Remote Blood Pressure Measurement Through Facial PPG Signals
Bibliographic record
Abstract
Blood pressure (BP) is a measure of the force exerted by blood against the walls of arteries as the heart pumps it throughout the body. Today, isolated patients require regular and precise blood pressure measurements. The current sphygmomanometers demand a contact-based measurement setup using cuffs, which increases the risk of infection and skin sensitivity. The dataset comprises videos of 142 participants engaged in three activities. These activities were recorded using an iPhone 11 camera mounted on a tripod, and the videos underwent preprocessing techniques that includes background removal, face detection, selection of region of interest (ROI), and isolation of RGB channels. Motion artifacts removal is done by Richardson Lucy Algorithm - a blind deconvolution method which restores the image with high PSNR, BRISQUE score and edge sharpness. Extraction of ROI by UNET segmentation is done using rectangular shaped mask which has given good predictions with 95.02% accuracy. For non-contact BP measurement, Photoplethysmography (PPG) signals are extracted from each channel of the video. Two parameters, Pulse Transit Time (PTT) and Pulse Amplitude Ratio (PAR), are extracted from each dicrotic notches of PPG signal. Gradient Boosting Machine algorithm estimates both systolic and diastolic pressure with a minimum Root mean square error (RMSE) of 0.09 and an accuracy mean of 99.08%, outperforming the Multiple Linear Regression, Random Forest Classifier and Support Vector Machine algorithms.
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 | 0.000 | 0.001 |
| 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 | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".