A large electroencephalographic motor imagery dataset for electroencephalographic brain computer interfaces

Unraveling EEG correlates of unimanual finger movements: insights from non-repetitive flexion and extension tasks

BACKGROUND

The loss of finger control in individuals with neuromuscular disorders significantly impacts their quality of life. Electroencephalography (EEG)-based brain-computer interfaces that actuate neuroprostheses directly via decoded motor intentions can help restore lost finger mobility. However, the extent to which finger movements exhibit distinct and decodable EEG correlates remains unresolved. This study aims to investigate the EEG correlates of unimanual, non-repetitive finger flexion and extension.

METHODS

Sixteen healthy, right-handed participants completed multiple sessions of right-hand finger movement experiments. These included five individual (Thumb, Index, Middle, Ring, and Pinky) and four coordinated (Pinch, Point, ThumbsUp, and Fist) finger flexions and extensions, along with a rest condition (None). High-density EEG and finger trajectories were simultaneously recorded and analyzed. We examined low-frequency (0.3-3 Hz) time series and movement-related cortical potentials (MRCPs), and event-related desynchronization/synchronization (ERD/S) in the alpha- (8-13 Hz) and beta (13-30 Hz) bands. A clustering approach based on Riemannian distances was used to chart similarities between the broadband EEG responses (0.3-70 Hz) to the different finger scenarios. The contribution of different state-of-the-art features was identified across sub-bands, from low-frequency to low gamma (30-70 Hz), and an ensemble approach was used to pairwise classify single-trial finger movements and rest.

RESULTS

A significant decrease in EEG amplitude in the low-frequency time series was observed in the contralateral frontal-central regions during finger flexion and extension. Distinct MRCP patterns were found in the pre-, ongoing-, and post-movement stages. Additionally, strong ERD was detected in the contralateral central brain regions in both alpha and beta bands during finger flexion and extension, with the beta band showing a stronger rebound (ERS) post-movement. Within the finger movement repertoire, the Thumb was most distinctive, followed by the Fist. Decoding results indicated that low-frequency time-domain amplitude better differentiates finger movements, while alpha and beta band power and Riemannian features better detect movement versus rest. Combining these features yielded over 80% finger movement detection accuracy, while pairwise classification accuracy exceeded 60% for the Thumb versus the other fingers.

CONCLUSION

Our findings confirm that non-repetitive finger movements, whether individual or coordinated, can be precisely detected from EEG. However, differentiating between specific movements is challenging due to highly overlapping neural correlates in time, spectral, and spatial domains. Nonetheless, certain finger movements, such as those involving the Thumb, exhibit distinct EEG responses, making them prime candidates for dexterous finger neuroprostheses.

Neurosurgical and BCI approaches to visual rehabilitation in occipital lobe tumor patients

This study investigates the effects of occipital lobe tumors on visual processing and the role of brain-computer interface (BCI) technologies in post-surgical visual rehabilitation. Through a combination of pre-surgical functional magnetic resonance imaging (fMRI) and Diffusion Tensor Imaging (DTI), intra-operative direct cortical stimulation (DCS) and Electrocorticography (ECoG), and post-surgical BCI interventions, we provide insight into the complex dynamics between occipital lobe tumors and visual function. Our results highlight a discrepancy between clinical assessments of visual field damage and the patient's reported visual experiences, suggesting a residual functional capacity within the damaged occipital regions. Additionally, the absence of expected visual phenomena during surgery and the promising outcomes from BCI-driven rehabilitation underscore the complexity of visual processing and the potential of technology-enhanced rehabilitation strategies. This work emphasizes the need for an interdisciplinary approach in developing effective treatments for visual impairments related to brain tumors, illustrating the significant implications for neurosurgical practices and the advancement of rehabilitation sciences.

