Ongoing EEG artifact correction using blind source separation

OBJECTIVE

Analysis of the electroencephalogram (EEG) for epileptic spike and seizure detection or brain-computer interfaces can be severely hampered by the presence of artifacts. The aim of this study is to describe and evaluate a fast automatic algorithm for ongoing correction of artifacts in continuous EEG recordings, which can be applied offline and online.

METHODS

The automatic algorithm for ongoing correction of artifacts is based on fast blind source separation. It uses a sliding window technique with overlapping epochs and features in the spatial, temporal and frequency domain to detect and correct ocular, cardiac, muscle and powerline artifacts.

RESULTS

The approach was validated in an independent evaluation study on publicly available continuous EEG data with 2035 marked artifacts. Validation confirmed that 88% of the artifacts could be removed successfully (ocular: 81%, cardiac: 84%, muscle: 98%, powerline: 100%). It outperformed state-of-the-art algorithms both in terms of artifact reduction rates and computation time.

CONCLUSIONS

Fast ongoing artifact correction successfully removed a good proportion of artifacts, while preserving most of the EEG signals.

SIGNIFICANCE

The presented algorithm may be useful for ongoing correction of artifacts, e.g., in online systems for epileptic spike and seizure detection or brain-computer interfaces.

ETCNet: An EEG-based motor imagery classification model combining efficient channel attention and temporal convolutional network

Brain-computer interface (BCI) enables the control of external devices using signals from the brain, offering immense potential in assisting individuals with neuromuscular disabilities. Among the different paradigms of BCI systems, the motor imagery (MI) based electroencephalogram (EEG) signal is widely recognized as exceptionally promising. Deep learning (DL) has found extensive applications in the processing of MI signals, wherein convolutional neural networks (CNN) have demonstrated superior performance compared to conventional machine learning (ML) approaches. Nevertheless, challenges related to subject independence and subject dependence persist, while the inherent low signal-to-noise ratio of EEG signals remains a critical aspect that demands attention. Accurately deciphering intentions from EEG signals continues to present a formidable challenge. This paper introduces an advanced end-to-end network that effectively combines the efficient channel attention (ECA) and temporal convolutional network (TCN) components for the classification of motor imagination signals. We incorporated an ECA module prior to feature extraction in order to enhance the extraction of channel-specific features. A compact convolutional network model uses for feature extraction in the middle part. Finally, the time characteristic information is obtained by using TCN. The results show that our network is a lightweight network that is characterized by few parameters and fast speed. Our network achieves an average accuracy of 80.71% on the BCI Competition IV-2a dataset.

A time segment adaptive optimization method based on separability criterion and correlation analysis for motor imagery BCIs

Motor imagery (MI) plays a crucial role in brain-computer interface (BCI), and the classification of MI tasks using electroencephalogram (EEG) is currently under extensive investigation. During MI classification, individual differences among subjects in terms of response and time latency need to be considered. Optimizing the time segment for different subjects can enhance subsequent classification performance. In view of the individual differences of subjects in motor imagery tasks, this article proposes a Time Segment Adaptive Optimization method based on Separability criterion and Correlation analysis (TSAOSC). The fundamental principle of this method involves applying the separability criterion to various sizes of time windows within the training data, identifying the optimal raw reference signal, and adaptively adjusting the time segment position for each trial's data by analyzing its relationship with the optimal reference signal. We evaluated our method on three BCI competition datasets, respectively. The utilization of the TSAOSC method in the experiments resulted in an enhancement of 4.90% in average classification accuracy compared to its absence. Additionally, building upon the TSAOSC approach, this study proposes a Nonlinear-TSAOSC method (N-TSAOSC) for analyzing EEG signals with nonlinearity, which shows improvements in the classification accuracy of certain subjects. The results of the experiments demonstrate that the proposed method is an effective time segment optimization method, and it can be integrated into other algorithms to further improve their accuracy.

Effect of motion state variability on error-related potentials during continuous feedback paradigms and their consequences for classification

BACKGROUND

An erroneous motion would elicit the error-related potential (ErrP) when humans monitor the behavior of the external devices. This EEG modality has been largely applied to brain-computer interface in an active or passive manner with discrete visual feedback. However, the effect of variable motion state on ErrP morphology and classification performance raises concerns when the interaction is conducted with continuous visual feedback.

