Brain activity associated with attention sustained on the task of safe driving has received considerable attention recently in many neurophysiological studies. Those investigations have also accurately estimated shifts in drivers' levels of arousal, fatigue, and vigilance, as evidenced by variations in their task performance, by evaluating electroencephalographic (EEG) changes. However, monitoring the neurophysiological activities of automobile drivers poses a major measurement challenge when using a laboratory-oriented biosensor technology. This work presents a novel dry EEG sensor based mobile wireless EEG system (referred to herein as Mindo) to monitor in real time a driver's vigilance status in order to link the fluctuation of driving performance with changes in brain activities. The proposed Mindo system incorporates the use of a wireless and wearable EEG device to record EEG signals from hairy regions of the driver conveniently. Additionally, the proposed system can process EEG recordings and translate them into the vigilance level. The study compares the system performance between different regression models. Moreover, the proposed system is implemented using JAVA programming language as a mobile application for online analysis. A case study involving 15 study participants assigned a 90 min sustained-attention driving task in an immersive virtual driving environment demonstrates the reliability of the proposed system. Consistent with previous studies, power spectral analysis results confirm that the EEG activities correlate well with the variations in vigilance. Furthermore, the proposed system demonstrated the feasibility of predicting the driver's vigilance in real time.

This paper proposes a generalized prediction system called a recurrent self-evolving fuzzy neural network (RSEFNN) that employs an on-line gradient descent learning rule to address the electroencephalography (EEG) regression problem in brain dynamics for driving fatigue. The cognitive states of drivers significantly affect driving safety; in particular, fatigue driving, or drowsy driving, endangers both the individual and the public. For this reason, the development of brain-computer interfaces (BCIs) that can identify drowsy driving states is a crucial and urgent topic of study. Many EEG-based BCIs have been developed as artificial auxiliary systems for use in various practical applications because of the benefits of measuring EEG signals. In the literature, the efficacy of EEG-based BCIs in recognition tasks has been limited by low resolutions. The system proposed in this paper represents the first attempt to use the recurrent fuzzy neural network (RFNN) architecture to increase adaptability in realistic EEG applications to overcome this bottleneck. This paper further analyzes brain dynamics in a simulated car driving task in a virtual-reality environment. The proposed RSEFNN model is evaluated using the generalized cross-subject approach, and the results indicate that the RSEFNN is superior to competing models regardless of the use of recurrent or nonrecurrent structures.

A generalized EEG-based Neural Fuzzy system to predict driver's drowsiness was proposed in this study. Driver's drowsy state monitoring system has been implicated as a causal factor for the safety driving issue, especially when the driver fell asleep or distracted in driving. However, the difficulties in developing such a system are lack of significant index for detecting the driver's drowsy state in real-time and the interference of the complicated noise in a realistic and dynamic driving environment. In our past studies, we found that the electroencephalogram (EEG) power spectrum changes were highly correlated with the driver's behavior performance especially the occipital component. Different from presented subject-dependent drowsy state monitor systems, whose system performance may decrease rapidly when different subject applies with the drowsiness detection model constructed by others, in this study, we proposed a generalized EEG-based Self-organizing Neural Fuzzy system to monitor and predict the driver's drowsy state with the occipital area. Two drowsiness prediction models, subject-dependent and generalized cross-subject predictors, were investigated in this study for system performance analysis. Correlation coefficients and root mean square errors are showed as the experimental results and interpreted the performances of the proposed system significantly better than using other traditional Neural Networks ( p -value <;0.038). Besides, the proposed EEG-based Self-organizing Neural Fuzzy system can be generalized and applied in the subjects' independent sessions. This unique advantage can be widely used in the real-life applications.

Electroencephalogram (EEG) signals are frequently used in brain-computer interfaces (BC!s), but they are easily contaminated by artifacts and noise, so preprocessing must be done before they are fed into a machine learning algorithm for classification or regression. Spatial filters have been widely used to increase the signal-to-noise ratio of EEG for BC! classification problems, but their applications in BC! regression problems have been very limited. This paper proposes two common spatial pattern (CSP) filters for EEG-based regression problems in BC!, which are extended from the CSP filter for classification, by using fuzzy sets. Experimental results on EEG-based response speed estimation from a large-scale study, which collected 143 sessions of sustained-attention psychomotor vigilance task data from 17 subjects during a 5-month period, demonstrate that the two proposed spatial filters can significantly increase the EEG signal quality. When used in LASSO and k-nearest neighbors regression for user response speed estimation, the spatial filters can reduce the root-mean-square estimation error by 10.02-19.77%, and at the same time increase the correlation to the true response speed by 19.39-86.47%.

Electroencephalography (EEG) signals are often contaminated with artifacts. It is imperative to develop a practical and reliable artifact removal method to prevent the misinterpretation of neural signals and the underperformance of brain-computer interfaces. Based on the U-Net architecture, we developed a new artifact removal model, IC-U-Net, for removing pervasive EEG artifacts and reconstructing brain signals. IC-U-Net was trained using mixtures of brain and non-brain components decomposed by independent component analysis. It uses an ensemble of loss functions to model complex signal fluctuations in EEG recordings. The effectiveness of the proposed method in recovering brain activities and removing various artifacts (e.g., eye blinks/movements, muscle activities, and line/channel noise) was demonstrated in a simulation study and four real-world EEG experiments. IC-U-Net can reconstruct a multi-channel EEG signal and is applicable to most artifact types, offering a promising end-to-end solution for automatically removing artifacts from EEG recordings. It also meets the increasing need to image natural brain dynamics in a mobile setting. The code and pre-trained IC-U-Net model are available at https://github.com/roseDwayane/AIEEG.