Decoding Algorithm of Motor Imagery Electroencephalogram Signal Based on CLRNet Network Model.

EEG decoding based on motor imagery is an important part of brain-computer interface technology and is an important indicator that determines the overall performance of the brain-computer interface. Due to the complexity of motor imagery EEG feature analysis, traditional classification models rely heavily on the signal preprocessing and feature design stages. End-to-end neural networks in deep learning have been applied to the classification task processing of motor imagery EEG and have shown good results. This study uses a combination of a convolutional neural network (CNN) and a long short-term memory (LSTM) network to obtain spatial information and temporal correlation from EEG signals. The use of cross-layer connectivity reduces the network gradient dispersion problem and enhances the overall network model stability. The effectiveness of this network model is demonstrated on the BCI Competition IV dataset 2a by integrating CNN, BiLSTM and ResNet (called CLRNet in this study) to decode motor imagery EEG. The network model combining CNN and BiLSTM achieved 87.0% accuracy in classifying motor imagery patterns in four classes. The network stability is enhanced by adding ResNet for cross-layer connectivity, which further improved the accuracy by 2.0% to achieve 89.0% classification accuracy. The experimental results show that CLRNet has good performance in decoding the motor imagery EEG dataset. This study provides a better solution for motor imagery EEG decoding in brain-computer interface technology research.

The relation between implicit statistical learning and proactivity as revealed by EEG.

Environmental events often occur on a probabilistic basis but can sometimes be predicted based on specific cues and thus approached proactively. Incidental statistical learning enables the acquisition of knowledge about probabilistic cue-target contingencies. However, the neural mechanisms of statistical learning about contingencies (SLC), the required conditions for successful learning, and the role of implicit processes in the resultant proactive behavior are still debated. We examined changes in behavior and cortical activity during an SLC task in which subjects responded to visual targets. Unbeknown to them, there were three types of target cues associated with high-, low-, and zero target probabilities. About half of the subjects spontaneously gained explicit knowledge about the contingencies (contingency-aware group), and only they showed evidence of proactivity: shortened response times to predictable targets and enhanced event-related brain responses (cue-evoked P300 and contingent negative variation, CNV) to high probability cues. The behavioral and brain responses were strictly associated on a single-trial basis. Source reconstruction of the brain responses revealed activation of fronto-parietal brain regions associated with cognitive control, particularly the anterior cingulate cortex and precuneus. We also found neural correlates of SLC in the contingency-unaware group, but these were restricted to post-target latencies and visual association areas. Our results document a qualitative difference between explicit and implicit learning processes and suggest that in certain conditions, proactivity may require explicit knowledge about contingencies.

Automated recognition of epilepsy from EEG signals using a combining space-time algorithm of CNN-LSTM.

Intelligent recognition methods for classifying non-stationary and non-invasive epileptic diagnoses are essential tools in neurological research. Electroencephalogram (EEG) signals exhibit better temporal characteristics in the detection of epilepsy compared to radiation medical images like computed tomography (CT) and magnetic resonance imaging (MRI), as they provide real-time insights into the disease' condition. While classical machine learning methods have been used for epilepsy EEG classification, they still often require manual parameter adjustments. Previous studies primarily focused on binary epilepsy recognition (epilepsy vs. healthy subjects) rather than as ternary status recognition (continuous epilepsy vs. intermittent epilepsy vs. healthy subjects). In this study, we propose a novel deep learning method that combines a convolution neural network (CNN) with a long short-term memory (LSTM) network for multi-class classification including both binary and ternary tasks, using a publicly available benchmark database on epilepsy EEGs. The hybrid CNN-LSTM automatically acquires knowledge without the need for extra pre-processing or manual intervention. Besides, the joint network method benefits from memory function and stronger feature extraction ability. Our proposed hybrid CNN-LSTM achieves state-of-the-art performance in ternary classification, outperforming classical machine learning and the latest deep learning models. For the three-class classification, in the method achieves an accuracy, specificity, sensitivity, and ROC of 98%, 97.4, 98.3% and 96.8%, respectively. In binary classification, the method achieves better results, with ACC of 100%, 100%, and 99.8%, respectively. Our dual stream spatiotemporal hybrid network demonstrates superior performance compared to other methods. Notably, it eliminates the need for manual operations, making it more efficient for doctors to diagnose during the clinical process and alleviating the workload of neurologists.

