Enhancing Brain-Computer Interface Performance by Incorporating Brain-to-Brain Coupling.

The study aimed to compare the effects of combined action observation and motor imagery (AOMI) and motor imagery (MI)-based brain-computer interface (BCI) training on upper limb recovery, cortical excitation, and cognitive task performance in chronic stroke patients. 17 chronic stroke patients were recruited and randomly assigned to AOMI-based BCI (n = 9) and MI-based BCI groups (n = 8). The AOMI-based BCI group received AOMI-based BCI training via functional electrical stimulation (FES) feedback, whereas the MI-based BCI group obtained MI-based BCI training via FES feedback. Both groups participated in training for 12 sessions (3 days/week, consecutive four weeks). To evaluate upper limb function recovery, the Fugl–Meyer Assessment for upper extremity (FMA-UE) was employed. Event-related desynchronization (ERD) and online classification accuracy were utilized to measure cortical excitation of the affected sensorimotor hand region and cognitive task performance, respectively. Both AOMI and MI-based BCI training improved upper limb function in chronic stroke patients. However, the AOMI-based BCI group showed significantly greater motor gain than the MI-based BCI group. In addition, the AOMI-based BCI group demonstrated significantly greater cortical excitation of the affected sensorimotor hand region and cognitive task performance. The correlation analysis revealed that higher cognitive task performance during AOMI-based BCI training may promote greater cortical excitation of the affected sensorimotor hand region, which contributes to greater upper limb function improvement compared to MI-based BCI training.

Correlation-based channel selection and regularized feature optimization for MI-based BCI

Objective.A motor imagery (MI)-based brain-computer interface (BCI) enables users to engage with external environments by capturing and decoding electroencephalography (EEG) signals associated with the imagined movement of specific limbs. Despite significant advancements in BCI technologies over the past 40 years, a notable challenge remains: many users lack BCI proficiency, unable to produce sufficiently distinct and reliable MI brain patterns, hence leading to low classification rates in their BCIs. The objective of this study is to enhance the online performance of MI-BCIs in a personalized, biomarker-driven approach using transcranial alternating current stimulation (tACS).Approach.Previous studies have identified that the peak power spectral density value in sensorimotor idling rhythms is a neural correlate of participants' upper limb MI-BCI performances. In this active-controlled, single-blind study, we applied 20 min of tACS at the participant-specific, peakµfrequency in resting-state sensorimotor rhythms (SMRs), with the goal of enhancing resting-stateµSMRs.Main results.After tACS, we observed significant improvements in event-related desynchronizations (ERDs) ofµSMRs, and in the performance of an online MI-BCI that decodes left versus right hand commands in healthy participants (N= 10)-but not in an active control-stimulation control group (N= 10). Lastly, we showed a significant correlation between the resting-stateµSMRs andµERD, offering a mechanistic interpretation behind the observed changes in online BCI performances.Significance.Our research lays the groundwork for future non-invasive interventions designed to enhance BCI performances, thereby improving the independence and interactions of individuals who rely on these systems.

The accuracy of the classification of user intentions is essential for motor imagery (MI)-based brain-computer interface (BCI). Effective and appropriate training for users could help us produce the high reliability of mind decision making related with MI tasks. In this study, we aimed to investigate the effects of visual guidance on the classification performance of MI-based BCI. In this study, leveraging both the single-subject and the multi-subject BCI paradigms, we train and classify MI tasks with three different scenarios in a 3D virtual environment, including non-object-directed scenario, static-object-directed scenario, and dynamic object-directed scenario. Subjects are required to imagine left-hand or right-hand movement with the visual guidance. We demonstrate that the classification performances of left-hand and right-hand MI task have differences on these three scenarios, and confirm that both static-object-directed and dynamic object-directed scenarios could provide better classification accuracy than the non-object-directed case. We further indicate that both static-object-directed and dynamic object-directed scenarios could shorten the response time as well as be suitable applied in the case of small training data. In addition, experiment results demonstrate that the multi-subject BCI paradigm could improve the classification performance comparing with the single-subject paradigm. These results suggest that it is possible to improve the classification performance with the appropriate visual guidance and better BCI paradigm. We believe that our findings would have the potential for improving classification performance of MI-based BCI and being applied in the practical applications.

F190. Mindfulness based stress reduction’s influence on brain-computer interface control

Motor imagery (MI) based brain-computer interfaces (BCIs) enable the direct control of external devices through the imagined movements of various body parts. Unlike previous systems that used fixed-length EEG trials for MI decoding, asynchronous BCIs aim to detect the user's MI without explicit triggers. They are challenging to implement, because the algorithm needs to first distinguish between resting-states and MI trials, and then classify the MI trials into the correct task, all without any triggers. This paper proposes a sliding window prescreening and classification (SWPC) approach for MI-based asynchronous BCIs, which consists of two modules: a prescreening module to screen MI trials out of the resting-state, and a classification module for MI classification. Both modules are trained with supervised learning followed by self-supervised learning, which refines the feature extractors. Within-subject and cross-subject asynchronous MI classifications on four different EEG datasets validated the effectiveness of SWPC, i.e., it always achieved the highest average classification accuracy, and outperformed the best state-of-the-art baseline on each dataset by about 2%.

