robustness of theses algorithms in noisy work environments, industrial noise was added to the in-ear recorded signals and an adaptive denoising filter was used. RESULTS: The developed algorithms show an absolute mean error of 4.3 beats per minute (BPM) and 2.7 cycles per minute (CPM). The mean difference estimate is -0.44 BPM with a limit of agreement (LoA) interval of -14.3 to 13.4 BPM and 2.40 CPM with a LoA interval of -2.62 to 7.48 CPM. Excellent denoising is achieved with the adaptive filter, able to cope with ambient sound pressure levels of up to 110 dB SPL, resulting in a small error for heart rate detection, but a much larger error for breathing rate detection. CONCLUSION: Extraction of the heart and breathing rates from an acoustical measurement in the occluded earcanal under an HPD is possible and can even be conducted in the presence of a high level of ambient noise. SIGNIFICANCE: This proof of concept enables the development of a wide range of noninvasive health and safety monitoring audio wearables for industrial workplaces and life-critical applications where HPDs are used.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".