DSFE: Decoding EEG-Based Finger Motor Imagery Using Feature-Dependent Frequency, Feature Fusion and Ensemble Learning

Accurate decoding finger motor imagery is essential for fine motor control using EEG signals. However, decoding finger motor imagery is particularly challenging compared with ordinary motor imagery. This paper proposed a novel EEG decoding method of feature-dependent frequency band selection, feature fusion, and ensemble learning (DSFE) for finger motor imagery. First, a feature-dependent frequency band selection method based on correlation coefficient (FDCC) was proposed to select feature-specific effective bands. Second, a feature fusion method was proposed to fuse different types of candidate features to produce multiple refined sets of decoding features. Finally, an ensemble model using the weighted voting strategy was proposed to make full use of these diverse sets of final features. The results on a public EEG dataset of five fingers motor imagery showed that the DSFE method is effective and achieves the highest decoding accuracy of 50.64%, which is 7.64% higher than existing studies using exactly the same data. The experiments further revealed that both the effective frequency bands of different subjects and the effective frequency bands of different types of features are different in finger motor imagery. Furthermore, compared with two-hand motor imagery, the effective decoding information of finger motor imagery is transferred to the lower frequency. The idea and findings in this paper provide a valuable perspective for understanding fine motor imagery in-depth.

Design Decisions for Wearable EEG to Detect Motor Imagery Movements

The objective of this study was to make informed decisions regarding the design of wearable electroencephalography (wearable EEG) for the detection of motor imagery movements based on testing the critical features for the development of wearable EEG. Three datasets were utilized to determine the optimal acquisition frequency. The brain zones implicated in motor imagery movement were analyzed, with the aim of improving wearable-EEG comfort and portability. Two detection algorithms with different configurations were implemented. The detection output was classified using a tool with various classifiers. The results were categorized into three groups to discern differences between general hand movements and no movement; specific movements and no movement; and specific movements and other specific movements (between five different finger movements and no movement). Testing was conducted on the sampling frequencies, trials, number of electrodes, algorithms, and their parameters. The preferred algorithm was determined to be the FastICACorr algorithm with 20 components. The optimal sampling frequency is 1 kHz to avoid adding excessive noise and to ensure efficient handling. Twenty trials are deemed sufficient for training, and the number of electrodes will range from one to three, depending on the wearable EEG's ability to handle the algorithm parameters with good performance.

Use of Artificial Intelligence Techniques to Assist Individuals with Physical Disabilities

Assistive technologies (AT) enable people with disabilities to perform activities of daily living more independently, have greater access to community and healthcare services, and be more productive performing educational and/or employment tasks. Integrating artificial intelligence (AI) with various agents, including electronics, robotics, and software, has revolutionized AT, resulting in groundbreaking technologies such as mind-controlled exoskeletons, bionic limbs, intelligent wheelchairs, and smart home assistants. This article provides a review of various AI techniques that have helped those with physical disabilities, including brain-computer interfaces, computer vision, natural language processing, and human-computer interaction. The current challenges and future directions for AI-powered advanced technologies are also addressed.

Exploring Novel Practical Approach to Post-Stroke Upper-Limb Neurorehabilitation Based on Complex Motor Imagery Tasks

Motor imagery (MI) is one of the main strategies for upper-limb movement rehabilitation in post-stroke individuals. Promising results of MI applied for rehabilitation have been reported in the literature. However, there is currently a need related to the recovery of movements aimed to Activities of Daily Living (ADLs) for individuals with severe motor impairments. Therefore, this study presents the evaluation of a novel MI protocol for post-stroke upper-limb neurorehabilitation using complex tasks related to the manipulation of a drinking cup. The protocol is based on the Action Observation (AO), which was used under a first-person 2D virtual reality. Subjects had to simultaneously imagine the movements presented in AO for the manipulation of a cup varying in four positions. EEG signals were recorded from 16 channels located mainly in the motor cortex of the brain. Two computational strategies based on Riemannian Geometry (RG) with and without Feature Selection (FS) using Pair-Wise Feature Proximity (PWFP) were implemented for the binary identification of each complex MI-Task vs. MI-Rest. This approach was evaluated on 30 healthy individuals and 2 post-stroke individuals. Using Linear Discriminant Analysis (LDA) as a classifier, the results report a maximum accuracy of 0.78 for both healthy and post-stroke individuals, and a minimum FPR of 0.21 and 0.13 for healthy and post-stroke individuals, respectively. This highlights the potential use of this type of paradigms for the implementation of more robust BCI systems that allow the rehabilitation of movements close to ADLs. Therefore, complex MI tasks may be a suitable variant for rehabilitation in post-stroke individuals.

