A Two-Branch CNN Fusing Temporal and Frequency Features for Motor Imagery EEG Decoding

With the development of technology and the rise of the meta-universe concept, the brain-computer interface (BCI) has become a hotspot in the research field, and the BCI based on motor imagery (MI) EEG has been widely concerned. However, in the process of MI-EEG decoding, the performance of the decoding model needs to be improved. At present, most MI-EEG decoding methods based on deep learning cannot make full use of the temporal and frequency features of EEG data, which leads to a low accuracy of MI-EEG decoding. To address this issue, this paper proposes a two-branch convolutional neural network (TBTF-CNN) that can simultaneously learn the temporal and frequency features of EEG data. The structure of EEG data is reconstructed to simplify the spatio-temporal convolution process of CNN, and continuous wavelet transform is used to express the time-frequency features of EEG data. TBTF-CNN fuses the features learned from the two branches and then inputs them into the classifier to decode the MI-EEG. The experimental results on the BCI competition IV 2b dataset show that the proposed model achieves an average classification accuracy of 81.3% and a kappa value of 0.63. Compared with other methods, TBTF-CNN achieves a better performance in MI-EEG decoding. The proposed method can make full use of the temporal and frequency features of EEG data and can improve the decoding accuracy of MI-EEG.     

Conditional Entropy: A Potential Digital Marker for Stress

Recent decades have witnessed a substantial progress in the utilization of brain activity for the identification of stress digital markers. In particular, the success of entropic measures for this purpose is very appealing, considering (1) their suitability for capturing both linear and non-linear characteristics of brain activity recordings and (2) their direct association with the brain signal variability. These findings rely on external stimuli to induce the brain stress response. On the other hand, research suggests that the use of different types of experimentally induced psychological and physical stressors could potentially yield differential impacts on the brain response to stress and therefore should be dissociated from more general patterns. The present study takes a step toward addressing this issue by introducing conditional entropy (CE) as a potential electroencephalography (EEG)-based resting-state digital marker of stress. For this purpose, we use the resting-state multi-channel EEG recordings of 20 individuals whose responses to stress-related questionnaires show significantly higher and lower level of stress. Through the application of representational similarity analysis (RSA) and K-nearest-neighbor (KNN) classification, we verify the potential that the use of CE can offer to the solution concept of finding an effective digital marker for stress.     

Quantifying time irreversibility using probabilistic differences between symmetric permutations

To simplify the quantification of time irreversibility, we employ order patterns instead of the raw multi-dimension vectors in time series, and considering the existence of forbidden permutation, we propose a subtraction-based parameter, $Y_S$, to measure the probabilistic differences between symmetric permutations for time irreversibility. Two chaotic models, the logistic and Henon systems, and reversible Gaussian process and their surrogate data are used to validate the time-irreversible measure, and time irreversibility of epileptic EEGs from Nanjing General Hospital is detected by the parameter. Test results prove that it is promising to quantify time irreversibility by measuring the subtraction-based probabilistic differences between symmetric order patterns, and our findings highlight the manifestation of nonlinearity of whether healthy or diseased EEGs and suggest that the epilepsy leads to a decline in the nonlinearity of brain electrical activities during seize-free intervals.     

Integration of EEG source imaging and fMRI during continuous viewing of natural movies

Electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) are noninvasive neuroimaging tools which can be used to measure brain activity with excellent temporal and spatial resolution, respectively. By combining the neural and hemodynamic recordings from these modalities, we can gain better insight into how and where the brain processes complex stimuli, which may be especially useful in patients with different neural diseases. However, due to their vastly different spatial and temporal resolutions, the integration of EEG and fMRI recordings is not always straightforward. One fundamental obstacle has been that paradigms used for EEG experiments usually rely on event-related paradigms, while fMRI is not limited in this regard. Therefore, here we ask whether one can reliably localize stimulus-driven EEG activity using the continuously varying feature intensities occurring in natural movie stimuli presented over relatively long periods of time. Specifically, we asked whether stimulus-driven aspects in the EEG signal would be co-localized with the corresponding stimulus-driven BOLD signal during free viewing of a movie. Secondly, we wanted to integrate the EEG signal directly with the BOLD signal, by estimating the underlying impulse response function (IRF) that relates the BOLD signal to the underlying current density in the primary visual area (V1). We made sequential fMRI and 64-channel EEG recordings in seven subjects who passively watched 2-min-long segments of a James Bond movie. To analyze EEG data in this natural setting, we developed a method based on independent component analysis (ICA) to reject EEG artifacts due to blinks, subject movement, etc., in a way unbiased by human judgment. We then calculated the EEG source strength of this artifact-free data at each time point of the movie within the entire brain volume using low-resolution electromagnetic tomography (LORETA). This provided for every voxel in the brain (i.e., in 3D space) an estimate of the current density at every time point. We then carried out a correlation between the time series of visual contrast changes in the movie with that of EEG voxels. We found the most significant correlations in visual area V1, just as seen in previous fMRI studies (Bartels A, Zeki, S, Logothetis NK. Natural vision reveals regional specialization to local motion and to contrast-invariant, global flow in the human brain. Cereb Cortex 2008;18(3):705–717), but on the time scale of milliseconds rather than of seconds. To obtain an estimate of how the EEG signal relates to the BOLD signal, we calculated the IRF between the BOLD signal and the estimated current density in area V1. We found that this IRF was very similar to that observed using combined intracortical recordings and fMRI experiments in nonhuman primates. Taken together, these findings open a new approach to noninvasive mapping of the brain. It allows, firstly, the localization of feature-selective brain areas during natural viewing conditions with the temporal resolution of EEG. Secondly, it provides a tool to assess EEG/BOLD transfer functions during processing of more natural stimuli. This is especially useful in combined EEG/fMRI experiments, where one can now potentially study neural-hemodynamic relationships across the whole brain volume in a noninvasive manner.     

