AI-Based Driver Health and Drowsiness Risk Prediction System Using Vision and Heart Rate Monitoring
Interdisciplinary Journal of AI, Machine Learning & Data Science · 23.05.2026 · 1 (2) · e011
DOI: 10.66261/e8r4nz32 ↗Kurz gefasst
Fachartikel in der Zeitschrift Interdisciplinary Journal of AI, Machine Learning & Data Science, online erschienen am 23.05.2026. Verfasst von Paul Francis S und 3 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Driver fatigue and sudden physiological health deterioration together account for nearly a third of fatal road accidents worldwide, yet most deployed monitoring solutions address only one of these two risk categories. This paper describes a real-time, multimodal driver safety system that combines camera-based Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR) analysis with continuous physiological telemetry from a commercially available Bluetooth Low Energy (BLE) smart watch. A weighted soft-voting ensemble of a Random Forest classifier (weight 0.45) and a Gradient Boosting classifier (weight 0.55), trained on a 2,000-sample physiologically calibrated synthetic dataset, classifies driver state into three distinct risk levels — NORMAL, WARNING, and CRITICAL — with an overall accuracy of 94.2% and an area under the ROC curve of 0.987. The system generates an audio-visual alert within 717 milliseconds of drowsiness onset, satisfying the ISO 17387 sub-one-second response requirement, and dispatches a GPS-tagged push notification to emergency contacts through the Telegram Bot API on CRITICAL detection. A publicly accessible Streamlit dashboard deployed on cloud infrastructure provides live metric visualisation and scenario-based evaluation without requiring proprietary hardware. Total hardware cost is below INR 3,000.
Zitieren
APA
S, P. F., N, S., Sangeet, S., & R, P. (2026). AI-Based Driver Health and Drowsiness Risk Prediction System Using Vision and Heart Rate Monitoring. Interdisciplinary Journal of AI, Machine Learning & Data Science, 1(2), e011. https://doi.org/10.66261/e8r4nz32
Vancouver
S PF, N S, Sangeet S, R P. AI-Based Driver Health and Drowsiness Risk Prediction System Using Vision and Heart Rate Monitoring. Interdisciplinary Journal of AI, Machine Learning & Data Science. 2026;1(2):e011. doi:10.66261/e8r4nz32
BibTeX
@article{S2026,
author = {S, Paul Francis and N, Surendhar and Sangeet, Sunaina and R, Priyanga},
title = {AI-Based Driver Health and Drowsiness Risk Prediction System Using Vision and Heart Rate Monitoring},
journal = {Interdisciplinary Journal of AI, Machine Learning & Data Science},
year = {2026},
volume = {1},
number = {2},
pages = {e011},
doi = {10.66261/e8r4nz32}
}
EUVIMED