A Portable Multi-Modal Cushion for Continuous Monitoring of a Driver’s Vital Signs
DOI: 10.3390/s23084002
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the growing need for robust driver monitoring systems in vehicles with increasing automation levels. As drivers must remain capable of intervening at any moment, monitoring for drowsiness, stress, and acute physiological events like heart attacks or strokes is critical, particularly for aging populations. The authors present a portable, multi-modal cushion designed to continuously monitor a driver’s vital signs—specifically heart rate (HR) and respiratory rate (RR)—unobtrusively. The device aims to overcome limitations of existing systems, such as privacy concerns with cameras, certification issues with seat-embedded sensors, and reliance on specific hand contact with steering wheel sensors. The proposed system integrates four measurement modalities into four redundant sensor units (4xU sensors) embedded in a cushion: capacitive electrocardiography (cECG), reflective photoplethysmography (rPPG), magnetic induction measurement (MIM), and seismocardiography (SCG). This redundancy ensures coverage across different seating positions and mitigates signal loss due to motion artifacts. The hardware includes active electrodes for cECG, infrared LEDs and photodiodes for rPPG, a Colpitts oscillator with a planar coil for MIM, and an accelerometer for SCG. These sensors feed data to a controller box equipped with an analog front-end for cECG processing and a microcontroller for digital signal acquisition. The system samples data at 128 Hz and stores it on an SD card or transmits it via USB. The cushion was evaluated in a proof-of-concept study involving 20 healthy participants (aged 19–60) using a driving simulator for approximately 25 minutes. Participants performed standard driving tasks and controlled movements to simulate real-world conditions. The cushion’s measurements were compared against gold-standard conductive ECG and impedance pneumography. The results demonstrated high accuracy for heart rate estimation, with over 70% of measurements meeting medical-grade standards according to IEC 60601-2-27. Respiratory rate measurements showed fair quality, with approximately 30% of readings having errors below 2 breaths per minute. The study also indicated that the cECG could capture morphological changes useful for broader cardiovascular diagnosis. The significance of this work lies in the development of a universal, privacy-preserving monitoring tool that does not require direct skin contact or specific user positioning. The multi-modal approach allows for the detection of drowsiness and stress through heart rate and breathing variability, as well as the early prediction of cardiovascular diseases. To facilitate further research, the authors released the recorded data as the publicly available UnoVis dataset, marking the first such dataset for multi-modal unobtrusive sensors in a driving scenario. This contribution supports the development of sensor fusion algorithms and machine learning models for in-vehicle health monitoring.
Key finding
The multi-modal cushion achieved medical-grade accuracy for heart rate estimation in over 70% of measurements and maintained respiratory rate errors below two breaths per minute in approximately 30% of cases during simulated driving.
Methodology
simulator
Sample size: 20
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via topic_sweep_doaj on 2026-06-01.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | — | — | — | 1 | 2026-06-01 |
| archive | success | openalex | — | — | 5 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-04 |
| chunk | success | chunk | — | — | 1 | 2026-06-04 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-04 |
| enrich | success | — | — | — | 1 | 2026-06-01 |
| promote | success | — | — | — | 1 | 2026-06-04 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | partial | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified_with_issues.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: physiological data
- Methodological Resource: tool software, validation psychometrics