Paperdoi:10.1109/AICAS59952.2024.10595972
Driving Towards Safety: Online PPG-based Drowsiness Detection with TCNs
IEEE AICAS 2024
TL;DR
TCN on PPG from steering-wheel sensors; 16 subjects, LOSO: 77.03% accuracy, FPR 8.21%, FNR 13.92%; quantised model on a ULP SoC: 4.8 ms, 117 µJ per inference.
- Form factor: steering wheel (finger/palm contact PPG)
Abstract
Increasing driver and driving safety is one of the most compelling needs of the automotive industry, both in terms of economic and social impact. Current approaches primarily focus on analyzing unsafe vehicle behavior, often overlooking the critical factor of the driver’s physiological state. This paper introduces a novel solution leveraging temporal convolutional networks (TCNs) for unobtrusive driver drowsiness detection based on photoplethys-mography (PPG). PPG data is collected seamlessly using sensors integrated into the steering wheel, providing a non-invasive assessment of the autonomic nervous system (ANS). We benchmarked our model on 16 subjects using a leave-one-subject-out (LOSO) cross-validation scheme, achieving an average accuracy of 77.03%. The model also shows good performance in avoiding false alarms when the driver is alert with a false positive ratio of just 8.21% and correctly detecting drowsiness with a low false negative ratio of 13.92%, improving the state-of-the-art for PPG based approaches. A quantized version of the model is deployed on a commercial ultra-low-power (ULP) system-on-a-chip (SoC), demonstrating real-world feasibility with an inference time of 4.8 ms and energy per inference of 117 μJ. This work represents a significant step towards unobtrusive, real-time physiological monitoring in driving environments, contributing to the ongoing efforts to improve driver’s safety.
Verbatim from Semantic Scholar (opens in a new tab) · Abstract via Semantic Scholar; © the authors/publisher
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Keywords
Models
How it works
Cite this paper
Rapa, P. M., Orlandi, M., Amidei, A., Burrello, A., Rabbeni, R., Pavan, P., Benini, L., & Benatti, S. (2024). Driving Towards Safety: Online PPG-based Drowsiness Detection with TCNs. IEEE AICAS 2024. https://doi.org/10.1109/AICAS59952.2024.10595972
Rapa, Pierangelo Maria, Mattia Orlandi, Andrea Amidei, Alessio Burrello, Roberto Rabbeni, Paolo Pavan, Luca Benini, and Simone Benatti. 2024. "Driving Towards Safety: Online PPG-based Drowsiness Detection with TCNs." IEEE AICAS 2024. https://doi.org/10.1109/AICAS59952.2024.10595972.
Rapa, P. M., Orlandi, M., Amidei, A., Burrello, A., Rabbeni, R., Pavan, P., Benini, L. and Benatti, S. (2024) 'Driving Towards Safety: Online PPG-based Drowsiness Detection with TCNs', IEEE AICAS 2024. doi: 10.1109/AICAS59952.2024.10595972.
Rapa, Pierangelo Maria, et al. "Driving Towards Safety: Online PPG-based Drowsiness Detection with TCNs." IEEE AICAS 2024, 2024. https://doi.org/10.1109/AICAS59952.2024.10595972.
P. M. Rapa et al., "Driving Towards Safety: Online PPG-based Drowsiness Detection with TCNs," IEEE AICAS 2024, 2024, doi: 10.1109/AICAS59952.2024.10595972.
@article{rapa2024driving,
title = {{Driving Towards Safety: Online PPG-based Drowsiness Detection with TCNs}},
author = {Rapa, Pierangelo Maria and Orlandi, Mattia and Amidei, Andrea and Burrello, Alessio and Rabbeni, Roberto and Pavan, Paolo and Benini, Luca and Benatti, Simone},
year = {2024},
journal = {IEEE AICAS 2024},
doi = {10.1109/AICAS59952.2024.10595972}
}Added to the ChatPPG research hub