EEG data analysis with stacked differentiable neural computers

Comparative study of rainfall prediction based on different decomposition methods of VMD

Rainfall forecasting is an important means for macro-control of water resources and prevention of future disasters. In order to achieve a more accurate prediction effect, this paper analyzes the applicability of the "full decomposition" and "stepwise decomposition" of the VMD (Variational mode decomposition) algorithm to the actual prediction service; The MAVOA (Modified African Vultures Optimization Algorithm) improved by Tent chaotic mapping is selected; and the DNC (Differentiable Neural Computer), which combines the advantages of recurrent neural networks and computational processing, is applied to the forecasting. The different VMD decompositions of the MAVOA-DNC combination together with other comparative models are applied to example predictions at four sites in the Huaihe River Basin. The results show that SMFSD (Single-model Fully stepwise decomposition) is the most effective, and the average Root Mean Square Error (RMSE) of the forecasts for the four sites of SMFSD-MAVOA-DNC is 9.02, the average Mean Absolute Error (MAE) of 7.13, and the average Nash-Sutcliffe Efficiency (NSE) of 0.94. Compared with the traditional VMD full decomposition, the RMSE is reduced by 7.42, the MAE is reduced by 4.83, and the NSE is increased by 0.05; the best forecasting results are obtained compared with other coupled models.

A Driving Performance Forecasting System Based on Brain Dynamic State Analysis Using 4-D Convolutional Neural Networks

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 2-D spatial information, of the EEG channel location were comprehensively considered. A 4-D convolutional neural-network (4-D CNN) algorithm was then proposed to associate all information from the EEG signals and the changes in the human state and behavioral performance. A 4-D CNN achieves superior forecasting performance over 2-D CNN, 3-D CNN, and shallow networks. The results showed a 3.82% improvement in the root mean-square error, a 3.45% improvement in the error rate, and a 11.98% improvement in the correlation coefficient with 4-D CNN compared with 3-D CNN. The 4-D 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.

A Review on Signal Processing Approaches to Reduce Calibration Time in EEG-Based Brain-Computer Interface

In an electroencephalogram- (EEG-) based brain–computer interface (BCI), a subject can directly communicate with an electronic device using his EEG signals in a safe and convenient way. However, the sensitivity to noise/artifact and the non-stationarity of EEG signals result in high inter-subject/session variability. Therefore, each subject usually spends long and tedious calibration time in building a subject-specific classifier. To solve this problem, we review existing signal processing approaches, including transfer learning (TL), semi-supervised learning (SSL), and a combination of TL and SSL. Cross-subject TL can transfer amounts of labeled samples from different source subjects for the target subject. Moreover, Cross-session/task/device TL can reduce the calibration time of the subject for the target session, task, or device by importing the labeled samples from the source sessions, tasks, or devices. SSL simultaneously utilizes the labeled and unlabeled samples from the target subject. The combination of TL and SSL can take advantage of each other. For each kind of signal processing approaches, we introduce their concepts and representative methods. The experimental results show that TL, SSL, and their combination can obtain good classification performance by effectively utilizing the samples available. In the end, we draw a conclusion and point to research directions in the future.

Vision-Guided MPC for Robotic Path Following Using Learned Memory-Augmented Model

The control of the interaction between the robot and environment, following a predefined geometric surface path with high accuracy, is a fundamental problem for contact-rich tasks such as machining, polishing, or grinding. Flexible path-following control presents numerous applications in emerging industry fields such as disassembly and recycling, where the control system must adapt to a range of dissimilar object classes, where the properties of the environment are uncertain. We present an end-to-end framework for trajectory-independent robotic path following for contact-rich tasks in the presence of parametric uncertainties. We formulate a combination of model predictive control with image-based path planning and real-time visual feedback, based on a learned state-space dynamic model. For modeling the dynamics of the robot-environment system during contact, we introduce the application of the differentiable neural computer, a type of memory augmented neural network (MANN). Although MANNs have been as yet unexplored in a control context, we demonstrate a reduction in RMS error of ∼21.0% compared with an equivalent Long Short-Term Memory (LSTM) architecture. Our framework was validated in simulation, demonstrating the ability to generalize to materials previously unseen in the training dataset.

A Unified Analytical Framework With Multiple fNIRS Features for Mental Workload Assessment in the Prefrontal Cortex

Knowing the actual level of mental workload is important to ensure the efficacy of brain-computer interface (BCI) based cognitive training. Extracting signals from limited area of a brain region might not reveal the actual information. In this study, a functional near-infrared spectroscopy (fNIRS) device equipped with multi-channel and multi-distance measurement capability was employed for the development of an analytical framework to assess mental workload in the prefrontal cortex (PFC). In addition to the conventional features, e.g. hemodynamic slope, we introduced a new feature - deep contribution ratio which is the proportion of cerebral hemodynamics to the fNIRS signals. Multiple sets of features were examined by a simple logical operator to suppress the false detection rate in identifying the activated channels. Using the number of activated channels as input to a linear support vector machine (SVM), the performance of the proposed analytical framework was assessed in classifying three levels of mental workload. The best set of features involves the combination of hemodynamic slope and deep contribution ratio, where the identified number of activated channels returned an average accuracy of 80.6% in predicting mental workload, compared to a single conventional feature (accuracy: 59.8%). This suggests the feasibility of the proposed analytical framework with multiple features as a means towards a more accurate assessment of mental workload in fNIRS-based BCI applications.