ECG and EEG based detection and multilevel classification of stress using machine learning for specified genders: A preliminary study.

Mental health, especially stress, plays a crucial role in the quality of life. During different phases (luteal and follicular phases) of the menstrual cycle, women may exhibit different responses to stress from men. This, therefore, may have an impact on the stress detection and classification accuracy of machine learning models if genders are not taken into account. However, this has never been investigated before. In addition, only a handful of stress detection devices are scientifically validated. To this end, this work proposes stress detection and multilevel stress classification models for unspecified and specified genders through ECG and EEG signals. Models for stress detection are achieved through developing and evaluating multiple individual classifiers. On the other hand, the stacking technique is employed to obtain models for multilevel stress classification. ECG and EEG features extracted from 40 subjects (21 females and 19 males) were used to train and validate the models. In the low&high combined stress conditions, RBF-SVM and kNN yielded the highest average classification accuracy for females (79.81%) and males (73.77%), respectively. Combining ECG and EEG, the average classification accuracy increased to at least 87.58% (male, high stress) and up to 92.70% (female, high stress). For multilevel stress classification from ECG and EEG, the accuracy for females was 62.60% and for males was 71.57%. This study shows that the difference in genders influences the classification performance for both the detection and multilevel classification of stress. The developed models can be used for both personal (through ECG) and clinical (through ECG and EEG) stress monitoring, with and without taking genders into account.

Neural signals-based respiratory motion tracking: a proof-of-concept study.

Objective.Respiratory motion tracking techniques can provide optimal treatment accuracy for thoracoabdominal radiotherapy and robotic surgery. However, conventional imaging-based respiratory motion tracking techniques are time-lagged owing to the system latency of medical linear accelerators and surgical robots. This study aims to investigate the precursor time of respiratory-related neural signals and analyze the potential of neural signals-based respiratory motion tracking.Approach.The neural signals and respiratory motion from eighteen healthy volunteers were acquired simultaneously using a 256-channel scalp electroencephalography (EEG) system. The neural signals were preprocessed using the MNE python package to extract respiratory-related EEG neural signals. Cross-correlation analysis was performed to assess the precursor time and cross-correlation coefficient between respiratory-related EEG neural signals and respiratory motion.Main results.Respiratory-related neural signals that precede the emergence of respiratory motion are detectable via non-invasive EEG. On average, the precursor time of respiratory-related EEG neural signals was 0.68 s. The representative cross-correlation coefficients between EEG neural signals and respiratory motion of the eighteen healthy subjects varied from 0.22 to 0.87.Significance.Our findings suggest that neural signals have the potential to compensate for the system latency of medical linear accelerators and surgical robots. This indicates that neural signals-based respiratory motion tracking is a potential promising solution to respiratory motion and could be useful in thoracoabdominal radiotherapy and robotic surgery.

Neurofeedback for post-traumatic stress disorder: systematic review and meta-analysis of clinical and neurophysiological outcomes.

