Predicting Motor Imagery Performance From Resting-State EEG Using Dynamic Causal Modeling

Connectivity study on resting-state EEG between motor imagery BCI-literate and BCI-illiterate groups

Objective.Although motor imagery-based brain-computer interface (MI-BCI) holds significant potential, its practical application faces challenges such as BCI-illiteracy. To mitigate this issue, researchers have attempted to predict BCI-illiteracy by using the resting state, as this was found to be associated with BCI performance. As connectivity's significance in neuroscience has grown, BCI researchers have applied connectivity to it. However, the issues of connectivity have not been considered fully. First, although various connectivity metrics exist, only some have been used to predict BCI-illiteracy. This is problematic because each metric has a distinct hypothesis and perspective to estimate connectivity, resulting in different outcomes according to the metric. Second, the frequency range affects the connectivity estimation. In addition, it is still unknown whether each metric has its own optimal frequency range. Third, the way that estimating connectivity may vary depending upon the dataset has not been investigated. Meanwhile, we still do not know a great deal about how the resting state electroencephalography (EEG) network differs between BCI-literacy and -illiteracy.Approach.To address the issues above, we analyzed three large public EEG datasets using three functional connectivity and three effective connectivity metrics by employing diverse graph theory measures. Our analysis revealed that the appropriate frequency range to predict BCI-illiteracy varies depending upon the metric. The alpha range was found to be suitable for the metrics of the frequency domain, while alpha + theta were found to be appropriate for multivariate Granger causality. The difference in network efficiency between BCI-literate and -illiterate groups was constant regardless of the metrics and datasets used. Although we observed that BCI-literacy had stronger connectivity, no other significant constructional differences were found.Significance.Based upon our findings, we predicted MI-BCI performance for the entire dataset. We discovered that combining several graph features could improve the prediction's accuracy.

A novel method for modeling effective connections between brain regions based on EEG signals and graph neural networks for motor imagery detection

Classified as biomedical signal processing, cerebral signal processing plays a key role in human-computer interaction (HCI) and medical diagnosis. The motor imagery (MI) problem is an important research area in this field. Accurate solutions to this problem will greatly affect real-world applications. Most of the proposed methods are based on raw signal processing techniques. Known as prior knowledge, the structural-functional information and interregional connections can improve signal processing accuracy. It is possible to correctly perceive the generated signals by considering the brain structure (i.e. anatomical units), the source of signals, and the structural-functional dependence of different brain regions (i.e. effective connection) that are the semantic generators of signals. This study employed electroencephalograph (EEG) signals based on the activity of brain regions (cortex) and effective connections between brain regions based on dynamic causal modeling to solve the MI problem. EEG signals, as well as effective connections between brain regions to improve the interpretability of MI action, were fed into the architecture of Graph Convolutional Neural Network (GCN). The proposed model allowed GCN to extract more discriminative features. The results indicated that the proposed method was successful in developing a model with a MI detection accuracy of 93.73%.

Multi-Task Heterogeneous Ensemble Learning-Based Cross-Subject EEG Classification Under Stroke Patients

Robot-assisted motor training is applied for neurorehabilitation in stroke patients, using motor imagery (MI) as a representative paradigm of brain-computer interfaces to offer real-life assistance to individuals facing movement challenges. However, the effectiveness of training with MI may vary depending on the location of the stroke lesion, which should be considered. This paper introduces a multi-task electroencephalogram-based heterogeneous ensemble learning (MEEG-HEL) specifically designed for cross-subject training. In the proposed framework, common spatial patterns were used for feature extraction, and the features according to stroke lesions are shared and selected through sequential forward floating selection. The heterogeneous ensembles were used as classifiers. Nine patients with chronic ischemic stroke participated, engaging in MI and motor execution (ME) paradigms involving finger tapping. The classification criteria for the multi-task were established in two ways, taking into account the characteristics of stroke patients. In the cross-subject session, the first involved a direction recognition task for two-handed classification, achieving a performance of 0.7419 (±0.0811) in MI and 0.7061 (±0.1270) in ME. The second task focused on motor assessment for lesion location, resulting in a performance of 0.7457 (±0.1317) in MI and 0.6791 (±0.1253) in ME. Comparing the specific-subject session, except for ME on the motor assessment task, performance on both tasks was significantly higher than the cross-subject session. Furthermore, classification performance was similar to or statistically higher in cross-subject sessions compared to baseline models. The proposed MEEG-HEL holds promise in improving the practicality of neurorehabilitation in clinical settings and facilitating the detection of lesions.

Upper extremity training followed by lower extremity training with a brain-computer interface rehabilitation system

Introduction

Brain-computer interfaces (BCIs) based on functional electrical stimulation have been used for upper extremity motor rehabilitation after stroke. However, little is known about their efficacy for multiple BCI treatments. In this study, 19 stroke patients participated in 25 upper extremity followed by 25 lower extremity BCI training sessions.

Methods

Patients' functional state was assessed using two sets of clinical scales for the two BCI treatments. The Upper Extremity Fugl-Meyer Assessment (FMA-UE) and the 10-Meter Walk Test (10MWT) were the primary outcome measures for the upper and lower extremity BCI treatments, respectively.