NEW METHOD

In the present study, we designed a cursor control experiment. Participants monitored a continuously moving cursor to reach the target on one side of the screen. Motion state varied multiple times with two factors: (1) motion direction and (2) motion speed. The effects of these two factors on the morphological characteristics and classification performance of ErrP were analyzed. Furthermore, an offline simulation was performed to evaluate the effectiveness of the proposed extended ErrP-decoder in resolving the interference by motion direction changes.

RESULTS

The statistical analyses revealed that motion direction and motion speed significantly influenced the amplitude of feedback-ERN and frontal-Pe components, while only motion direction significantly affected the classification performance.

COMPARISON WITH EXISTING METHODS

Significant deviation was found in ErrP detection utilizing classical correct-versus-erroneous event training. However, this bias can be alleviated by 16% by the extended ErrP-decoder.

CONCLUSION

The morphology and classification performance of ErrP signal can be affected by motion state variability during continuous feedback paradigms. The results enhance the comprehension of ErrP morphological components and shed light on the detection of BCI's error behavior in practical continuous control.

Exploring the effects of different BCI-based attention training games on the brain: A functional near-infrared spectroscopy study

BCI games have been widely employed as non-invasive therapeutic interventions for conditions, but their efficacy remains a subject of debate. This study explores the efficacy of two prevalent forms of Brain-Computer Interface (BCI)-based attention training games: video games (VG) and physical games (PG). The effectiveness of these games has been examined through the lens of neuroscience, using functional Near-Infrared Spectroscopy (fNIRS) to monitor cortical activation. After the fNIRS test, subjects completed an Intrinsic Motivation Inventory (IMI) questionnaire. PG tasks activated six channels (L-PFC, R-PFC and R-TL), while VG tasks activated only one (R-PFC). Furthermore, females exhibited stronger activation during PG tasks, while males had none in either. Our findings suggest that under equivalent game rules and themes, PG may prove more effective for cognitive rehabilitation than VG, with stronger intrinsic motivation. We also found this result may exhibit gender differences. Finally, this research offers valuable insights for the future design of BCI-based games from a neuroscience perspective.

TSANet: multibranch attention deep neural network for classifying tactile selective attention in brain-computer interfaces

Brain-computer interfaces (BCIs) enable communication between the brain and a computer and electroencephalography (EEG) has been widely used to implement BCIs because of its high temporal resolution and noninvasiveness. Recently, a tactile-based EEG task was introduced to overcome the current limitations of visual-based tasks, such as visual fatigue from sustained attention. However, the classification performance of tactile-based BCIs as control signals is unsatisfactory. Therefore, a novel classification approach is required for this purpose. Here, we propose TSANet, a deep neural network, that uses multibranch convolutional neural networks and a feature-attention mechanism to classify tactile selective attention (TSA) in a tactile-based BCI system. We tested TSANet under three evaluation conditions, namely, within-subject, leave-one-out, and cross-subject. We found that TSANet achieved the highest classification performance compared with conventional deep neural network models under all evaluation conditions. Additionally, we show that TSANet extracts reasonable features for TSA by investigating the weights of spatial filters. Our results demonstrate that TSANet has the potential to be used as an efficient end-to-end learning approach in tactile-based BCIs.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13534-023-00309-4.

Conversion of a medical implant into a versatile computer-brain interface

BACKGROUND

Information transmission into the human nervous system is the basis for a variety of prosthetic applications. Spinal cord stimulation (SCS) systems are widely available, have a well documented safety record, can be implanted minimally invasively, and are known to stimulate afferent pathways. Nonetheless, SCS devices are not yet used for computer-brain-interfacing applications.

OBJECTIVE

Here we aimed to establish computer-to-brain communication via medical SCS implants in a group of 20 individuals who had been operated for the treatment of chronic neuropathic pain.

METHODS

In the initial phase, we conducted interface calibration with the aim of determining personalized stimulation settings that yielded distinct and reproducible sensations. These settings were subsequently utilized to generate inputs for a range of behavioral tasks. We evaluated the required calibration time, task training duration, and the subsequent performance in each task.