Background: Posttraumatic stress disorder (PTSD) is a debilitating condition affecting millions of people worldwide. Existing treatments often fail to address the complexity of its symptoms and functional impairments resulting from severe and prolonged trauma. Electroencephalographic Neurofeedback (NFB) has emerged as a promising treatment that aims to reduce the symptoms of PTSD by modulating brain activity.Objective: We conducted a systematic review and meta-analysis of ten clinical trials to answer the question: how effective is NFB in addressing PTSD and other associated symptoms across different trauma populations, and are these improvements related to neurophysiological changes?Method: The review followed the Preferred Reporting Items for Systematic Reviews and Meta analyses guidelines. We considered all published and unpublished randomised controlled trials (RCTs) and non-randomised studies of interventions (NRSIs) involving adults with PTSD as a primary diagnosis without exclusion by type of trauma, co-morbid diagnosis, locality, or sex. Ten controlled studies were included; seven RCTs and three NRSIs with a total number of participants n = 293 (128 male). Only RCTs were included in the meta-analysis (215 participants; 88 male).Results: All included studies showed an advantage of NFB over control conditions in reducing symptoms of PTSD, with indications of improvement in symptoms of anxiety and depression and related neurophysiological changes. Meta-analysis of the pooled data shows a significant reduction in PTSD symptoms post-treatment SMD of -1.76 (95% CI -2.69, -0.83), and the mean remission rate was higher in the NFB group (79.3%) compared to the control group (24.4%). However, the studies reviewed were mostly small, with heterogeneous populations and varied quality.Conclusions: The effect of NFB on the symptoms of PTSD was moderate and mechanistic evidence suggested that NFB leads to therapeutic changes in brain functioning. Future research should focus on more rigorous methodological designs, expanded sample size and longer follow-up.

Neurofeedback (NFB) was found to have moderate beneficial effects on PTSD symptoms, and positive effects on secondary outcomes such as depression and anxiety, according to a meta-analysis of seven randomised controlled trials (RCTs).The beneficial effects of NFB were observed across diverse populations, including those with different types of trauma (military and civilians) and from different ethnic backgrounds.Results suggest that modulation of alpha rhythm might be a viable NFB protocol in patients with PTSD, as changes in neurophysiological functioning, such as connectivity in the Default Mode Network (DMN) and Salience Network (SN), were observed post-NFB and were correlated with a decrease in PTSD severity.

A large EEG database with users' profile information for motor imagery brain-computer interface research.

We present and share a large database containing electroencephalographic signals from 87 human participants, collected during a single day of brain-computer interface (BCI) experiments, organized into 3 datasets (A, B, and C) that were all recorded using the same protocol: right and left hand motor imagery (MI). Each session contains 240 trials (120 per class), which represents more than 20,800 trials, or approximately 70 hours of recording time. It includes the performance of the associated BCI users, detailed information about the demographics, personality profile as well as some cognitive traits and the experimental instructions and codes (executed in the open-source platform OpenViBE). Such database could prove useful for various studies, including but not limited to: (1) studying the relationships between BCI users' profiles and their BCI performances, (2) studying how EEG signals properties varies for different users' profiles and MI tasks, (3) using the large number of participants to design cross-user BCI machine learning algorithms or (4) incorporating users' profile information into the design of EEG signal classification algorithms.

Multimodal Approach for Pilot Mental State Detection Based on EEG.

The safety of flight operations depends on the cognitive abilities of pilots. In recent years, there has been growing concern about potential accidents caused by the declining mental states of pilots. We have developed a novel multimodal approach for mental state detection in pilots using electroencephalography (EEG) signals. Our approach includes an advanced automated preprocessing pipeline to remove artefacts from the EEG data, a feature extraction method based on Riemannian geometry analysis of the cleaned EEG data, and a hybrid ensemble learning technique that combines the results of several machine learning classifiers. The proposed approach provides improved accuracy compared to existing methods, achieving an accuracy of 86% when tested on cleaned EEG data. The EEG dataset was collected from 18 pilots who participated in flight experiments and publicly released at NASA's open portal. This study presents a reliable and efficient solution for detecting mental states in pilots and highlights the potential of EEG signals and ensemble learning algorithms in developing cognitive cockpit systems. The use of an automated preprocessing pipeline, feature extraction method based on Riemannian geometry analysis, and hybrid ensemble learning technique set this work apart from previous efforts in the field and demonstrates the innovative nature of the proposed approach.

An Explainable EEG-Based Human Activity Recognition Model Using Machine-Learning Approach and LIME.