Results

Patients' motor function as assessed by the FMA-UE improved by an average of 4.2 points (p < 0.001) following upper extremity BCI treatment. In addition, improvements in activities of daily living and clinically relevant improvements in hand and finger spasticity were observed. Patients showed further improvements after the lower extremity BCI treatment, with walking speed as measured by the 10MWT increasing by 0.15 m/s (p = 0.001), reflecting a substantial meaningful change. Furthermore, a clinically relevant improvement in ankle spasticity and balance and mobility were observed.

Discussion

The results of the current study provide evidence that both upper and lower extremity BCI treatments, as well as their combination, are effective in facilitating functional improvements after stroke. In addition, and most importantly improvements did not stop after the first 25 upper extremity BCI sessions.

Analyzing and computing humans by means of the brain using Brain-Computer Interfaces - understanding the user - previous evidence, self-relevance and the user's self-concept as potential superordinate human factors of relevance

Brain-computer interfaces (BCIs) are well-known instances of how technology can convert a user's brain activity taken from non-invasive electroencephalography (EEG) into computer commands for the purpose of computer-assisted communication and interaction. However, not all users are attaining the accuracy required to use a BCI consistently, despite advancements in technology. Accordingly, previous research suggests that human factors could be responsible for the variance in BCI performance among users. Therefore, the user's internal mental states and traits including motivation, affect or cognition, personality traits, or the user's satisfaction, beliefs or trust in the technology have been investigated. Going a step further, this manuscript aims to discuss which human factors could be potential superordinate factors that influence BCI performance, implicitly, explicitly as well as inter- and intraindividually. Based on the results of previous studies that used comparable protocols to examine the motivational, affective, cognitive state or personality traits of healthy and vulnerable EEG-BCI users within and across well-investigated BCIs (P300-BCIs or SMR-BCIs, respectively), it is proposed that the self-relevance of tasks and stimuli and the user's self-concept provide a huge potential for BCI applications. As potential key human factors self-relevance and the user's self-concept (self-referential knowledge and beliefs about one's self) guide information processing and modulate the user's motivation, attention, or feelings of ownership, agency, and autonomy. Changes in the self-relevance of tasks and stimuli as well as self-referential processing related to one's self (self-concept) trigger changes in neurophysiological activity in specific brain networks relevant to BCI. Accordingly, concrete examples will be provided to discuss how past and future research could incorporate self-relevance and the user's self-concept in the BCI setting - including paradigms, user instructions, and training sessions.

MEANSP: How Many Channels are Needed to Predict the Performance of a SMR-Based BCI?

Predicting whether a particular individual would reach an adequate control of a Brain-Computer Interface (BCI) has many practical advantages. On the one hand, participants with low predicted performance could be trained with specifically designed sessions and avoid frustrating experiments; on the other hand, planning time and resources would be more efficient; and finally, the variables related to an accurate prediction could be manipulated to improve the prospective BCI performance. To this end, several predictors have been proposed in the literature, most of them based on the power estimation of EEG signals at the specific frequency bands. Many of these studies evaluate their predictors in relatively small datasets and/or using a relatively high number of channels. In this manuscript, we propose a novel predictor called [Formula: see text] to predict the performance of participants using BCIs that are based on the modulation of sensorimotor rhythms. This novel predictor has been positively evaluated using only 2, 3, 4 or 5 channels. [Formula: see text] has shown to perform as well as or better than other state-of-the-art predictors. The best sets of different number of channels are also provided, which have been tested in two different settings to prove their robustness. The proposed predictor has been successfully evaluated using two large-scale datasets containing 150 and 80 participants, respectively. We also discuss predictor thresholds for users to expect good performance in feedback experiments and show the advantages in comparison to a competing algorithm.

Predicting Motor Imagery BCI Performance Based on EEG Microstate Analysis

Motor imagery (MI) electroencephalography (EEG) is natural and comfortable for controllers, and has become a research hotspot in the field of the brain-computer interface (BCI). Exploring the inter-subject MI-BCI performance variation is one of the fundamental problems in MI-BCI application. EEG microstates with high spatiotemporal resolution and multichannel information can represent brain cognitive function. In this paper, four EEG microstates (MS1, MS2, MS3, MS4) were used in the analysis of the differences in the subjects' MI-BCI performance, and the four microstate feature parameters (the mean duration, the occurrences per second, the time coverage ratio, and the transition probability) were calculated. The correlation between the resting-state EEG microstate feature parameters and the subjects' MI-BCI performance was measured. Based on the negative correlation of the occurrence of MS1 and the positive correlation of the mean duration of MS3, a resting-state microstate predictor was proposed. Twenty-eight subjects were recruited to participate in our MI experiments to assess the performance of our resting-state microstate predictor. The experimental results show that the average area under curve (AUC) value of our resting-state microstate predictor was 0.83, and increased by 17.9% compared with the spectral entropy predictor, representing that the microstate feature parameters can better fit the subjects' MI-BCI performance than spectral entropy predictor. Moreover, the AUC of microstate predictor is higher than that of spectral entropy predictor at both the single-session level and average level. Overall, our resting-state microstate predictor can help MI-BCI researchers better select subjects, save time, and promote MI-BCI development.