Multimodal imaging: an evaluation of univariate and multivariate methods for simultaneous EEG/fMRI

The combination of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) has been proposed as a tool to study brain dynamics with both high temporal and high spatial resolution. Multimodal imaging techniques rely on the assumption of a common neuronal source for the different recorded signals. In order to maximally exploit the combination of these techniques, one needs to understand the coupling (i.e., the relation) between electroencephalographic (EEG) and fMRI blood oxygen level-dependent (BOLD) signals.     

Identification of epilepsy from intracranial EEG signals by using different neural network models

In this work, a framework is provided for identifying intracranial electroencephalography (iEEG) seizures based on discrete wavelet transform (DWT) analysis of iEEG signals using forward propagation and feedback neural networks. The performance of 5 different data sets combination classifications is studied using the probabilistic neural network (PNN), learning vector quantization neural network (LVQ) and Elman neural network (ENN). Different feature combinations serve as the input vectors of the classifiers to obtain the best outcomes. It has been found that PNN has less running time and provides better classification accuracy (CA) than ENN and LVQ classifiers for all 5 classification problems. It is worth noticing that the CA for the C-D classification task, which shows the status of pre-ictal versus post-ictal, has been greatly improved, and reached 83.13%. Hence, the epilepsy iEEG signals pattern recognition based on DWT statistical features using the PNN classifier is more suitable for forming a reliable, automatic classification system in order to assist doctors in diagnosis.     

Brain Dynamics Altered by Photic Stimulation in Patients with Alzheimer’s Disease and Mild Cognitive Impairment

Individuals with mild cognitive impairment (MCI) are at high risk of developing Alzheimer’s disease (AD). Repetitive photic stimulation (PS) is commonly used in routine electroencephalogram (EEG) examinations for rapid assessment of perceptual functioning. This study aimed to evaluate neural oscillatory responses and nonlinear brain dynamics under the effects of PS in patients with mild AD, moderate AD, severe AD, and MCI, as well as healthy elderly controls (HC). EEG power ratios during PS were estimated as an index of oscillatory responses. Multiscale sample entropy (MSE) was estimated as an index of brain dynamics before, during, and after PS. During PS, EEG harmonic responses were lower and MSE values were higher in the AD subgroups than in HC and MCI groups. PS-induced changes in EEG complexity were less pronounced in the AD subgroups than in HC and MCI groups. Brain dynamics revealed a “transitional change” between MCI and Mild AD. Our findings suggest a deficiency in brain adaptability in AD patients, which hinders their ability to adapt to repetitive perceptual stimulation. This study highlights the importance of combining spectral and nonlinear dynamical analysis when seeking to unravel perceptual functioning and brain adaptability in the various stages of neurodegenerative diseases.     

Investigation on Identifying Implicit Learning Event from EEG Signal Using Multiscale Entropy and Artificial Bee Colony

The way people learn will play an essential role in the sustainable development of the educational system for the future. Utilizing technology in the age of information and incorporating it into how people learn can produce better learners. Implicit learning is a type of learning of the underlying rules without consciously seeking or understanding the rules; it is commonly seen in small children while learning how to speak their native language without learning grammar. This research aims to introduce a processing system that can systematically identify the relationship between implicit learning events and their Encephalogram (EEG) signal characteristics. This study converted the EEG signal from participants while performing cognitive task experiments into Multiscale Entropy (MSE) data. Using MSE data from different frequency bands and channels as features, the system explored a wide range of classifiers and observed their performance to see how they classified the features related to participants’ performance. The Artificial Bee Colony (ABC) method was used for feature selection to improve the process to make the system more efficient. The results showed that the system could correctly identify the differences between participants’ performance using MSE data and the ABC method with 95% confidence.     

Nonlinear EEG Changes Associated with Clinical Improvement in Depressed Patients

Assuming that the depressive syndrome could be related to a cerebral dynamical disease, we attempted to describe in a longitudinal and quantitative manner the modifications of brain electrical activity during depressive episodes treatment. This study tested whether mood improvement during therapy (pharmacological treatment or electroconvulsive therapy) is related to concomitant modifications of brain dynamics. The evolution of brain activity and mood were measured, every two days during treatment for three depressed patients and over three weeks for a control subject. Complexity of brain electrical activity was computed for each site of recording (EEG with 31 electrodes), leading to maps of complexity; depressive mood modulations were quantified using a self-assessment scale. The results show a specific organization of depressed patients' brain dynamics compared to the control's dynamics. Moreover, covariations between nonlinear changes in brain dynamics and mood improvement are observed during the remission of depressive episodes.