Electroencephalography (EEG) is a non-invasive method employed to discern human behaviors by monitoring the neurological responses during cognitive and motor tasks. Machine learning (ML) represents a promising tool for the recognition of human activities (HAR), and eXplainable artificial intelligence (XAI) can elucidate the role of EEG features in ML-based HAR models. The primary objective of this investigation is to investigate the feasibility of an EEG-based ML model for categorizing everyday activities, such as resting, motor, and cognitive tasks, and interpreting models clinically through XAI techniques to explicate the EEG features that contribute the most to different HAR states. The study involved an examination of 75 healthy individuals with no prior diagnosis of neurological disorders. EEG recordings were obtained during the resting state, as well as two motor control states (walking and working tasks), and a cognition state (reading task). Electrodes were placed in specific regions of the brain, including the frontal, central, temporal, and occipital lobes (Fz, C1, C2, T7, T8, Oz). Several ML models were trained using EEG data for activity recognition and LIME (Local Interpretable Model-Agnostic Explanations) was employed for interpreting clinically the most influential EEG spectral features in HAR models. The classification results of the HAR models, particularly the Random Forest and Gradient Boosting models, demonstrated outstanding performances in distinguishing the analyzed human activities. The ML models exhibited alignment with EEG spectral bands in the recognition of human activity, a finding supported by the XAI explanations. To sum up, incorporating eXplainable Artificial Intelligence (XAI) into Human Activity Recognition (HAR) studies may improve activity monitoring for patient recovery, motor imagery, the healthcare metaverse, and clinical virtual reality settings.

Single-trial visually evoked potentials predict both individual choice and market outcomes.

A central assumption in the behavioral sciences is that choice behavior generalizes enough across individuals that measurements from a sampled group can predict the behavior of the population. Following from this assumption, the unit of behavioral sampling or measurement for most neuroimaging studies is the individual; however, cognitive neuroscience is increasingly acknowledging a dissociation between neural activity that predicts individual behavior and that which predicts the average or aggregate behavior of the population suggesting a greater importance of individual differences than is typically acknowledged. For instance, past work has demonstrated that some, but not all, of the neural activity observed during value-based decision-making is able to predict not just individual subjects' choices but also the success of products on large, online marketplaces-even when those two behavioral outcomes deviate from one another-suggesting that some neural component processes of decision-making generalize to aggregate market responses more readily across individuals than others do. While the bulk of such research has highlighted affect-related neural responses (i.e. in the nucleus accumbens) as a better predictor of group-level behavior than frontal cortical activity associated with the integration of more idiosyncratic choice components, more recent evidence has implicated responses in visual cortical regions as strong predictors of group preference. Taken together, these findings suggest a role of neural responses during early perception in reinforcing choice consistency across individuals and raise fundamental scientific questions about the role sensory systems in value-based decision-making processes. We use a multivariate pattern analysis approach to show that single-trial visually evoked electroencephalographic (EEG) activity can predict individual choice throughout the post-stimulus epoch; however, a nominally sparser set of activity predicts the aggregate behavior of the population. These findings support an account in which a subset of the neural activity underlying individual choice processes can scale to predict behavioral consistency across people, even when the choice behavior of the sample does not match the aggregate behavior of the population.

Evaluation of interpretability for deep learning algorithms in EEG emotion recognition: A case study in autism.

Current models on Explainable Artificial Intelligence (XAI) have shown a lack of reliability when evaluating feature-relevance for deep neural biomarker classifiers. The inclusion of reliable saliency-maps for obtaining trustworthy and interpretable neural activity is still insufficiently mature for practical applications. These limitations impede the development of clinical applications of Deep Learning. To address, these limitations we propose the RemOve-And-Retrain (ROAR) algorithm which supports the recovery of highly relevant features from any pre-trained deep neural network. In this study we evaluated the ROAR methodology and algorithm for the Face Emotion Recognition (FER) task, which is clinically applicable in the study of Autism Spectrum Disorder (ASD). We trained a Convolutional Neural Network (CNN) from electroencephalography (EEG) signals and assessed the relevance of FER-elicited EEG features from individuals diagnosed with and without ASD. Specifically, we compared the ROAR reliability from well-known relevance maps such as Layer-Wise Relevance Propagation, PatternNet, Pattern-Attribution, and Smooth-Grad Squared. This study is the first to bridge previous neuroscience and ASD research findings to feature-relevance calculation for EEG-based emotion recognition with CNN in typically-development (TD) and in ASD individuals.