A electroencephalography (EEG) based braincomputer interface (BCI) provides a communication channel to operate the external environment by decoding brain patterns. Movement-Related Cortical Potentials (MRCPs) are one particular type of EEG pattern during movement of peripheral limbs. The performance of motor imagery (MI) is related to pattern of MRCPs by planning simulation. In resent decade, MI-based BCI have shown potential as its performance significantly improved. In this study, the feasibility of selected-based method was proposed by compared with conventional method. The detection accuracy overall performances were $72.42\pm 3.12\%$ . When a top 97.8% trial is selected, overall performance improved approximately 3.15% compared to baseline. When MI were analyzed in non-selected trials, C3 and C4 channel showed no different aspects in left and right class respectively. The brain state was changed after the cue appeared, and these power of delta band appeared in all subjects. The performance of classification was improved by rejecting trials with no difference between the state before and after cue.

Electroencephalogram (EEG) based brain-computer interfaces (BCIs) for wheelchair control have great value for those with devastating neuromuscular disorders. Although there have been many attempts to implement EEG-based wheelchair control systems by P300, steady state visual evoked potential (SSVEP), and motor imagery (MI) related event-related desynchronization/synchronization (ERD/ERS), the number of simultaneous control commands in those BCI systems is strictly limited, and those BCI control do not work for a non-negligible portion of users due to the problem of BCI Illiteracy.In this paper, we develop a multimodal BCI based wheelchair control system, the user could employ subject-optimized mental strategies to produce multiple commands to control the wheelchair, which include ERD/ERS, SSVEP, and simultaneous ERD/ERS and SSVEP. It could not only help address ”BCI illiteracy”, but also provide simultaneous control commands for complex control. Experiment results demonstrate the proposed system is effective and flexible in practical application.KeywordsBCIwheelchair controlmultimodalBCI Illiteracy

Improved motor imagery brain-computer interface performance via adaptive modulation filtering and two-stage classification

Performance of motor imagery (MI)-based brain computer interfaces (BCIs) highly depends on the extraction of features from different brain neural processes. Commonly designed BCIs use band power changes in single channel electroencephalograms (EEGs) to discriminate different MI tasks. In this paper, we studied the information about interactions of spatially separated brain areas by considering the relationships between brain source signals through functional connectivity. We investigated dynamic time-frequency connectivity patterns during four motor imagery movements including left hand, right hand, both feet and tongue by means of Coherence measure estimated from multivariate adaptive autoregressive model coefficients. To tackle the volume conduction problem, sensor space signals were transformed into source space using independent component analysis technique. We showed distinct time-varying Coherence for different motor imageries. For tongue MI movement, bilateral connectivity was observed in hand areas of both hemispheres. The similar connectivity was detected for feet MI task, but with more focus on right hemisphere. During right and left hand MI, bilateral and contralateral brain connectivities were observed respectively. Results provided valuable information for possible classification of MI tasks by considering brain source functional connectivity patterns for BCIs.

Objective. Channel selection in the electroencephalogram (EEG)-based brain–computer interface (BCI) has been extensively studied for over two decades, with the goal being to select optimal subject-specific channels that can enhance the overall decoding efficacy of the BCI. With the emergence of deep learning (DL)-based BCI models, there arises a need for fresh perspectives and novel techniques to conduct channel selection. In this regard, subject-independent channel selection is relevant, since DL models trained using cross-subject data offer superior performance, and the impact of inherent inter-subject variability of EEG characteristics on subject-independent DL training is not yet fully understood. Approach. Here, we propose a novel methodology for implementing subject-independent channel selection in DL-based motor imagery (MI)-BCI, using layer-wise relevance propagation (LRP) and neural network pruning. Experiments were conducted using Deep ConvNet and 62-channel MI data from the Korea University EEG dataset. Main Results. Using our proposed methodology, we achieved a 61% reduction in the number of channels without any significant drop (p = 0.09) in subject-independent classification accuracy, due to the selection of highly relevant channels by LRP. LRP relevance-based channel selections provide significantly better accuracies compared to conventional weight-based selections while using less than 40% of the total number of channels, with differences in accuracies ranging from 5.96% to 1.72%. The performance of the adapted sparse-LRP model using only 16% of the total number of channels is similar to that of the adapted baseline model (p = 0.13). Furthermore, the accuracy of the adapted sparse-LRP model using only 35% of the total number of channels exceeded that of the adapted baseline model by 0.53% (p = 0.81). Analyses of channels chosen by LRP confirm the neurophysiological plausibility of selection, and emphasize the influence of motor, parietal, and occipital channels in MI-EEG classification. Significance. The proposed method addresses a traditional issue in EEG-BCI decoding, while being relevant and applicable to the latest developments in the field of BCI. We believe that our work brings forth an interesting and important application of model interpretability as a problem-solving technique.