Can Inter-Subject Associativity Predict Data-Driven BCI Performance?

Intra- and inter-subject variability causes covariate shifts in training and testing feature spaces, resulting in low sensorimotor (SMR) brain-computer interface (BCI) performance for practical implementation. Studies involving data-driven transfer learning strategies demonstrated improving BCI performance by covariate shift adaptation. In this study, we aim to illustrate if inter-subject associativity (e.g., subjects having similar SMR brain dynamics) can predict data-driven inter-subject BCI performance. We implemented a BCI classification pipeline with a common spatial pattern, principal component analysis and linear discriminant analysis for performance evaluation. Both intra- and inter-subject BCI were evaluated in 5-Fold Validation settings. We further proposed a Bhattacharyya distance-based covariate shift score (CSS) for assessing the difference between training and testing feature domains. We performed Pearson correlation analysis to draw the relation-ship between BCI performance and CSS. Intra-subject BCI performances were significantly and negatively correlated with CSS (r = -0.94, p < 0.05). For the inter-subject experiment, BCI performances were also highly and negatively associated with CSS (r = -0.61, p < 0.05). However, this data-driven BCI evaluation framework does not necessarily manifest inter-subject associativity in BCI performance, requiring further investigations for a conclusion.Clinical relevance- If it predicts BCI performance successfully, inter-subject associativity could reduce time-consuming and annoying subject-specific calibration for the users.

Transcranial Magnetic Stimulation of the Dorsolateral Prefrontal Cortex Increases Posterior Theta Rhythm and Reduces Latency of Motor Imagery

Experiments show activation of the left dorsolateral prefrontal cortex (DLPFC) in motor imagery (MI) tasks, but its functional role requires further investigation. Here, we address this issue by applying repetitive transcranial magnetic stimulation (rTMS) to the left DLPFC and evaluating its effect on brain activity and the latency of MI response. This is a randomized, sham-controlled EEG study. Participants were randomly assigned to receive sham (15 subjects) or real high-frequency rTMS (15 subjects). We performed EEG sensor-level, source-level, and connectivity analyses to evaluate the rTMS effects. We revealed that excitatory stimulation of the left DLPFC increases theta-band power in the right precuneus (PrecuneusR) via the functional connectivity between them. The precuneus theta-band power negatively correlates with the latency of the MI response, so the rTMS speeds up the responses in 50% of participants. We suppose that posterior theta-band power reflects attention modulation of sensory processing; therefore, high power may indicate attentive processing and cause faster responses.

Neuropsychological Evidence Underlying Counterclockwise Bias in Running: Electroencephalography and Functional Magnetic Resonance Imaging Studies of Motor Imagery

We aimed to answer the question "why do people run the track counterclockwise (CCW)?" by investigating the neurophysiological differences in clockwise (CW) versus CCW direction using motor imagery. Three experiments were conducted with healthy adults. Electroencephalography (EEG) was used to examine hemispheric asymmetries in the prefrontal, frontal, and central regions during CW and CCW running imagery (n = 40). We also evaluated event-related potential (ERP) N200 and P300 amplitudes and latencies (n = 66) and conducted another experiment using functional magnetic resonance imaging (fMRI) (n = 30). EEG data indicated greater left frontal cortical activation during CCW imagery, whereas right frontal activation was more dominant during CW imagery. The prefrontal and central asymmetries demonstrated greater left prefrontal activation during both CW and CCW imagery, with CCW rotation exhibiting higher, though statistically insignificant, asymmetry scores than CW rotation. As a result of the fMRI experiment, greater activation was found during CW than during CCW running imagery in the brain regions of the left insula, Brodmann area 18, right caudate nucleus, left dorsolateral prefrontal cortex, left superior parietal cortex, and supplementary motor area. In the ERP experiment, no significant differences were found depending on direction. These findings suggest that CCW rotation might be associated with the motivational approach system, behavioral activation, or positive affect. However, CW rotation reflects withdrawal motivation, behavioral inhibition, or negative affect. Furthermore, CW rotation is understood to be associated with neural inefficiency, increased task difficulty, or unfamiliarity.

TMS over dorsolateral prefrontal cortex affects the timing of motor imagery but not overt action: Further support for the motor-cognitive model

The Motor-Cognitive model suggests a functional dissociation between motor imagery and overt action, in contrast to the Functional Equivalence view of common processes between the two behaviours. According to the Motor-Cognitive model, motor imagery differs from overt action primarily through the use of executive resources to monitor and elaborate a motor image during execution, which can result in a lack of correspondence between motor imagery and its overt action counterpart. The present study examined the importance of executive resources in motor imagery by using TMS to impair the function of the dorsolateral prefrontal cortex while measuring the time to complete imagined versus overt actions. In two experiments, TMS over the dorsolateral prefrontal cortex slowed motor imagery but did not affect overt actions. TMS over the same region also interfered with performance of a mental calculation task, though it did not reliably affect less demanding cognitive tasks also thought to rely on executive functions. Taken together, these results were consistent with the Motor-Cognitive model but not with the idea of functional equivalence. The implications of these results for the theoretical understanding of motor imagery, and potential applications of the Motor-Cognitive model to the use of motor imagery in training and rehabilitation, are discussed.