RESULTS

We could establish a stable spinal computer-brain interface in 18 of the 20 participants. Each of the 18 then performed one or more of the following tasks: A rhythm-discrimination task (n = 13), a Morse-decoding task (n = 3), and/or two different balance/body-posture tasks (n = 18; n = 5). The median calibration time was 79 min. The median training time for learning to use the interface in a subsequent task was 1:40 min. In each task, every participant demonstrated successful performance, surpassing chance levels.

CONCLUSION

The results constitute the first proof-of-concept of a general purpose computer-brain interface paradigm that could be deployed on present-day medical SCS platforms.

[Research progress of brain-computer interface application paradigms based on rapid serial visual presentation]

Rapid serial visual presentation (RSVP) is a type of psychological visual stimulation experimental paradigm that requires participants to identify target stimuli presented continuously in a stream of stimuli composed of numbers, letters, words, images, and so on at the same spatial location, allowing them to discern a large amount of information in a short period of time. The RSVP-based brain-computer interface (BCI) can not only be widely used in scenarios such as assistive interaction and information reading, but also has the advantages of stability and high efficiency, which has become one of the common techniques for human-machine intelligence fusion. In recent years, brain-controlled spellers, image recognition and mind games are the most popular fields of RSVP-BCI research. Therefore, aiming to provide reference and new ideas for RSVP-BCI related research, this paper reviewed the paradigm design and system performance optimization of RSVP-BCI in these three fields. It also looks ahead to its potential applications in cutting-edge fields such as entertainment, clinical medicine, and special military operations.

[Recognition of motor imagery electroencephalogram based on flicker noise spectroscopy and weighted filter bank common spatial pattern]

Due to the high complexity and subject variability of motor imagery electroencephalogram, its decoding is limited by the inadequate accuracy of traditional recognition models. To resolve this problem, a recognition model for motor imagery electroencephalogram based on flicker noise spectrum (FNS) and weighted filter bank common spatial pattern ( wFBCSP) was proposed. First, the FNS method was used to analyze the motor imagery electroencephalogram. Using the second derivative moment as structure function, the ensued precursor time series were generated by using a sliding window strategy, so that hidden dynamic information of transition phase could be captured. Then, based on the characteristic of signal frequency band, the feature of the transition phase precursor time series and reaction phase series were extracted by wFBCSP, generating features representing relevant transition and reaction phase. To make the selected features adapt to subject variability and realize better generalization, algorithm of minimum redundancy maximum relevance was further used to select features. Finally, support vector machine as the classifier was used for the classification. In the motor imagery electroencephalogram recognition, the method proposed in this study yielded an average accuracy of 86.34%, which is higher than the comparison methods. Thus, our proposed method provides a new idea for decoding motor imagery electroencephalogram.

Development of hybrid feature learner model integrating FDOSM for golden subject identification in motor imagery

Brain-computer interfaces (BCIs) based on motor imagery (MI) face challenges due to the complex nature of brain activity, nonstationary and high-dimensional properties, and individual variations in motor behaviour. The identification of a consistent "golden subject" in MI-based BCIs remains an open challenge, complicated by multiple evaluation metrics and conflicting trade-offs, presenting complex Multi-Criteria Decision Making (MCDM) problems. This study proposes a hybrid brain signal decoding model called Hybrid Adaboost Feature Learner (HAFL), which combines feature extraction and classification using VGG-19, STFT, and Adaboost classifier. The model is validated using a pre-recorded MI-EEG dataset from the BCI competition at Graz University. The fuzzy decision-making framework is integrated with HAFL to allocate a golden subject for MI-BCI applications through the Golden Subject Decision Matrix (GSDM) and the Fuzzy Decision by Opinion Score Method (FDOSM). The effectiveness of the HAFL model in addressing inter-subject variability in EEG-based MI-BCI is evaluated using an MI-EEG dataset involving nine subjects. Comparing subject performance fairly is challenging due to complexity variations, but the FDOSM method provides valuable insights. Through FDOSM-based External Group Aggregation (EGA), subject S5 achieves the highest score of 2.900, identified as the most promising golden subject for subject-to-subject transfer learning. The proposed methodology is compared against other benchmark studies from various key perspectives and exhibits significant novelty in several aspects. The findings contribute to the development of more robust and effective BCI systems, paving the way for advancements in subject-to-subject transfer learning for BCI-MI applications.