An EEG & eye-tracking dataset of ALS patients & healthy people during eye-tracking-based spelling system usage

This research presents a dataset consisting of electroencephalogram and eye tracking recordings obtained from six patients with amyotrophic lateral sclerosis (ALS) in a locked-in state and one hundred seventy healthy individuals. The ALS patients exhibited varying degrees of disease progression, ranging from partial mobility and weakened speech to complete paralysis and loss of speech. Despite these physical impairments, the ALS patients retained good eye function, which allowed them to use a virtual keyboard for communication. Data from ALS patients was recorded multiple times at their homes, while data from healthy individuals was recorded once in a laboratory setting. For each data recording, the experimental design involved nine recording sessions per participant, each corresponding to a common human action or demand. This dataset can serve as a valuable benchmark for several applications, such as improving spelling systems with brain-computer interfaces, investigating motor imagination, exploring motor cortex function, monitoring motor impairment progress in patients undergoing rehabilitation, and studying the effects of ALS on cognitive and motor processes.

Aggregating intrinsic information to enhance BCI performance through federated learning

Insufficient data is a long-standing challenge for Brain-Computer Interface (BCI) to build a high-performance deep learning model. Though numerous research groups and institutes collect a multitude of EEG datasets for the same BCI task, sharing EEG data from multiple sites is still challenging due to the heterogeneity of devices. The significance of this challenge cannot be overstated, given the critical role of data diversity in fostering model robustness. However, existing works rarely discuss this issue, predominantly centering their attention on model training within a single dataset, often in the context of inter-subject or inter-session settings. In this work, we propose a hierarchical personalized Federated Learning EEG decoding (FLEEG) framework to surmount this challenge. This innovative framework heralds a new learning paradigm for BCI, enabling datasets with disparate data formats to collaborate in the model training process. Each client is assigned a specific dataset and trains a hierarchical personalized model to manage diverse data formats and facilitate information exchange. Meanwhile, the server coordinates the training procedure to harness knowledge gleaned from all datasets, thus elevating overall performance. The framework has been evaluated in Motor Imagery (MI) classification with nine EEG datasets collected by different devices but implementing the same MI task. Results demonstrate that the proposed framework can boost classification performance up to 8.4% by enabling knowledge sharing between multiple datasets, especially for smaller datasets. Visualization results also indicate that the proposed framework can empower the local models to put a stable focus on task-related areas, yielding better performance. To the best of our knowledge, this is the first end-to-end solution to address this important challenge.

Individual-finger motor imagery classification: a data-driven approach with Shapley-informed augmentation

Objective. Classifying motor imagery (MI) tasks that involve fine motor control of the individual five fingers presents unique challenges when utilizing electroencephalography (EEG) data. In this paper, we systematically assess the classification of MI functions for the individual five fingers using single-trial time-domain EEG signals. This assessment encompasses both within-subject and cross-subject scenarios, supported by data-driven analysis that provides statistical validation of the neural correlate that could potentially discriminate between the five fingers.Approach. We present Shapley-informed augmentation, an informed approach to enhance within-subject classification accuracy. This method is rooted in insights gained from our data-driven analysis, which revealed inconsistent temporal features encoding the five fingers MI across sessions of the same subject. To evaluate its impact, we compare within-subject classification performance both before and after implementing this augmentation technique.Main results. Both the data-driven approach and the model explainability analysis revealed that the parietal cortex contains neural information that helps discriminate the individual five fingers' MI apart. Shapley-informed augmentation successfully improved classification accuracy in sessions severely affected by inconsistent temporal features. The accuracy for sessions impacted by inconsistency in their temporal features increased by an average of26.3%±6.70, thereby enabling a broader range of subjects to benefit from brain-computer interaction (BCI) applications involving five-fingers MI classification. Conversely, non-impacted sessions experienced only a negligible average accuracy decrease of2.01±5.44%. The average classification accuracy achieved is around 60.0% (within-session), 50.0% (within-subject) and 40.0% (leave-one-subject-out).Significance. This research offers data-driven evidence of neural correlates that could discriminate between the individual five fingers MI and introduces a novel Shapley-informed augmentation method to address temporal variability of features, ultimately contributing to the development of personalized systems.