Development of a Bispectral index score prediction model based on an interpretable deep learning algorithm.

BACKGROUND: Proper maintenance of hypnosis is crucial for ensuring the safety of patients undergoing surgery. Accordingly, indicators, such as the Bispectral index (BIS), have been developed to monitor hypnotic levels. However, the black-box nature of the algorithm coupled with the hardware makes it challenging to understand the underlying mechanisms of the algorithms and integrate them with other monitoring systems, thereby limiting their use. OBJECTIVE: We propose an interpretable deep learning model that forecasts BIS values 25 s in advance using 30 s electroencephalogram (EEG) data. MATERIAL AND METHODS: The proposed model utilized EEG data as a predictor, which is then decomposed into amplitude and phase components using fast Fourier Transform. An attention mechanism was applied to interpret the importance of these components in predicting BIS. The predictability of the model was evaluated on both regression and binary classification tasks, where the former involved predicting a continuous BIS value, and the latter involved classifying a dichotomous status at a BIS value of 60. To evaluate the interpretability of the model, we analyzed the attention values expressed in the amplitude and phase components according to five ranges of BIS values. The proposed model was trained and evaluated using datasets collected from two separate medical institutions. RESULTS AND CONCLUSION: The proposed model achieved excellent performance on both the internal and external validation datasets. The model achieved a root-mean-square error of 6.614 for the regression task, and an area under the receiver operating characteristic curve of 0.937 for the binary classification task. Interpretability analysis provided insight into the relationship between EEG frequency components and BIS values. Specifically, the attention mechanism revealed that higher BIS values were associated with increased amplitude attention values in high-frequency bands and increased phase attention values in various frequency bands. This finding is expected to facilitate a more profound understanding of the BIS prediction mechanism, thereby contributing to the advancement of anesthesia technologies.

QEEG markers of superior shooting performance in skilled marksmen: An investigation of cortical activity on psychomotor efficiency hypothesis.

For elite performers, psychomotor behavior's success or failure can be traced to differences in brain dynamics. The psychomotor efficiency hypothesis suggests refined cortical activity through 1) selective activation of task-relevant processes and 2) inhibition of non-essential processes. The use of electroencephalography (EEG) has been applied to investigate psychomotor performance's neural processes. The EEG markers that reflect an elevation of psychomotor efficiency include left temporal alpha (T3 alpha), frontal midline theta (Fm theta), sensorimotor rhythm (SMR), and the coherence between frontal and left temporal regions. However, the relationship between elite performers' task-relevant and non-essential neural processes is still not well understood. Therefore, this study aimed to explore how each task-relevant and inhibition of non-essential processes contribute to superior psychomotor behavior. Thirty-five highly skilled marksmen were recruited to perform 30 shots in the shooting task while the EEG was recorded. The marksmen were divided into two groups (superior & inferior) based on a median split of shooting performance. The superior group exhibited higher accuracy and precision, with a reduction in movement jerk. EEG measures revealed that the superior group exhibited higher SMR before the trigger pull than the inferior group. In addition, the superior group demonstrated reduced Fz-T3 coherence in their bull's eye shots than the missed shots. These results suggest that the superior group exhibited less effortful engagement of task-relevant processes and lower interference from non-essential cortical regions than the inferior group. The study's overall findings support the psychomotor efficiency hypothesis. When comparing highly skilled performers, the slight differences in brain dynamics ultimately contribute to the success or failure of psychomotor performance.

Resting-state electroencephalography microstate dynamics altered in patients with migraine with and without aura-A pilot study.