Evidence That Brain-Controlled Functional Electrical Stimulation Could Elicit Targeted Corticospinal Facilitation of Hand Muscles in Healthy Young Adults

OBJECTIVES

Brain-computer interface (BCI)-controlled functional electrical stimulation (FES) has been used in rehabilitation for improving hand motor function. However, mechanisms of improvements are still not well understood. The objective of this study was to investigate how BCI-controlled FES affects hand muscle corticospinal excitability.

MATERIALS AND METHODS

A total of 12 healthy young adults were recruited in the study. During BCI calibration, a single electroencephalography channel from the motor cortex and a frequency band were chosen to detect event-related desynchronization (ERD) of cortical oscillatory activity during kinesthetic wrist motor imagery (MI). The MI-based BCI system was used to detect active states on the basis of ERD activity in real time and produce contralateral wrist extension movements through FES of the extensor carpi radialis (ECR) muscle. As a control condition, FES was used to generate wrist extension at random intervals. The two interventions were performed on separate days and lasted 25 minutes. Motor evoked potentials (MEPs) in ECR (intervention target) and flexor carpi radialis (FCR) muscles were elicited through single-pulse transcranial magnetic stimulation of the motor cortex to compare corticospinal excitability before (pre), immediately after (post0), and 30 minutes after (post30) the interventions.

RESULTS

After the BCI-FES intervention, ECR muscle MEPs were significantly facilitated at post0 and post30 time points compared with before the intervention (pre), whereas there were no changes in the FCR muscle corticospinal excitability. Conversely, after the random FES intervention, both ECR and FCR muscle MEPs were unaffected compared with before the intervention (pre).

CONCLUSIONS

Our results demonstrated evidence that BCI-FES intervention could elicit muscle-specific short-term corticospinal excitability facilitation of the intervention targeted (ECR) muscle only, whereas randomly applied FES was ineffective in eliciting any changes. Notably, these findings suggest that associative cortical and peripheral activations during BCI-FES can effectively elicit targeted muscle corticospinal excitability facilitation, implying possible rehabilitation mechanisms.

CAMBA framework: Unveiling the brain asymmetry alterations and longitudinal changes after stroke using resting-state EEG

Hemispheric asymmetry or lateralization is a fundamental principle of brain organization. However, it is poorly understood to what extent the brain asymmetries across different levels of functional organizations are evident in health or altered in brain diseases. Here, we propose a framework that integrates three degrees of brain interactions (isolated nodes, node-node, and edge-edge) into a unified analysis pipeline to capture the sliding window-based asymmetry dynamics at both the node and hemisphere levels. We apply this framework to resting-state EEG in healthy and stroke populations and investigate the stroke-induced abnormal alterations in brain asymmetries and longitudinal asymmetry changes during poststroke rehabilitation. We observe that the mean asymmetry in patients was abnormally enhanced across different frequency bands and levels of brain interactions, with these abnormal patterns strongly associated with the side of the stroke lesion. Compared to healthy controls, patients displayed significant alterations in asymmetry fluctuations, disrupting and reconfiguring the balance of inter-hemispheric integration and segregation. Additionally, analyses reveal that specific abnormal asymmetry metrics in patients tend to move towards those observed in healthy controls after short-term brain-computer interface rehabilitation. Furthermore, preliminary evidence suggests that baseline clinical and asymmetry features can predict poststroke improvements in the Fugl-Meyer assessment of the lower extremity (mean absolute error of about 2). Overall, these findings advance our understanding of hemispheric asymmetry. Our framework offers new insights into the mechanisms underlying brain alterations and recovery after a brain lesion, may help identify prognostic biomarkers, and can be easily extended to different functional modalities.

Detecting passive and active response in patients with behaviourally diagnosed unresponsive wakefulness syndrome

The diagnosis of unresponsive wakefulness syndrome depends mostly on the motor response following verbal commands. However, there is a potential for misdiagnosis in patients who understand verbal commands (passive response) but cannot perform voluntary movements (active response). To evaluate passive and active responses in such patients, this study used an approach combining functional magnetic resonance imaging and passive listening tasks to evaluate the level of speech comprehension, with portable brain-computer interface modalities that were applied to elicit an active response to attentional modulation tasks at the bedside. We included ten patients who were clinically diagnosed as unresponsive wakefulness syndrome. Two of ten patients showed no significant activation, while limited activation in the auditory cortex was found in six patients. The remaining two patients showed significant activation in language areas, and were able to control the brain-computer interface with reliable accuracy. Using a combined passive/active approach, we identified unresponsive wakefulness syndrome patients who showed both active and passive neural responses. This suggests that some patients with unresponsive wakefulness syndrome diagnosed behaviourally are both wakeful and responsive, and the combined approach is useful for distinguishing a minimally conscious state from unresponsive wakefulness syndrome physiologically.

