Personalized µ-transcranial alternating current stimulation improves online brain–computer interface control

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

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.

Human cooperation relies on key features of social interaction in order to reach desirable outcomes. Similarly, human-robot interaction may benefit from integration with human-human interaction factors. In this paper, we aim to investigate brain-to-brain coupling during motor imagery (MI)-based brain-computer interface (BCI) training using eye-contact and hand-touch interaction. Twelve pairs of friends (experimental group) and 10 pairs of strangers (control group) were recruited for MI-based BCI tests concurrent with electroencephalography (EEG) hyperscanning. Event-related desynchronization (ERD) was estimated to measure cortical activation, and interbrain functional connectivity was assessed using multilevel statistical analysis. Furthermore, we compared BCI classification performance under different social interaction conditions. In the experimental group, greater ERD was found around the contralateral sensorimotor cortex under social interaction conditions compared with MI without any social interaction. Notably, EEG channels with decreased power were mainly distributed around the frontal, central, and occipital regions. A significant increase in interbrain coupling was also found under social interaction conditions. BCI decoding accuracies were significantly improved in the eye contact condition and eye and hand contact condition compared with the no-interaction condition. However, for the strangers' group, no positive effects were observed in comparisons of cortical activations between interaction and no-interaction conditions. These findings indicate that social interaction can improve the neural synchronization between familiar partners with enhanced brain activations and brain-to-brain coupling. This study may provide a novel method for enhancing MI-based BCI performance in conjunction with neural synchronization between users.

Currently, the operational electroencephalography (EEG)-based brain–computer interfaces (BCIs) suffer from problems of BCI latency/lag issues, which restricts the use of interfaces impractical scenarios. One of the reasons behind the present challenges is the application of a purely data-driven approach to the BCI pipeline. Although BCI applications have improved significantly with the research in the fields of artificial intelligence (AI) and machine learning (ML), fundamental issues of data-driven training restrict the latency that can be achieved under current BCI paradigms. This work explores the possibility of future BCI using a combination of data-driven and theory-driven methods. In this study, an EEG-BCI dataset from steady-state visually evoked potentials (SSVEPs) is applied, where the SSVEP signals contain, source components from the occipital, parietal and frontal regions of the brain. Source reconstruction is done with the combination of independent component analysis (ICA) and low-resolution electromagnetic tomography analysis (LORETA). This method was able to predict BCI classification labels 5[Formula: see text]s earlier, based on pre-recorded signals from the scalp. The novelty of the current contribution lies in utilizing the source reconstructed EEG time-series for BCI classification, which allows for retention of classification accuracy up to 70% while working with the reduced data dimensionality. Implementation of this algorithm will allow a significant reduction in lag in online BCIs.

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.

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

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

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.

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.

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.

Brain–computer interface controlled gaming: Evaluation of usability by severely motor restricted end-users

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.

Introduction: This current study is part of a larger, on-going clinical trial (NCT02098265), which evaluates non-invasive electroencephalographic (EEG) based brain-computer interface(BCI) therapy for restoration of distal upper extremity motor function in stroke survivors. We acquired data for 8 participants (mean age= 64 years) presenting with varying levels of upper-extremity motor deficits and chronicity since stroke. EEG based BCI task-related performance outcomes were compared with distal extremity behavioral testing on the 9-Hole Peg Test - 9HPT) to illustrate the relationship of BCI training performance on behavioral performance. Methods: EEG data is acquired with BCI2000, a 16 channel recording system (g.LADYbird-g. GAMMAsys-g. USBamp, Guger Technologies, Graz, Austria) with electrodes positioned according to the standard 10-20 system over the sensorimotor cortex at C3 & C4. Participants performed a hand movement task; randomly cued to move either their affected or unaffected hand depending on the appearance of virtual target and cursor on the screen. 9HPT Data was selected from two BCI conditions: 1) BCI with visual stimulus only, and 2) BCI with visual stimulation plus functional electrical stimulation (FES) of the impaired arm, and tongue stimulation (TS) at four time-points: baseline (prior to BCI therapy), mid-point of BCI therapy, post-therapy, and one month post-therapy. Results: BCI visual plus stimulus for the unaffected side was found to best relate to 9HPT scores (p= 0.0928) with a trend to significance. BCI visual plus stimulus for the affected side was not shown to correlate with 9HPT scores (p= 0.2655). The results suggest that 9HPT scores better relate with average task accuracy when the TS and FES adjuvants are incorporated (BCI stimulus vs 9H PT unaffected p= 0.09284, BCI stimulus vs 9H PT affected p= 0.26553) compared to the BCI visual only task (BCI visual vs 9HPT unaffected p=0.2702, BCI visual vs 9HPT affected (p= 0.89276). Conclusion: Non-invasive EEG-based BCI therapy may be suitable for the restoration of distal upper extremity motor function but average task accuracy does not appear to be a valid indicator of motor improvement. This finding suggests that visual only BCI systems are inadequate for motor rehabilitation.

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.

BCI is a strong tool that improves human-system communication. It improves the brain's ability to interact with its surroundings. Recent decades have seen substantial advances in neuroscience and computer science. This has made BCI a leader in computational neuroscience and intelligence research. Recent technological advances including wearable sensing devices, real-time data streaming, machine learning, and deep learning have raised the need for electroencephalographic (EEG)-based brain-computer interface (BCI) in clinical and translational applications. EEG-based Brain-Computer Interfaces (BCIs) detect cognitive state variations throughout laborious tasks, making them advantageous for individuals. To fill in the gaps in the wide overview of the past five years (2019-2024), we surveyed the newest research on EEG signal detection and computational intelligence in brain-computer interfaces. To provide a more accurate account, we will begin by reviewing Brain-Computer Interface (BCI) technology and its main challenges. Modern signal detection and enhancement techniques for EEG signal collection and refinement follow. We also provide advanced computational intelligence methods for tracking, maintaining, and monitoring human cognitive and operational performance in everyday applications. Combinations, interpretable fuzzy models, transfer learning, and deep learning are used. We conclude with a sample of cutting-edge BCI-driven healthcare applications and explore future EEG-based BCI research.