Towards unsupervised coherence-based assessment of ECG quality in different posture and movement conditions
Bibliographic record
Abstract
Electrocardiogram (ECG) signals are one of the most common and important physiological signals for assessing cardiovascular health. The rapid advancement in wearable technology has opened new avenues for continuous monitoring of various cardiovascular diseases (CVDs) in non-clinical settings. At the same time, the amount of data available for analysis due to these unobtrusive sensors has increased considerably. Automated processing and extraction of useful features from such huge amounts of data requires the recorded bio-signals to have high signal-to-noise ratio (SNR). Hence, researchers have proposed different metrics to assess the quality of single- and multi-lead ECG signals. In this ongoing study, we focus on using spectral coherence to analyse the quality of simultaneously measured ECG signals recorded from two locations on the body. Keeping in mind the use of wearable devices for continuous monitoring throughout the day, we designed the protocol for this study to include collection of data in scenarios involving sitting, standing and walking in upright and slouched postures. The latter are common in elderly adults and also for normal people with back problems. The results show that spectral coherence correlates well with the expected level of noise due to activity, and provides better insight into the quality of the ECG signals as compared to an SNR index calculated using the ratio of energies in different frequency bands of the signal.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".