Using fMRI to localize target regions for implanted brain-computer interfaces in locked-in syndrome

OBJECTIVE

Electrocorticography (ECoG)-based brain-computer interface (BCI) systems have the potential to improve quality of life of people with locked-in syndrome (LIS) by restoring their ability to communicate independently. Before implantation of such a system, it is important to localize ECoG electrode target regions. Here, we assessed the predictive value of functional magnetic resonance imaging (fMRI) for the localization of suitable target regions on the sensorimotor cortex for ECoG-based BCI in people with locked-in syndrome.

METHODS

Three people with locked-in syndrome were implanted with a chronic, fully implantable ECoG-BCI system. We compared pre-surgical fMRI activity with post-implantation ECoG activity from areas known to be active and inactive during attempted hand movement (sensorimotor hand region and dorsolateral prefrontal cortex, respectively).

RESULTS

Results showed a spatial match between fMRI activity and changes in ECoG low and high frequency band power (10 - 30 and 65 - 95 Hz, respectively) during attempted movement. Also, we found that fMRI can be used to select a sub-set of electrodes that show strong task-related signal changes that are therefore likely to generate adequate BCI control.

CONCLUSIONS

Our findings indicate that fMRI is a useful non-invasive tool for the pre-surgical workup of BCI implant candidates.

SIGNIFICANCE

If these results are confirmed in more BCI studies, fMRI might be used for more efficient surgical BCI procedures with focused cortical coverage and lower participant burden.

Humans and robots: Friends of the future? A bird's eye view of biomanufacturing industry 5.0

The evolution of industries have introduced versatile technologies, motivating limitless possibilities of tackling pivotal global predicaments in the arenas of medicine, environment, defence, and national security. In this direction, ardently emerges the new era of Industry 5.0 through the eyes of biomanufacturing, which integrates the most advanced systems 21st century has to offer by means of integrating artificial systems to mimic and nativize the natural milieu to substitute the deficits of nature, thence leading to a new meta world. Albeit, it questions the natural order of the living world, which necessitates certain paramount stipulations to be addressed for a successful expansion of biomanufacturing Industry 5.0. Can humans live in synergism with artificial beings? How can humans establish dominance of hierarchy with artificial counterparts? This perspective provides a bird's eye view on the plausible direction of a new meta world inquisitively. For this purpose, we propose the influence of internet of things (IoT) via new generation interfacial systems, such as, human-machine interface (HMI) and brain-computer interface (BCI) in the domain of tissue engineering and regenerative medicine, which can be extended to target modern warfare and smart healthcare.

Cell-specific alterations in autophagy-lysosomal activity near the chronically implanted microelectrodes

Intracortical microelectrodes that can record and stimulate brain activity have become a valuable technique for basic science research and clinical applications. However, long-term implantation of these microelectrodes can lead to progressive neurodegeneration in the surrounding microenvironment, characterized by elevation in disease-associated markers. Dysregulation of autophagy-lysosomal degradation, a major intracellular waste removal process, is considered a key factor in the onset and progression of neurodegenerative diseases. It is plausible that similar dysfunctions in autophagy-lysosomal degradation contribute to tissue degeneration following implantation-induced focal brain injury, ultimately impacting recording performance. To understand how the focal, persistent brain injury caused by long-term microelectrode implantation impairs autophagy-lysosomal pathway, we employed two-photon microscopy and immunohistology. This investigation focused on the spatiotemporal characterization of autophagy-lysosomal activity near the chronically implanted microelectrode. We observed an aberrant accumulation of immature autophagy vesicles near the microelectrode over the chronic implantation period. Additionally, we found deficits in autophagy-lysosomal clearance proximal to the chronic implant, which was associated with an accumulation of autophagy cargo and a reduction in lysosomal protease level during the chronic period. Furthermore, our evidence demonstrates reactive astrocytes have myelin-containing lysosomes near the microelectrode, suggesting its role of myelin engulfment during acute implantation period. Together, this study sheds light on the process of brain tissue degeneration caused by long-term microelectrode implantation, with a specific focus on impaired intracellular waste degradation.

