Vehicle accidents are the primary cause of fatalities worldwide. Most often, experiencing fatigue on the road leads to operator errors and behavioral lapses. Thus, there is a need to predict the cognitive state of drivers, particularly their fatigue level. Electroencephalography (EEG) has been demonstrated to be effective for monitoring changes in the human brain state and behavior. Thirty-seven subjects participated in this driving experiment and performed a perform lane-keeping task in a visual-reality environment. Three domains, namely, frequency, temporal and 2D spatial information, of EEG channel location were comprehensively considered. A 4D convolutional neural network (4D CNN) algorithm was then proposed to associate all information from the EEG signals and the changes in the human state and behavioral performance. 4D CNN achieves superior forecasting performance over 2D CNN, 3D CNN and shallow networks. The results showed a 3.82% improvement in the RMSE, a 3.45% improvement in the error rate, and a 11.98% improvement in the correlation coefficient with 4D CNN compared with 3D CNN. The 4D CNN algorithm extracts the significant theta and alpha activations in the frontal and posterior cingulate cortices under distinct fatigue levels. This work contributes to enhancing our understanding of deep learning methods in the analysis of EEG signals. We even envision that deep learning might serve as a bridge between translation neuroscience and further real-world applications.

Abstract-The class imbalance problem in machine learning occurs when certain classes are underrepresented relative to the others, leading to a learning bias toward the majority classes. To cope with the skewed class distribution, many learning methods featuring minority oversampling have been proposed, which are proved to be effective. To reduce information loss during feature space projection, this study proposes a novel oversampling algorithm, named minority oversampling in kernel adaptive subspaces (MOKAS), which exploits the invariant feature extraction capability of a kernel version of the adaptive subspace self-organizing maps. The synthetic instances are generated from well-trained subspaces and then their pre-images are reconstructed in the input space. Additionally, these instances characterize nonlinear structures present in the minority class data distribution and help the learning algorithms to counterbalance the skewed class distribution in a desirable manner. Experimental results on both real and synthetic data show that the proposed MOKAS is capable of modeling complex data distribution and outperforms a set of state-of-the-art oversampling algorithms.

Differentiable Neural Computer (DNC) has demonstrated remarkable capabilities in solving complex problems. In this paper we propose to stack an enhanced version of differentiable neural computer together to extend its learning capabilities. Firstly, we give an intuitive interpretation of DNC to explain the architectural essence and demonstrate the stacking feasibility by contrasting it with the conventional Recurrent Neural Network (RNN). Secondly, the architecture of stacked DNCs is proposed and modified for electroencephalogram (EEG) data analysis. We substitute the original Long Short-Term Memory (LSTM) network controller by a recurrent convolutional network controller and adjust the memory accessing structures for processing EEG topographic data. Thirdly, the practicability of our proposed model is verified by an open-sourced EEG dataset with the highest average accuracy achieved; then after fine-tuning the parameters, we show the minimal mean error obtained on a proprietary EEG dataset. Finally, by analyzing the behavioral characteristics of the trained stacked DNCs model, we highlight the suitableness and potential of utilizing stacked DNCs in EEG signal processing.

Kohonen's Adaptive Subspace Self-Organizing Map (ASSOM) learns several subspaces of the data where each subspace represents some invariant characteristics of the data. To deal with the imbalance classification problem, earlier we have proposed a method for oversampling the minority class using Kohonen's ASSOM. This investigation extends that study, clarifies some issues related to our earlier work, provides the algorithm for generation of the oversamples, applies the method on several benchmark data sets, and makes an application to a Brain Computer Interface (BCI) problem. First we compare the performance of our method using some benchmark data sets with several state-of-the-art methods. Finally, we apply the ASSOMbased technique to analyze a BCI based application using electroencephalogram (EEG) datasets. Our results demonstrate the effectiveness of the ASSOM-based method in dealing with imbalance classification problem.

No abstract