Health-Radar: Noncontact Multitarget Heart Rate Variability Detection Using FMCW Radar
Bibliographic record
Abstract
Heart rate variability (HRV), indicating the variation in intervals between consecutive heartbeats, is a crucial physiological indicator of human health. However, detecting HRV using frequency-modulated continuous-wave (FMCW) radar is highly susceptible to interference from respiration, minor body movements, and environmental noise, especially in multitarget scenarios. To address these challenges, we propose the Health-Radar system, which comprises three functional modules. In the target detection module, the system accurately identifies the number and locations of targets. In the phase extraction module, the signal undergoes dc offset calibration to extract the chest displacement signals. In the heartbeat signal extraction module, we introduce Health-VMD, an adaptive parameter variational mode decomposition (VMD) method. This method optimizes the VMD parameters using an improved grasshopper optimization algorithm (GOA) and accurately extracts vital sign signals from chest displacement signals to estimate HRV. In addition, we propose a novel objective function, composed of permutation entropy, mutual information, and energy loss rate (PME), specifically designed for vital sign extraction. Experiments with multiple participants in various scenarios demonstrated that the designed system can accurately identify different targets and detect HRV with high precision. The root-mean-square error (RMSE) of the detected interbeat intervals (IBIs) is 29.72 ms, the RMSE of the standard deviation of NN intervals (SDNN) is 4.1 ms, and the RMSE of the root mean square of successive differences (RMSSD) is 18.61 ms, outperforming existing methods.
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) | 0.001 | 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".