Real-time assessment of hypnotic depth, using an EEG-based brain-computer interface: a preliminary study

OBJECTIVE

Hypnosis can be an effective treatment for many conditions, and there have been attempts to develop instrumental approaches to continuously monitor hypnotic state level ("depth"). However, there is no method that addresses the individual variability of electrophysiological hypnotic correlates. We explore the possibility of using an EEG-based passive brain-computer interface (pBCI) for real-time, individualised estimation of the hypnosis deepening process.

RESULTS

The wakefulness and deep hypnosis intervals were manually defined and labelled in 27 electroencephalographic (EEG) recordings obtained from eight outpatients after hypnosis sessions. Spectral analysis showed that EEG correlates of deep hypnosis were relatively stable in each patient throughout the treatment but varied between patients. Data from each first session was used to train classification models to continuously assess deep hypnosis probability in subsequent sessions. Models trained using four frequency bands (1.5-45, 1.5-8, 1.5-14, and 4-15 Hz) showed accuracy mostly exceeding 85% in a 10-fold cross-validation. Real-time classification accuracy was also acceptable, so at least one of the four bands yielded results exceeding 74% in any session. The best results averaged across all sessions were obtained using 1.5-14 and 4-15 Hz, with an accuracy of 82%. The revealed issues are also discussed.

Pro-myelinating clemastine administration improves recording performance of chronically implanted microelectrodes and nearby neuronal health

Intracortical microelectrodes have become a useful tool in neuroprosthetic applications in the clinic and to understand neurological disorders in basic neurosciences. Many of these brain-machine interface technology applications require successful long-term implantation with high stability and sensitivity. However, the intrinsic tissue reaction caused by implantation remains a major failure mechanism causing loss of recorded signal quality over time. Oligodendrocytes remain an underappreciated intervention target to improve chronic recording performance. These cells can accelerate action potential propagation and provides direct metabolic support for neuronal health and functionality. However, implantation injury causes oligodendrocyte degeneration and leads to progressive demyelination in surrounding brain tissue. Previous work highlighted that healthy oligodendrocytes are necessary for greater electrophysiological recording performance and the prevention of neuronal silencing around implanted microelectrodes over the chronic implantation period. Thus, we hypothesize that enhancing oligodendrocyte activity with a pharmaceutical drug, Clemastine, will prevent the chronic decline of microelectrode recording performance. Electrophysiological evaluation showed that the promyelination Clemastine treatment significantly elevated the signal detectability and quality, rescued the loss of multi-unit activity, and increased functional interlaminar connectivity over 16-weeks of implantation. Additionally, post-mortem immunohistochemistry showed that increased oligodendrocyte density and myelination coincided with increased survival of both excitatory and inhibitory neurons near the implant. Overall, we showed a positive relationship between enhanced oligodendrocyte activity and neuronal health and functionality near the chronically implanted microelectrode. This study shows that therapeutic strategy that enhance oligodendrocyte activity is effective for integrating the functional device interface with brain tissue over chronic implantation period.

Online semi-supervised learning for motor imagery EEG classification

OBJECTIVE

Time-consuming data labeling in brain-computer interfaces (BCIs) raises many problems such as mental fatigue and is one key factor that hinders the real-world adoption of motor imagery (MI)-based BCIs. An alternative approach is to integrate readily available, as well as informative, unlabeled data online, whereas this approach is less investigated.

APPROACH

We proposed an online semi-supervised learning scheme to improve the classification performance of MI-based BCI. This scheme uses regularized weighted online sequential extreme learning machine (RWOS-ELM) as the base classifier and updates its model parameters with incoming balanced data chunk-by-chunk. In the initial stage, we designed a technique that combines the synthetic minority oversampling with the edited nearest neighbor rule for data augmentation to construct more discriminative initial classifiers. When used online, the incoming chunk of data is first pseudo-labeled by RWOS-ELM as well as an auxiliary classifier, and then balanced again by the above-mentioned technique. Initial classifiers are further updated based on these class-balanced data.