Personalized Brain-Computer Interface and Its Applications

Brain-computer interfaces (BCIs) are a new technology that subverts traditional human-computer interaction, where the control signal source comes directly from the user's brain. When a general BCI is used for practical applications, it is difficult for it to meet the needs of different individuals because of the differences among individual users in physiological and mental states, sensations, perceptions, imageries, cognitive thinking activities, and brain structures and functions. For this reason, it is necessary to customize personalized BCIs for specific users. So far, few studies have elaborated on the key scientific and technical issues involved in personalized BCIs. In this study, we will focus on personalized BCIs, give the definition of personalized BCIs, and detail their design, development, evaluation methods and applications. Finally, the challenges and future directions of personalized BCIs are discussed. It is expected that this study will provide some useful ideas for innovative studies and practical applications of personalized BCIs.

Repetitive Peripheral Magnetic Stimulation Combined with Motor Imagery Changes Resting-State EEG Activity: A Randomized Controlled Trial

Repetitive peripheral magnetic stimulation is a novel non-invasive technique for applying repetitive magnetic stimulation to the peripheral nerves and muscles. Contrarily, a person imagines that he/she is exercising during motor imagery. Resting-state electroencephalography can evaluate the ability of motor imagery; however, the effects of motor imagery and repetitive peripheral magnetic stimulation on resting-state electroencephalography are unknown. We examined the effects of motor imagery and repetitive peripheral magnetic stimulation on the vividness of motor imagery and resting-state electroencephalography. The participants were divided into a motor imagery group and motor imagery and repetitive peripheral magnetic stimulation group. They performed 60 motor imagery tasks involving wrist dorsiflexion movement. In the motor imagery and repetitive peripheral magnetic stimulation group, we applied repetitive peripheral magnetic stimulation to the extensor carpi radialis longus muscle during motor imagery. We measured the vividness of motor imagery and resting-state electroencephalography before and after the task. Both groups displayed a significant increase in the vividness of motor imagery. The motor imagery and repetitive peripheral magnetic stimulation group exhibited increased β activity in the anterior cingulate cortex by source localization for electroencephalography. Hence, combined motor imagery and repetitive peripheral magnetic stimulation changes the resting-state electroencephalography activity and may promote motor imagery.

Resting-State EEG in Alpha Rhythm May Be Indicative of the Performance of Motor Imagery-Based Brain-Computer Interface

Motor imagery-based brain-computer interfaces (MI-BCIs) have great application prospects in motor enhancement and rehabilitation. However, the capacity to control a MI-BCI varies among persons. Predicting the MI ability of a user remains challenging in BCI studies. We first calculated the relative power level (RPL), power spectral entropy (PSE) and Lempel-Ziv complexity (LZC) of the resting-state open and closed-eye EEG of different frequency bands and investigated their correlations with the upper and lower limbs MI performance (left hand, right hand, both hands and feet MI tasks) on as many as 105 subjects. Then, the most significant related features were used to construct a classifier to separate the high MI performance group from the low MI performance group. The results showed that the features of open-eye resting alpha-band EEG had the strongest significant correlations with MI performance. The PSE performed the best among all features for the screening of the MI performance, with the classification accuracy of 85.24%. These findings demonstrated that the alpha bands might offer information related to the user's MI ability, which could be used to explore more effective and general neural markers to screen subjects and design individual MI training strategies.

Multimodal resting-state connectivity predicts affective neurofeedback performance

Neurofeedback has been suggested as a potential complementary therapy to different psychiatric disorders. Of interest for this approach is the prediction of individual performance and outcomes. In this study, we applied functional connectivity-based modeling using electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) modalities to (i) investigate whether resting-state connectivity predicts performance during an affective neurofeedback task and (ii) evaluate the extent to which predictive connectivity profiles are correlated across EEG and fNIRS techniques. The fNIRS oxyhemoglobin and deoxyhemoglobin concentrations and the EEG beta and gamma bands modulated by the alpha frequency band (beta-m-alpha and gamma-m-alpha, respectively) recorded over the frontal cortex of healthy subjects were used to estimate functional connectivity from each neuroimaging modality. For each connectivity matrix, relevant edges were selected in a leave-one-subject-out procedure, summed into "connectivity summary scores" (CSS), and submitted as inputs to a support vector regressor (SVR). Then, the performance of the left-out-subject was predicted using the trained SVR model. Linear relationships between the CSS across both modalities were evaluated using Pearson's correlation. The predictive model showed a mean absolute error smaller than 20%, and the fNIRS oxyhemoglobin CSS was significantly correlated with the EEG gamma-m-alpha CSS (r = -0.456, p = 0.030). These results support that pre-task electrophysiological and hemodynamic resting-state connectivity are potential predictors of neurofeedback performance and are meaningfully coupled. This investigation motivates the use of joint EEG-fNIRS connectivity as outcome predictors, as well as a tool for functional connectivity coupling investigation.

A Novel Approach for Segment-Length Selection Based on Stationarity to Perform Effective Connectivity Analysis Applied to Resting-State EEG Signals

Connectivity among different areas within the brain is a topic that has been notably studied in the last decade. In particular, EEG-derived measures of effective connectivity examine the directionalities and the exerted influences raised from the interactions among neural sources that are masked out on EEG signals. This is usually performed by fitting multivariate autoregressive models that rely on the stationarity that is assumed to be maintained over shorter bits of the signals. However, despite being a central condition, the selection process of a segment length that guarantees stationary conditions has not been systematically addressed within the effective connectivity framework, and thus, plenty of works consider different window sizes and provide a diversity of connectivity results. In this study, a segment-size-selection procedure based on fourth-order statistics is proposed to make an informed decision on the appropriate window size that guarantees stationarity both in temporal and spatial terms. Specifically, kurtosis is estimated as a function of the window size and used to measure stationarity. A search algorithm is implemented to find the segments with similar stationary properties while maximizing the number of channels that exhibit the same properties and grouping them accordingly. This approach is tested on EEG signals recorded from six healthy subjects during resting-state conditions, and the results obtained from the proposed method are compared to those obtained using the classical approach for mapping effective connectivity. The results show that the proposed method highlights the influence that arises in the Default Mode Network circuit by selecting a window of 4 s, which provides, overall, the most uniform stationary properties across channels.

A Fusion-Based Technique With Hybrid Swarm Algorithm and Deep Learning for Biosignal Classification

The vital data about the electrical activities of the brain are carried by the electroencephalography (EEG) signals. The recordings of the electrical activity of brain neurons in a rhythmic and spontaneous manner from the scalp surface are measured by EEG. One of the most important aspects in the field of neuroscience and neural engineering is EEG signal analysis, as it aids significantly in dealing with the commercial applications as well. To uncover the highly useful information for neural classification activities, EEG studies incorporated with machine learning provide good results. In this study, a Fusion Hybrid Model (FHM) with Singular Value Decomposition (SVD) Based Estimation of Robust Parameters is proposed for efficient feature extraction of the biosignals and to understand the essential information it has for analyzing the brain functionality. The essential features in terms of parameter components are extracted using the developed hybrid model, and a specialized hybrid swarm technique called Hybrid Differential Particle Artificial Bee (HDPAB) algorithm is proposed for feature selection. To make the EEG more practical and to be used in a plethora of applications, the robust classification of these signals is necessary thereby relying less on the trained professionals. Therefore, the classification is done initially using the proposed Zero Inflated Poisson Mixture Regression Model (ZIPMRM) and then it is also classified with a deep learning methodology, and the results are compared with other standard machine learning techniques. This proposed flow of methodology is validated on a few standard Biosignal datasets, and finally, a good classification accuracy of 98.79% is obtained for epileptic dataset and 98.35% is obtained for schizophrenia dataset.

Neural Activation in the Ventromedial Prefrontal Cortex Precedes Conscious Experience of Being in or out of a Transient Hallucinatory State

BACKGROUND AND HYPOTHESES

Auditory verbal hallucinations (AVHs) is not only a common symptom in schizophrenia but also observed in individuals in the general population. Despite extensive research, AVHs are poorly understood, especially their underlying neuronal architecture. Neuroimaging methods have been used to identify brain areas and networks that are activated during hallucinations. A characteristic feature of AVHs is, however, that they fluctuate over time, with varying frequencies of starts and stops. An unanswered question is, therefore, what neuronal events co-occur with the initiation and inhibition of an AVH episode.

STUDY DESIGN

We investigated brain activation with fMRI in 66 individuals who experienced multiple AVH-episodes while in the scanner. We extracted time-series fMRI-data and monitored changes second-by-second from 10 s before to 15 s after participants indicated the start and stop of an episode, respectively, by pressing a hand-held response-button.

STUDY RESULTS

We found a region in the ventromedial prefrontal cortex (VMPFC) which showed a significant increase in activation initiated a few seconds before participants indicated the start of an episode, and a corresponding decrease in activation initiated a few seconds before the end of an episode.

CONCLUSIONS

The consistent increase and decrease in activation in this area in advance of the consciously experienced presence or absence of the "voice" imply that this region may act as a switch in turning episodes on and off. The activation is unlikely to be confounded by motor responses. The findings could have clinical implications for brain stimulation treatments, like transcranial magnetic stimulation.

Deep Residual Convolutional Neural Networks for Brain-Computer Interface to Visualize Neural Processing of Hand Movements in the Human Brain

Concomitant with the development of deep learning, brain-computer interface (BCI) decoding technology has been rapidly evolving. Convolutional neural networks (CNNs), which are generally used as electroencephalography (EEG) classification models, are often deployed in BCI prototypes to improve the estimation accuracy of a participant's brain activity. However, because most BCI models are trained, validated, and tested via within-subject cross-validation and there is no corresponding generalization model, their applicability to unknown participants is not guaranteed. In this study, to facilitate the generalization of BCI model performance to unknown participants, we trained a model comprising multiple layers of residual CNNs and visualized the reasons for BCI classification to reveal the location and timing of neural activities that contribute to classification. Specifically, to develop a BCI that can distinguish between rest, left-hand movement, and right-hand movement tasks with high accuracy, we created multilayers of CNNs, inserted residual networks into the multilayers, and used a larger dataset than in previous studies. The constructed model was analyzed with gradient-class activation mapping (Grad-CAM). We evaluated the developed model via subject cross-validation and found that it achieved significantly improved accuracy (85.69 ± 1.10%) compared with conventional models or without residual networks. Grad-CAM analysis of the classification of cases in which our model produced correct answers showed localized activity near the premotor cortex. These results confirm the effectiveness of inserting residual networks into CNNs for tuning BCI. Further, they suggest that recording EEG signals over the premotor cortex and some other areas contributes to high classification accuracy.

Motor Impairment in Stroke Patients is Associated with Network Properties During Consecutive Motor Imagery

OBJECTIVE

Our study aimed to predict the Fugl-Meyer assessment (FMA) upper limb using network properties during motor imagery using electroencephalography (EEG) signals.

METHODS

The subjects performed a finger tapping imagery task according to consecutive cues. We measured the weighted phase lag index (wPLI) as functional connectivity and directed transfer function (DTF) as causal connectivity in healthy controls and stroke patients. The network properties based on the wPLI and DTF were calculated. We predicted the FMA upper limb using partial least squares regression.

RESULTS

A higher DTF in the mu band was observed in stroke patients than in healthy controls. Notably, the difference in local properties at node F3 was negatively correlated with motor impairment in stroke patients. Finally, using significant network properties based on the wPLI and DTF, we predicted motor impairments using the FMA upper limb with a root-mean-square error of 1.68 (R² = 0.97). This outperformed the state-of-the-art predictors.

CONCLUSION

These findings demonstrate that network properties based on functional and causal connectivity were highly associated with motor function in stroke patients.

SIGNIFICANCE

Our network properties can help calculate the predictor of motor impairments in stroke rehabilitation and provide insight into the neural correlates related to motor function based on EEG after reorganization induced by stroke.

Brain functional and effective connectivity based on electroencephalography recordings: A review

Functional connectivity and effective connectivity of the human brain, representing statistical dependence and directed information flow between cortical regions, significantly contribute to the study of the intrinsic brain network and its functional mechanism. Many recent studies on electroencephalography (EEG) have been focusing on modeling and estimating brain connectivity due to increasing evidence that it can help better understand various brain neurological conditions. However, there is a lack of a comprehensive updated review on studies of EEG-based brain connectivity, particularly on visualization options and associated machine learning applications, aiming to translate those techniques into useful clinical tools. This article reviews EEG-based functional and effective connectivity studies undertaken over the last few years, in terms of estimation, visualization, and applications associated with machine learning classifiers. Methods are explored and discussed from various dimensions, such as either linear or nonlinear, parametric or nonparametric, time-based, and frequency-based or time-frequency-based. Then it is followed by a novel review of brain connectivity visualization methods, grouped by Heat Map, data statistics, and Head Map, aiming to explore the variation of connectivity across different brain regions. Finally, the current challenges of related research and a roadmap for future related research are presented.

Functional Connectivity Analysis in Motor-Imagery Brain Computer Interfaces

Motor Imagery BCI systems have a high rate of users that are not capable of modulating their brain activity accurately enough to communicate with the system. Several studies have identified psychological, cognitive, and neurophysiological measures that might explain this MI-BCI inefficiency. Traditional research had focused on mu suppression in the sensorimotor area in order to classify imagery, but this does not reflect the true dynamics that underlie motor imagery. Functional connectivity reflects the interaction between brain regions during the MI task and resting-state network and is a promising tool in improving MI-BCI classification. In this study, 54 novice MI-BCI users were split into two groups based on their accuracy and their functional connectivity was compared in three network scales (Global, Large and Local scale) during the resting-state, left vs. right-hand motor imagery task, and the transition between the two phases. Our comparison of High and Low BCI performers showed that in the alpha band, functional connectivity in the right hemisphere was increased in High compared to Low aptitude MI-BCI users during motor imagery. These findings contribute to the existing literature that indeed connectivity might be a valuable feature in MI-BCI classification and in solving the MI-BCI inefficiency problem.

Multi-Domain Convolutional Neural Networks for Lower-Limb Motor Imagery Using Dry vs. Wet Electrodes

Motor imagery (MI) brain–computer interfaces (BCIs) have been used for a wide variety of applications due to their intuitive matching between the user’s intentions and the performance of tasks. Applying dry electroencephalography (EEG) electrodes to MI BCI applications can resolve many constraints and achieve practicality. In this study, we propose a multi-domain convolutional neural networks (MD-CNN) model that learns subject-specific and electrode-dependent EEG features using a multi-domain structure to improve the classification accuracy of dry electrode MI BCIs. The proposed MD-CNN model is composed of learning layers for three domain representations (time, spatial, and phase). We first evaluated the proposed MD-CNN model using a public dataset to confirm 78.96% classification accuracy for multi-class classification (chance level accuracy: 30%). After that, 10 healthy subjects participated and performed three classes of MI tasks related to lower-limb movement (gait, sitting down, and resting) over two sessions (dry and wet electrodes). Consequently, the proposed MD-CNN model achieved the highest classification accuracy (dry: 58.44%; wet: 58.66%; chance level accuracy: 43.33%) with a three-class classifier and the lowest difference in accuracy between the two electrode types (0.22%, d = 0.0292) compared with the conventional classifiers (FBCSP, EEGNet, ShallowConvNet, and DeepConvNet) that used only a single domain. We expect that the proposed MD-CNN model could be applied for developing robust MI BCI systems with dry electrodes.

Effective Connectivity for Decoding Electroencephalographic Motor Imagery Using a Probabilistic Neural Network

Motor imagery (MI)-based brain-computer interfaces have gained much attention in the last few years. They provide the ability to control external devices, such as prosthetic arms and wheelchairs, by using brain activities. Several researchers have reported the inter-communication of multiple brain regions during motor tasks, thus making it difficult to isolate one or two brain regions in which motor activities take place. Therefore, a deeper understanding of the brain's neural patterns is important for BCI in order to provide more useful and insightful features. Thus, brain connectivity provides a promising approach to solving the stated shortcomings by considering inter-channel/region relationships during motor imagination. This study used effective connectivity in the brain in terms of the partial directed coherence (PDC) and directed transfer function (DTF) as intensively unconventional feature sets for motor imagery (MI) classification. MANOVA-based analysis was performed to identify statistically significant connectivity pairs. Furthermore, the study sought to predict MI patterns by using four classification algorithms-an SVM, KNN, decision tree, and probabilistic neural network. The study provides a comparative analysis of all of the classification methods using two-class MI data extracted from the PhysioNet EEG database. The proposed techniques based on a probabilistic neural network (PNN) as a classifier and PDC as a feature set outperformed the other classification and feature extraction techniques with a superior classification accuracy and a lower error rate. The research findings indicate that when the PDC was used as a feature set, the PNN attained the greatest overall average accuracy of 98.65%, whereas the same classifier was used to attain the greatest accuracy of 82.81% with the DTF. This study validates the activation of multiple brain regions during a motor task by achieving better classification outcomes through brain connectivity as compared to conventional features. Since the PDC outperformed the DTF as a feature set with its superior classification accuracy and low error rate, it has great potential for application in MI-based brain-computer interfaces.

Dynamic causal modeling of evoked responses during emergency braking: an ERP study

Describing a neural activity map based on observed responses in emergency situations, especially during driving, is a challenging issue that would help design driver-assistant devices and a better understanding of the brain. This study aimed to investigate which regions were involved during emergency braking, measuring the interactions and strength of the connections and describing coupling among these brain regions by dynamic causal modeling (DCM) parameters that we extracted from event-related potential signals, which were then estimated based on emergency braking data with visual stimulation. The data were reanalyzed from a simulator study, which was designed to create emergency situations for participants during a simple driving task. The experimental protocol includes driving a virtual reality car, and the subjects were exposed to emergency situations in a simulator system, while electroencephalogram, electro-oculogram, and electromyogram signals were recorded. In this research, locations of active brain regions in montreal neurological institute coordinates from event-related responses were identified using multiple sparse priors method, in which sensor space was allocated to resource space. Source localization results revealed nine active regions. After applying DCM on data, a proposed model during emergency braking for all people was obtained. The braking response time was defined based on the first noticeable (above noise-level) braking pedal deflection after an induced braking maneuver. The result revealed a significant difference in response time between subjects who have the lateral connection between visual cortex, visual processing, and detecting objects areas have shorter response time (p-value = 0.05) than the subjects who do not have such connections.

Effects of Frontal Theta Rhythms in a Prior Resting State on the Subsequent Motor Imagery Brain-Computer Interface Performance

Dealing with subjects who are unable to attain a proper level of performance, that is, those with brain–computer interface (BCI) illiteracy or BCI inefficients, is still a major issue in human electroencephalography (EEG) BCI systems. The most suitable approach to address this issue is to analyze the EEG signals of individual subjects independently recorded before the main BCI tasks, to evaluate their performance on these tasks. This study mainly focused on non-linear analyses and deep learning techniques to investigate the significant relationship between the intrinsic characteristics of a prior idle resting state and the subsequent BCI performance. To achieve this main objective, a public EEG motor/movement imagery dataset that constituted two individual EEG signals recorded from an idle resting state and a motor imagery BCI task was used in this study. For the EEG processing in the prior resting state, spectral analysis but also non-linear analyses, such as sample entropy, permutation entropy, and recurrent quantification analyses (RQA), were performed to obtain individual groups of EEG features to represent intrinsic EEG characteristics in the subject. For the EEG signals in the BCI tasks, four individual decoding methods, as a filter-bank common spatial pattern-based classifier and three types of convolution neural network-based classifiers, quantified the subsequent BCI performance in the subject. Statistical linear regression and ANOVA with post hoc analyses verified the significant relationship between non-linear EEG features in the prior resting state and three types of BCI performance as low-, intermediate-, and high-performance groups that were statistically discriminated by the subsequent BCI performance. As a result, we found that the frontal theta rhythm ranging from 4 to 8 Hz during the eyes open condition was highly associated with the subsequent BCI performance. The RQA findings that higher determinism and lower mean recurrent time were mainly observed in higher-performance groups indicate that more regular and stable properties in the EEG signals over the frontal regions during the prior resting state would provide a critical clue to assess an individual BCI ability in the following motor imagery task.

Deep and Wide Transfer Learning with Kernel Matching for Pooling Data from Electroencephalography and Psychological Questionnaires

Motor imagery (MI) promotes motor learning and encourages brain–computer interface systems that entail electroencephalogram (EEG) decoding. However, a long period of training is required to master brain rhythms’ self-regulation, resulting in users with MI inefficiency. We introduce a parameter-based approach of cross-subject transfer-learning to improve the performances of poor-performing individuals in MI-based BCI systems, pooling data from labeled EEG measurements and psychological questionnaires via kernel-embedding. To this end, a Deep and Wide neural network for MI classification is implemented to pre-train the network from the source domain. Then, the parameter layers are transferred to initialize the target network within a fine-tuning procedure to recompute the Multilayer Perceptron-based accuracy. To perform data-fusion combining categorical features with the real-valued features, we implement stepwise kernel-matching via Gaussian-embedding. Finally, the paired source–target sets are selected for evaluation purposes according to the inefficiency-based clustering by subjects to consider their influence on BCI motor skills, exploring two choosing strategies of the best-performing subjects (source space): single-subject and multiple-subjects. Validation results achieved for discriminant MI tasks demonstrate that the introduced Deep and Wide neural network presents competitive performance of accuracy even after the inclusion of questionnaire data.

Decoding Imagined Speech Based on Deep Metric Learning for Intuitive BCI Communication

Imagined speech is a highly promising paradigm due to its intuitive application and multiclass scalability in the field of brain-computer interfaces. However, optimal feature extraction and classifiers have not yet been established. Furthermore, retraining still requires a large number of trials when new classes are added. The aim of this study is (i) to increase the classification performance for imagined speech and (ii) to apply a new class using a pretrained classifier with a small number of trials. We propose a novel framework based on deep metric learning that learns the distance by comparing the similarity between samples. We also applied the instantaneous frequency and spectral entropy used for speech signals to electroencephalography signals during imagined speech. The method was evaluated on two public datasets (6-class Coretto DB and 5-class BCI Competition DB). We achieved a 6-class accuracy of 45.00 ± 3.13% and a 5-class accuracy of 48.10 ± 3.68% using the proposed method, which significantly outperformed state-of-the-art methods. Additionally, we verified that the new class could be detected through incremental learning with a small number of trials. As a result, the average accuracy is 44.50 ± 0.26% for Coretto DB and 47.12 ± 0.27% for BCI Competition DB, which shows similar accuracy to baseline accuracy without incremental learning. Our results have shown that the accuracy can be greatly improved even with a small number of trials by selecting appropriate features from imagined speech. The proposed framework could be directly used to help construct an extensible intuitive communication system based on brain-computer interfaces.

Vividness of Visual Imagery and Personality Impact Motor-Imagery Brain Computer Interfaces

Brain-computer interfaces (BCIs) are communication bridges between a human brain and external world, enabling humans to interact with their environment without muscle intervention. Their functionality, therefore, depends on both the BCI system and the cognitive capacities of the user. Motor-imagery BCIs (MI-BCI) rely on the users' mental imagination of body movements. However, not all users have the ability to sufficiently modulate their brain activity for control of a MI-BCI; a problem known as BCI illiteracy or inefficiency. The underlying mechanism of this phenomenon and the cause of such difference among users is yet not fully understood. In this study, we investigated the impact of several cognitive and psychological measures on MI-BCI performance. Fifty-five novice BCI-users participated in a left- versus right-hand motor imagery task. In addition to their BCI classification error rate and demographics, psychological measures including personality factors, affinity for technology, and motivation during the experiment, as well as cognitive measures including visuospatial memory and spatial ability and Vividness of Visual Imagery were collected. Factors that were found to have a significant impact on MI-BCI performance were Vividness of Visual Imagery, and the personality factors of orderliness and autonomy. These findings shed light on individual traits that lead to difficulty in BCI operation and hence can help with early prediction of inefficiency among users to optimize training for them.

Deep Neural Regression Prediction of Motor Imagery Skills Using EEG Functional Connectivity Indicators

Motor imaging (MI) induces recovery and neuroplasticity in neurophysical regulation. However, a non-negligible portion of users presents insufficient coordination skills of sensorimotor cortex control. Assessments of the relationship between wakefulness and tasks states are conducted to foster neurophysiological and mechanistic interpretation in MI-related applications. Thus, to understand the organization of information processing, measures of functional connectivity are used. Also, models of neural network regression prediction are becoming popular, These intend to reduce the need for extracting features manually. However, predicting MI practicing's neurophysiological inefficiency raises several problems, like enhancing network regression performance because of the overfitting risk. Here, to increase the prediction performance, we develop a deep network regression model that includes three procedures: leave-one-out cross-validation combined with Monte Carlo dropout layers, subject clustering of MI inefficiency, and transfer learning between neighboring runs. Validation is performed using functional connectivity predictors extracted from two electroencephalographic databases acquired in conditions close to real MI applications (150 users), resulting in a high prediction of pretraining desynchronization and initial training synchronization with adequate physiological interpretability.