Motor Imagery (MI)-based Brain Computer Interface (BCI) system is a potential technology for active neurorehabilitation of stroke patients by complementing the conventional passive rehabilitation methods. Research to date mainly focused on classifying left vs. right hand/foot MI of stroke patients. Though a very few studies have reported decoding imagined hand movement directions using electroencephalogram (EEG)-based BCI, the experiments were conducted on healthy subjects. Our work analyzes MI-based brain cortical activity from EEG signals and decodes the imagined hand movement directions in stroke patients. The decoded direction (left vs. right) of hand movement imagination is used to provide control commands to a motorized arm support on which patient's affected (paralyzed) arm is placed. This enables the patient to move his/her stroke-affected hand towards the intended (imagined) direction that aids neuroplasticity in the brain. The synchronization measure called Phase Locking Value (PLV), extracted from EEG, is the neuronal signature used to decode the directional movement of the MI task. Event-related desynchronization/synchronization (ERD/ERS) analysis on Mu and Beta frequency bands of EEG is done to select the time bin corresponding to the MI task. The dissimilarities between the two directions of MI tasks are identified by selecting the most significant channel pairs that provided maximum difference in PLV features. The training protocol has an initial calibration session followed by a feedback session with 50 trials of MI task in each session. The feedback session extracts PLV features corresponding to most significant channel pairs which are identified in the calibration session and is used to predict the direction of MI task in left/right direction. An average MI direction classification accuracy of 74.44% is obtained in performing the training protocol and 68.63% from the prediction protocol during feedback session on 16 stroke patients.

Online coadaptive training has been successfully employed to enable people to control motor imagery (MI)-based brain-computer interfaces (BCIs), allowing to completely skip the lengthy and demotivating open-loop calibration stage traditionally applied before closed-loop control. However, practical reasons may often dictate to eventually switch off decoder adaptation and proceed with BCI control under a fixed BCI model, a situation that remains rather unexplored. This work studies the existence and magnitude of potential post-adaptation effects on system performance, subject learning and brain signal modulation stability in a state-of-the-art, coadaptive training regime inspired by a game-like design. The results extracted in a cohort of 20 able-bodied individuals reveal that ceasing classifier adaptation after three runs (approx. 30 min) of a single-session training protocol had no significant impact on any of the examined BCI control and learning aspects in the remaining two runs (about 20 min) with a fixed classifier. Fifteen individuals achieved accuracies that are better than chance level and allowed them to successfully execute the given task. These findings alleviate a major concern regarding the applicability of coadaptive MI BCI training, thus helping to further establish this training approach and allow full exploitation of its benefits.

The electroencephalogram (EEG) based Brain-Computer Interfaces (BCIs) has been considerably extended to the multidisciplinary and challenging nature of BCI study. The algorithms of Digital signal processing and pattern recognition certainly constitute necessary components of a BCI system which are applied to the EEG signals to decode mental states those are relevant for BCI operation. The basic BCI concepts such as: brain activity monitoring, BCI operation, and the relevant mental states for BCI are applied to WSN. The major types of relevant mental states for BCI, namely motor imagery (ERD/ERS), steady state visual evoked potentials (SSVEP) are also mapped to MANET’s behaviour. The multivariate nature of the EEG combined with the neuroscience familiarity on hemispheric brain specialization is favourably taken into account to derive optimal combinations of the individual signals composing the EEG. BCI provides a non-muscular channel for sending commands to the external world using the electroencephalographic activity or other electrophysiological process of the brain function. A necessary factor in the successful operation of BCI systems is the methods used to process the brain signals. The processed data has been applied on to nodes of MANET where each set of sensor nodes are used for particular application. Based on the output of BCI commands, the MANET is operated and controlled with using only activities of neurons of brain, hence this approach could be more helpful to physically differently abled people or medically injured people.

Advances in the motor imagery (MI)-based brain-computer interfaces (BCIs) allow control of several applications by decoding neurophysiological phenomena, which are usually recorded by electroencephalography (EEG) using a non-invasive technique. Despite significant advances in MI-based BCI, EEG rhythms are specific to a subject and various changes over time. These issues point to significant challenges to enhance the classification performance, especially in a subject-independent manner. To overcome these challenges, we propose MIN2Net, a novel end-to-end multi-task learning to tackle this task. We integrate deep metric learning into a multi-task autoencoder to learn a compact and discriminative latent representation from EEG and perform classification simultaneously. This approach reduces the complexity in pre-processing, results in significant performance improvement on EEG classification. Experimental results in a subject-independent manner show that MIN2Net outperforms the state-of-the-art techniques, achieving an F1-score improvement of 6.72% and 2.23% on the SMR-BCI and OpenBMI datasets, respectively. We demonstrate that MIN2Net improves discriminative information in the latent representation. This study indicates the possibility and practicality of using this model to develop MI-based BCI applications for new users without calibration.