OBJECTIVE: To evaluate electroencephalography (EEG) microstate differences between patients with migraine with aura (MWA), patients with migraine without aura (MWoA), and healthy controls (HC). BACKGROUND: Previous research employing microstate analysis found unique microstate alterations in patients with MWoA; however, it is uncertain how microstates appear in patients with MWA. METHODS: This study was conducted at the Headache Clinic of the First Affiliated Hospital of Xi'an Jiaotong University. In total, 30 patients with MWA, 30 with MWoA, and 30 HC were enrolled in this cross-sectional study. An EEG was recorded for all participants under resting state. The microstate parameters of four widely recognized microstate classes A-D were calculated and compared across the three groups. RESULTS: The occurrence of microstate B (MsB) in the MWoA group was significantly higher than in the HC (p = 0.006, Cohen's d = 0.72) and MWA (p = 0.016, Cohen's d = 0.57) groups, while the contribution of MsB was significantly increased in the MWoA group compared to the HC group (p = 0.016, Cohen's d = 0.64). Microstate A (MsA) displayed a longer duration in the MWA group compared to the MWoA group (p = 0.007, Cohen's d = 0.69). Furthermore, the transition probability between MsB and microstate D was significantly increased in the MWoA group compared to the HC group (p = 0.009, Cohen's d = 0.68 for B to D; p = 0.007, Cohen's d = 0.71 for D to B). Finally, the occurrence and contribution of MsB were positively related to headache characteristics in the MWoA group but negatively in the MWA group, whereas the duration of MsA was positively related to the visual analog scale in the MWA group (all p < 0.05). CONCLUSIONS: Patients with MWA and MWoA have altered microstate dynamics, indicating that resting-state brain network disorders may play a role in migraine pathogenesis. Microstate parameters may have the potential to aid clinical management, which needs to be investigated further.

Correlation between EEG spectral power and cerebral perfusion in patients with acute ischemic stroke.

Dry electrode electroencephalography (EEG) has the potential to diagnose ischemic stroke in the acute phase. In the current study we determined the correlation between EEG spectral power and ischemic stroke size and location as determined by computed tomography perfusion (CTP). Dry electrode EEG recordings were performed in patients with acute ischemic stroke in the emergency room. CTP preceded the EEG recordings as part of standard imaging protocol. Infarct core volume, total hypoperfused volume and local cerebral blood flow (CBF) were estimated with CTP. Additionally, global and local EEG spectral power were determined. We used Spearman's correlation coefficients to evaluate the correlation between variables. We included 27 patients (median age 72 [IQR:69-80] years, 15/27 [56%] men). Median CTP-to-EEG time was 32 (range:8-138) minutes. Hypoperfused volumes were estimated for 12/27 (44%) patients. Infarct core volume correlated best with global delta power (ρ = 0.76, p < 0.01), total hypoperfused volume with global alpha power (ρ = -0.58, p = 0.05), and local CBF with local alpha power (ρ = 0.43, p < 0.01). We conclude that dry electrode EEG signals slow down with increasing hypoperfused volume, which could potentially be used to discriminate between small and large ischemic strokes.

Real-Time EEG-Based Emotion Recognition.

Most studies have demonstrated that EEG can be applied to emotion recognition. In the process of EEG-based emotion recognition, real-time is an important feature. In this paper, the real-time problem of emotion recognition based on EEG is explained and analyzed. Secondly, the short time window length and attention mechanisms are designed on EEG signals to follow emotion change over time. Then, long short-term memory with the additive attention mechanism is used for emotion recognition, due to timely emotion updates, and the model is applied to the SEED and SEED-IV datasets to verify the feasibility of real-time emotion recognition. The results show that the model performs relatively well in terms of real-time performance, with accuracy rates of 85.40% and 74.26% on SEED and SEED-IV, but the accuracy rate has not reached the ideal state due to data labeling and other losses in the pursuit of real-time performance.

Enhancing Cross-Subject Motor Imagery Classification in EEG-Based Brain-Computer Interfaces by Using Multi-Branch CNN.

