Key result
Machine learning using physiological signals predicts mild sleep deprivation with ~99% accuracy, driven by electrodermal activity.
Why the study?
Long periods without engaging in a non-driving-related task in conditionally automated vehicles can reduce vigilance, prompting evaluation of driver fatigue prediction using physiological signals and machine learning.
Can machine learning using physiological signals accurately predict driver fatigue and sleepiness in young drivers during conditionally automated driving?
Observational (n=63)
Can machine learning using physiological signals accurately predict driver fatigue and sleepiness in young drivers during conditionally automated driving?
Machine learning models using physiological signals, particularly electrodermal activity, can accurately predict mild sleep deprivation and sleepiness in drivers of conditionally automated vehicles.
Answers are grounded in this paper and cite their sources.
May aid real-time vigilance monitoring in automated vehicles; hypothesis-generating pending larger real-world validation.
• Mild sleep deprivation and sleepiness were predicted with 99% and 73%-accuracy. • Driver state between rural and urban scenarios was distinguished at 85%-accuracy. • The segmentation increased the accuracy of machine learning classifiers. • Electrodermal activity was the most predictive signal. Conditionally automated vehicles (Level 3 SAE) are emerging on the roads, but long periods without engaging in a non-driving-related task can reduce drivers’ vigilance. This study aims to determine whether driver fatigue can be accurately predicted using physiological signals and machine learning (ML) techniques in such a context. 63 young drivers completed two separate conditional automated drives of 30 min each, in either a rural or a urban area. Half of them had been mildly sleep-deprived the previous night (slept less than six hours). Electrocardiogram (ECG), electrodermal activity (EDA), and respiration were collected, along with subjective measures of sleepiness and affective state. Using ML, sleep deprivation, driving environment, and sleepiness could be predicted from physiological features with an accuracy of 99%, 85%, and 73% respectively. Signal segmentation increased model accuracy, and EDA features were the most predictive. The differences between the results obtained from statistical analyses of sleepiness measures and the accuracy achieved by ML models are discussed. The results of this empirical study indicate that even mild sleep deprivation affects the physiological state of drivers, which can have serious consequences when combined with long periods of inactivity. Car manufacturers and researchers should take this into account when designing intelligent systems capable of providing drivers with appropriate warnings before a critical situation arises.
No takes yet. Share an insight, caveat, or question.
Meteier et al. (2024) conducted an observational in Driver fatigue and sleepiness (n=63). Machine learning using physiological signals (ECG, EDA, respiration) was evaluated on Prediction accuracy of sleep deprivation, driving environment, and sleepiness. Machine learning models using physiological signals, particularly electrodermal activity, predicted mild sleep deprivation, driving environment, and sleepiness with 99%, 85%, and 73% accuracy.
Synapse has enriched 10 related papers. Consider them for comparative context: