16 December 2022 in IEEE Sensors Journal
Accurate estimation of driver vigilance state is important for improving driving safety and preventing accidents. Previous studies have extensively investigated the potentials of driving performance measures (e.g., lane position, steering wheel angle, lateral acceleration) and eye movement measures (e.g., glance frequency, duration) on driver’s vigilance state estimation. However, the change of these measures may be caused by various factors. Therefore, comprehensively involving more direct measures (e.g., drivers’ EEG response) is expected to increase the vigilance estimation performance. This study comprehensively uses measures across different functional domains (i.e., driving performance, eye movement, EEG) to establish an estimation model of driver vigilance state. Twenty participants were assigned a 2-hour sustained-attention driving task in a simulator, in which they followed a lead car closely. According to their brake reaction times to the brake signal of the lead vehicle, their vigilance states were divided into three levels (i.e., low, medium, high). A logistic regression model that estimates drivers’ vigilance state level based on multi-source data was established. This model is a promising approach to driver states detection and reveals the factors that should be considered in subsequent model development processes. It can be combined with driver vigilance arousal methods to improve driving safety.
14 November 2024 in IEEE Sensors Journal
Decline of driver vigilance is a critical factor of fatal railway accidents. To prevent accidents induced by driver vigilance decline, intervention strategies are needed. The aim of this study is to investigate if cool stimulation intervention (CS-intervention) can be used as a countermeasure for vigilance decline of high-speed railway (HSR) driver. The CS-intervention strategy was tested in an HSR driving simulator with 40 healthy participants with vigilance decline. Each participant completed two monotonous driving tasks: one without stimulation intervention (NO-intervention) and one with 20°C cool stimulation intervention (CS-intervention). Self-reported vigilance was assessed by using the Karolinska Sleepiness Scale (KSS), and reaction time (RT) was used to estimate the objective vigilance. Eye movement data, electrocardiogram (ECG), and electroencephalogram (EEG) signals were collected to investigate the potential arousing effects of CS-intervention. The CS-intervention can effectively awake drivers to reduce their reaction times and KSS. The driver’s percentage of eye closure (PERCLOS) decreased while driving with CS-intervention. The high-frequency part of EEG signals is active, while the permutation entropy (PE) value in the frontal lobe is attenuated. The connectivity between brain lobes is enhanced. The physiological responses also prove the effectiveness of CS-intervention. This study indicate that CS-intervention is an effective strategy to alleviate fatigue and maintain vigilance. Given that CS-intervention can effectively counteract vigilance decline, the findings in this study are expected to provide evidences for the improvement of HSR driving safety.
5 August 2024 in IEEE Sensors Journal
Accurately estimating high-speed rail (HSR) drivers’ vigilance is crucial for improving operational safety. Existing studies primarily focus on fatigue as the main cause for the decrement in vigilance. However, vigilance is a complex status affected by multiple factors. Therefore, we propose a novel method to evaluate drivers’ vigilance by considering both fatigue and mind-wandering. Firstly, we analyze manifestations of HSR drivers’ vigilance in terms of fatigue and mind-wandering. The results demonstrate that both fatigue and mind-wandering can significantly reduce vigilance, with drivers experiencing mind-wandering exhibiting longer reaction times. Secondly, we construct a two-dimensional model to evaluate HSR drivers’ vigilance with multi-modal signals. The electroencephalogram (EEG), electrocardiogram (ECG), and eye movement features are fused with a convolutional neural network (CNN), and the fused features are then input into a long short-term memory (LSTM) network to obtain estimation results. To address the issue of imbalanced samples affecting model performance, a Wasserstein deep convolutional generative adversarial network (W-DCGAN) is employed to augment the training data. The average accuracy of our model is 88.75%, with a macro-F1 score of 0.89. The testing accuracies in detecting low vigilance caused by fatigue, mind-wandering, or a combination of both are 82.00%, 85.00%, and 94.00% respectively. These results demonstrate that our proposed method can effectively evaluate HSR drivers’ vigilance from the perspectives of fatigue and mind-wandering.
4 November 2024 in IEEE Sensors Journal
Objective : Long monotonous driving tasks can induce driver fatigue, significantly reducing vigilance and threatening the safety of high-speed train operations. Despite the importance of addressing this issue, effective interventions to mitigate driver fatigue in the context of high-speed railway systems remain a challenge. This study aims to examine the effects of three tactile intervention strategies (transcutaneous electrical acupoint stimulation, thermal stimulation, and vibration stimulation) on alleviating driver fatigue. Methods : A high-speed train simulator was used to conduct experiments with subjects. Each participant was required to complete four driving tasks: one without any intervention and three with each of the aforementioned tactile interventions when experiencing fatigue. Physiological metrics such as reaction time, electrocardiogram (ECG), and electroencephalogram (EEG) were collected to assess driver vigilance. Findings : The results revealed that thermal and vibration stimulations effectively reduced reaction times (TS = 1.11s, VS = 1.09s, no-intervention = 1.12s) and slowed down the fatigue process. Drivers exhibited higher vigilance levels during these interventions, as reflected in improved ECG and EEG features. For example, the high-frequency energy of the EEG signal increases during the stimulation compared to before the stimulation. However, transcutaneous electrical acupoint stimulation did not show significant effects on fatigue reduction. Novelty : This study contributes to the literature by providing evidences to support that appropriate tactile interventions, particularly thermal and vibration stimulations, can effectively mitigate driver fatigue and improve vigilance levels. These findings offer practical insights for enhancing the safety of high-speed railway operations by minimizing risks associated with driver fatigue.