MAIN RESULTS

Offline experimental results on two publicly available MI datasets demonstrate the superiority of the proposed scheme over its counterparts. Further online experiments on six subjects show that their BCI performance gradually improved by learning from incoming unlabeled data.

SIGNIFICANCE

Our proposed online semi-supervised learning scheme has higher computation and memory usage efficiency, which is promising for online MI-based BCIs, especially in the case of insufficient labeled training data.

Self-attention-based convolutional neural network and time-frequency common spatial pattern for enhanced motor imagery classification

BACKGROUND

Motor imagery (MI) based brain-computer interfaces (BCIs) have promising potentials in the field of neuro-rehabilitation. However, due to individual variations in active brain regions during MI tasks, the challenge of decoding MI EEG signals necessitates improved classification performance for practical application.

NEW METHOD

This study proposes a self-attention-based Convolutional Neural Network (CNN) in conjunction with a time-frequency common spatial pattern (TFCSP) for enhanced MI classification. Due to the limited availability of training data, a data augmentation strategy is employed to expand the scale of MI EEG datasets. The self-attention-based CNN is trained to automatically extract the temporal and spatial information from EEG signals, allowing the self-attention module to select active channels by calculating EEG channel weights. TFCSP is further implemented to extract multiscale time-frequency-space features from EEG data. Finally, the EEG features derived from TFCSP are concatenated with those from the self-attention-based CNN for MI classification.

RESULTS

The proposed method is evaluated on two publicly accessible datasets, BCI Competition IV IIa and BCI Competition III IIIa, yielding mean accuracies of 79.28 % and 86.39 %, respectively.

CONCLUSIONS

Compared with state-of-the-art methods, our approach achieves superior classification results in accuracy. Self-attention-based CNN combining with TFCSP can make full use of the time-frequency-space information of EEG, and enhance the classification performance.

Review on brain-computer interface technologies in healthcare

Brain-computer interface (BCI) technologies have developed as a game changer, altering how humans interact with computers and opening up new avenues for understanding and utilizing the power of the human brain. The goal of this research study is to assess recent breakthroughs in BCI technologies and their future prospects. The paper starts with an outline of the fundamental concepts and principles that underpin BCI technologies. It examines the many forms of BCIs, including as invasive, partially invasive, and non-invasive interfaces, emphasizing their advantages and disadvantages. The progress of BCI hardware and signal processing techniques is investigated, with a focus on the shift from bulky and invasive systems to more portable and user-friendly options. Following that, the article delves into the important advances in BCI applications across several fields. It investigates the use of BCIs in healthcare, particularly in neurorehabilitation, assistive technology, and cognitive enhancement. BCIs' potential for boosting human capacities such as communication, motor control, and sensory perception is being thoroughly researched. Furthermore, the article investigates developing BCI applications in gaming, entertainment, and virtual reality, demonstrating how BCI technologies are growing outside medical and therapeutic settings. The study also gives light on the problems and limits that prevent BCIs from being widely adopted. Ethical concerns about privacy, data security, and informed permission are addressed, highlighting the importance of strong legislative frameworks to enable responsible and ethical usage of BCI technologies. Furthermore, the study delves into technological issues such as increasing signal resolution and precision, increasing system reliability, and enabling smooth connection with existing technology. Finally, this study paper gives an in-depth examination of the advances and future possibilities of BCI technologies. It emphasizes the transformative influence of BCIs on human-computer interaction and their potential to alter healthcare, gaming, and other industries. This research intends to stimulate further innovation and progress in the field of brain-computer interfaces by addressing problems and imagining future possibilities.

[Recognition of high-frequency steady-state visual evoked potential for brain-computer interface]

Coding with high-frequency stimuli could alleviate the visual fatigue of users generated by the brain-computer interface (BCI) based on steady-state visual evoked potential (SSVEP). It would improve the comfort and safety of the system and has promising applications. However, most of the current advanced SSVEP decoding algorithms were compared and verified on low-frequency SSVEP datasets, and their recognition performance on high-frequency SSVEPs was still unknown. To address the aforementioned issue, electroencephalogram (EEG) data from 20 subjects were collected utilizing a high-frequency SSVEP paradigm. Then, the state-of-the-art SSVEP algorithms were compared, including 2 canonical correlation analysis algorithms, 3 task-related component analysis algorithms, and 1 task discriminant component analysis algorithm. The results indicated that they all could effectively decode high-frequency SSVEPs. Besides, there were differences in the classification performance and algorithms' speed under different conditions. This paper provides a basis for the selection of algorithms for high-frequency SSVEP-BCI, demonstrating its potential utility in developing user-friendly BCI.

