Development of a Real-Time Driver Health Detection System Using a Smart Steering Wheel

Lee, Jae-Cheon; Liu, Hao · 2020 · Crossref

DOI: 10.36001/ijphm.2018.v9i3.2747

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 critical safety issue of traffic accidents caused by driver drowsiness and sudden cardiac events, such as arrhythmia. Motivated by statistics indicating that drowsiness contributes to significant annual fatalities and injuries, the authors propose a real-time driver health detection system integrated into a smart steering wheel. The primary objective is to monitor the driver’s physiological state continuously to detect vigilance levels and cardiac abnormalities, thereby enabling timely warnings to prevent accidents. The system hardware comprises three biological sensors, an interface circuit, a data acquisition board, and a personal computer. The sensors include pressure sensors attached to the seat belt and steering wheel to measure respiration and hand grip force, respectively; a photoplethysmogram (PPG) sensor using an LED and phototransistor to monitor blood volume changes; and electrocardiogram (ECG) probes made of conductive fiber attached to the steering wheel and seat backrest to detect heart electrical activity. The interface circuit conditions these signals, specifically filtering the ECG signal between 0.15 Hz and 4 Hz and amplifying it to remove noise. Data is processed via a 10-bit acquisition board and displayed on a graphical user interface. Due to safety risks associated with testing on drowsy drivers in real vehicles, experimental data was collected in a laboratory setting. The detection algorithms analyze the acquired signals to determine health status. Drowsiness is detected by calculating respiration rates from pressure sensor data and analyzing PPG signal peaks for heart rate and variability. The system compares these metrics against reference values; if three consecutive signals indicate drowsiness, the driver is flagged. Arrhythmia detection relies on ECG analysis, specifically identifying QRS wave peaks to calculate R-R intervals and R-wave durations. Deviations from normal ranges in these intervals indicate potential arrhythmia. In laboratory tests involving an arrhythmia patient, the system successfully identified abnormal R-R intervals and R-wave durations, confirming the occurrence of arrhythmia. The study concludes that the proposed smart steering wheel system effectively monitors driver vigilance and cardiac health in real time. The integration of multiple physiological signals enhances detection reliability, reducing false positives. While the current validation is based on laboratory data, the authors suggest that further testing with real-world driving data will improve the accuracy of the arrhythmia detection algorithm. This technology represents a step toward advanced prognostic health management for drivers, contributing to the intellectualization of vehicles and improved traffic safety.

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.

Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• drowsiness detection algorithms

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: validation psychometrics, tool software