A brain-computer interface (BCI) is a computer-based system that allows for communication between the brain and the outer world, enabling users to interact with computers using neural activity. This brain signal is obtained from electroencephalogram (EEG) signals. A significant obstacle to the development of BCIs based on EEG is the classification of subject-independent motor imagery data since EEG data are very individualized. Deep learning techniques such as the convolutional neural network (CNN) have illustrated their influence on feature extraction to increase classification accuracy. In this paper, we present a multi-branch (five branches) 2D convolutional neural network that employs several hyperparameters for every branch. The proposed model achieved promising results for cross-subject classification and outperformed EEGNet, ShallowConvNet, DeepConvNet, MMCNN, and EEGNet_Fusion on three public datasets. Our proposed model, EEGNet Fusion V2, achieves 89.6% and 87.8% accuracy for the actual and imagined motor activity of the eegmmidb dataset and scores of 74.3% and 84.1% for the BCI IV-2a and IV-2b datasets, respectively. However, the proposed model has a bit higher computational cost, i.e., it takes around 3.5 times more computational time per sample than EEGNet_Fusion.

SincMSNet: a Sinc filter convolutional neural network for EEG motor imagery classification.

Objective.Motor imagery (MI) is widely used in brain-computer interfaces (BCIs). However, the decode of MI-EEG using convolutional neural networks (CNNs) remains a challenge due to individual variability.Approach.We propose a fully end-to-end CNN called SincMSNet to address this issue. SincMSNet employs the Sinc filter to extract subject-specific frequency band information and utilizes mixed-depth convolution to extract multi-scale temporal information for each band. It then applies a spatial convolutional block to extract spatial features and uses a temporal log-variance block to obtain classification features. The model of SincMSNet is trained under the joint supervision of cross-entropy and center loss to achieve inter-class separable and intra-class compact representations of EEG signals.Main results.We evaluated the performance of SincMSNet on the BCIC-IV-2a (four-class) and OpenBMI (two-class) datasets. SincMSNet achieves impressive results, surpassing benchmark methods. In four-class and two-class inter-session analysis, it achieves average accuracies of 80.70% and 71.50% respectively. In four-class and two-class single-session analysis, it achieves average accuracies of 84.69% and 76.99% respectively. Additionally, visualizations of the learned band-pass filter bands by Sinc filters demonstrate the network's ability to extract subject-specific frequency band information from EEG.Significance.This study highlights the potential of SincMSNet in improving the performance of MI-EEG decoding and designing more robust MI-BCIs. The source code for SincMSNet can be found at:https://github.com/Want2Vanish/SincMSNet.

PSIs of EEG With Refined Frequency Decomposition Could Prognose Motor Recovery Before Rehabilitation Intervention.

Stroke often leads to permanent impairment in motor function. Accurate and quantitative prognosis of potential motor recovery before rehabilitation intervention can help healthcare centers improve resources organization and enable individualized intervention. The context of this paper investigated the potential of using electroencephalography (EEG) functional connectivity (FC) measures as biomarkers for assessing and prognosing improvement of Fugl-Meyer Assessment in upper extremity motor function ( ∆FMU) among participants with chronic stroke. EEG data from resting and motor imagery task were recorded from 13 participants with chronic stroke. Three functional connectivity methods, which were Pearson correlation measure (PCM), weighted Phase Lag Index (wPLI) and phase synchronization index (PSI), were investigated, under three regions of interest (inter-hemispheric, intra-hemispheric, and whole-brain), in two statues (resting and motor imagery), with 15 refined center frequencies. We applied correlation analysis to identify the optimal center frequencies and pairs of synchronized channels that were consistently associated with ∆FMU . Predictive models were generated using regression analysis algorithms based on optimized center frequencies and channel pairs identified from the proposed analysis method, with leave-one-out cross-validation. We found that PSI in the Alpha band (with center frequency of 9Hz) was the most sensitive FC measures for prognosing motor recovery. Strong and significant correlations were identified between the predictions and actual ∆FMU scores both in the resting state ( [Formula: see text], [Formula: see text], N=13) and motor imagery ( [Formula: see text], [Formula: see text], N=13). Our results suggested that EEG connectivity measured with PSI in resting state could be a promising biomarker for quantifying motor recovery before motor rehabilitation intervention.