[A design and evaluation of wearable p300 brain-computer interface system based on Hololens2]

Patients with amyotrophic lateral sclerosis ( ALS ) often have difficulty in expressing their intentions through language and behavior, which prevents them from communicating properly with the outside world and seriously affects their quality of life. The brain-computer interface (BCI) has received much attention as an aid for ALS patients to communicate with the outside world, but the heavy device causes inconvenience to patients in the application process. To improve the portability of the BCI system, this paper proposed a wearable P300-speller brain-computer interface system based on the augmented reality (MR-BCI). This system used Hololens2 augmented reality device to present the paradigm, an OpenBCI device to capture EEG signals, and Jetson Nano embedded computer to process the data. Meanwhile, to optimize the system's performance for character recognition, this paper proposed a convolutional neural network classification method with low computational complexity applied to the embedded system for real-time classification. The results showed that compared with the P300-speller brain-computer interface system based on the computer screen (CS-BCI), MR-BCI induced an increase in the amplitude of the P300 component, an increase in accuracy of 1.7% and 1.4% in offline and online experiments, respectively, and an increase in the information transfer rate of 0.7 bit/min. The MR-BCI proposed in this paper achieves a wearable BCI system based on guaranteed system performance. It has a positive effect on the realization of the clinical application of BCI.

[Research on phase modulation to enhance the feature of high-frequency steady-state asymmetric visual evoked potentials]

High-frequency steady-state asymmetric visual evoked potential (SSaVEP) provides a new paradigm for designing comfortable and practical brain-computer interface (BCI) systems. However, due to the weak amplitude and strong noise of high-frequency signals, it is of great significance to study how to enhance their signal features. In this study, a 30 Hz high-frequency visual stimulus was used, and the peripheral visual field was equally divided into eight annular sectors. Eight kinds of annular sector pairs were selected based on the mapping relationship of visual space onto the primary visual cortex (V1), and three phases (in-phase[0º, 0º], anti-phase [0º, 180º], and anti-phase [180º, 0º]) were designed for each annular sector pair to explore response intensity and signal-to-noise ratio under phase modulation. A total of 8 healthy subjects were recruited in the experiment. The results showed that three annular sector pairs exhibited significant differences in SSaVEP features under phase modulation at 30 Hz high-frequency stimulation. And the spatial feature analysis showed that the two types of features of the annular sector pair in the lower visual field were significantly higher than those in the upper visual field. This study further used the filter bank and ensemble task-related component analysis to calculate the classification accuracy of annular sector pairs under three-phase modulations, and the average accuracy was up to 91.5%, which proved that the phase-modulated SSaVEP features could be used to encode high- frequency SSaVEP. In summary, the results of this study provide new ideas for enhancing the features of high-frequency SSaVEP signals and expanding the instruction set of the traditional steady state visual evoked potential paradigm.

[Multi-scale feature extraction and classification of motor imagery electroencephalography based on time series data enhancement]

The brain-computer interface (BCI) based on motor imagery electroencephalography (MI-EEG) enables direct information interaction between the human brain and external devices. In this paper, a multi-scale EEG feature extraction convolutional neural network model based on time series data enhancement is proposed for decoding MI-EEG signals. First, an EEG signals augmentation method was proposed that could increase the information content of training samples without changing the length of the time series, while retaining its original features completely. Then, multiple holistic and detailed features of the EEG data were adaptively extracted by multi-scale convolution module, and the features were fused and filtered by parallel residual module and channel attention. Finally, classification results were output by a fully connected network. The application experimental results on the BCI Competition IV 2a and 2b datasets showed that the proposed model achieved an average classification accuracy of 91.87% and 87.85% for the motor imagery task, respectively, which had high accuracy and strong robustness compared with existing baseline models. The proposed model does not require complex signals pre-processing operations and has the advantage of multi-scale feature extraction, which has high practical application value.