Mental Fatigue Monitoring using Brain Dynamics Preferences

Driver's cognitive state of mental fatigue significantly affects driving performance and more importantly public safety. Previous studies leverage the response time (RT) as the metric for mental fatigue and aim at estimating the exact value of RT using electroencephalogram (EEG) signals within a regression model. However, due to the easily corrupted EEG signals and also non-smooth RTs during data collection, regular regression methods generally suffer from poor generalization performance. Considering that human response time is the reflection of brain dynamics preference rather than a single value, a novel model called Brain Dynamic ranking (BDrank) has been proposed. BDrank could learn from brain dynamics preferences using EEG data robustly and preserve the ordering corresponding to RTs. BDrank model is based on the regularized alternative ordinal classification comparing to regular regression based practices. Furthermore, a transition matrix is introduced to characterize the reliability of each channel used in EEG data, which helps in learning brain dynamics preferences only from informative EEG channels. In order to handle large-scale EEG signals~and obtain higher generalization, an online-generalized Expectation Maximum (OnlineGEM) algorithm also has been proposed to update BDrank in an online fashion. Comprehensive empirical analysis on EEG signals from 44 participants shows that BDrank together with OnlineGEM achieves substantial improvements in reliability while simultaneously detecting possible less informative and noisy EEG channels.