Zizheng Guo

TL;DR: A system to detect vigilance level using not only a driver's EEG signals but also driving contexts as inputs is proposed, and a support vector machine with particle swarm optimization methods are combined to improve classification accuracy.

TL;DR: The underlying neurological mechanisms of how mental fatigue impaired response inhibition were revealed and it was found that participants in the driving group reported higher levels of mental fatigue and had a higher percentage of eye closure and larger lateral deviations from their lane positions, which indicated there was effective manipulation ofmental fatigue through a prolonged simulated driving task.

TL;DR: The results suggest that mental fatigue can modulate the higher-level cognitive processes, in terms of less attentional resources allocated to the random stimuli, which leads to decreased speed in information evaluating and decision making against the stimuli.

TL;DR: The findings demonstrated that the hazard anticipatory activity of a driver could be recognized with EEG data as input, and SVM could detect the anticipatoryactivity of the driver to a potential hazard in a timely manner with an accuracy of 81%.

TL;DR: The results suggested that better abilities in visual multiobject tracking, working memory, task switching, and cognitive flexibility were correlated with higher safety evaluation score and shorter train delay time, which supports the recommendation that cognitive abilities investigated as predictors of safety performance could be useful for the selection and training of HSR dispatchers.