EEG-based finger movement classification with intrinsic time-scale decomposition

Introduction

Brain-computer interfaces (BCIs) are systems that acquire the brain's electrical activity and provide control of external devices. Since electroencephalography (EEG) is the simplest non-invasive method to capture the brain's electrical activity, EEG-based BCIs are very popular designs. Aside from classifying the extremity movements, recent BCI studies have focused on the accurate coding of the finger movements on the same hand through their classification by employing machine learning techniques. State-of-the-art studies were interested in coding five finger movements by neglecting the brain's idle case (i.e., the state that brain is not performing any mental tasks). This may easily cause more false positives and degrade the classification performances dramatically, thus, the performance of BCIs. This study aims to propose a more realistic system to decode the movements of five fingers and the no mental task (NoMT) case from EEG signals.

Methods

In this study, a novel praxis for feature extraction is utilized. Using Proper Rotational Components (PRCs) computed through Intrinsic Time Scale Decomposition (ITD), which has been successfully applied in different biomedical signals recently, features for classification are extracted. Subsequently, these features were applied to the inputs of well-known classifiers and their different implementations to discriminate between these six classes. The highest classifier performances obtained in both subject-independent and subject-dependent cases were reported. In addition, the ANOVA-based feature selection was examined to determine whether statistically significant features have an impact on the classifier performances or not.

Results

As a result, the Ensemble Learning classifier achieved the highest accuracy of 55.0% among the tested classifiers, and ANOVA-based feature selection increases the performance of classifiers on five-finger movement determination in EEG-based BCI systems.

Discussion

When compared with similar studies, proposed praxis achieved a modest yet significant improvement in classification performance although the number of classes was incremented by one (i.e., NoMT).

Cross-Subject Motor Imagery Decoding by Transfer Learning of Tactile ERD

For Brain-Computer Interface (BCI) based on motor imagery (MI), the MI task is abstract and spontaneous, presenting challenges in measurement and control and resulting in a lower signal-to-noise ratio. The quality of the collected MI data significantly impacts the cross-subject calibration results. To address this challenge, we introduce a novel cross-subject calibration method based on passive tactile afferent stimulation, in which data induced by tactile stimulation is utilized to calibrate transfer learning models for cross-subject decoding. During the experiments, tactile stimulation was applied to either the left or right hand, with subjects only required to sense tactile stimulation. Data from these tactile tasks were used to train or fine-tune models and subsequently applied to decode pure MI data. We evaluated BCI performance using both the classical Common Spatial Pattern (CSP) combined with the Linear Discriminant Analysis (LDA) algorithm and a state-of-the-art deep transfer learning model. The results demonstrate that the proposed calibration method achieved decoding performance at an equivalent level to traditional MI calibration, with the added benefit of outperforming traditional MI calibration with fewer trials. The simplicity and effectiveness of the proposed cross-subject tactile calibration method make it valuable for practical applications of BCI, especially in clinical settings.

Self-Supervised Learning for Electroencephalography

Decades of research have shown machine learning superiority in discovering highly nonlinear patterns embedded in electroencephalography (EEG) records compared with conventional statistical techniques. However, even the most advanced machine learning techniques require relatively large, labeled EEG repositories. EEG data collection and labeling are costly. Moreover, combining available datasets to achieve a large data volume is usually infeasible due to inconsistent experimental paradigms across trials. Self-supervised learning (SSL) solves these challenges because it enables learning from EEG records across trials with variable experimental paradigms, even when the trials explore different phenomena. It aggregates multiple EEG repositories to increase accuracy, reduce bias, and mitigate overfitting in machine learning training. In addition, SSL could be employed in situations where there is limited labeled training data, and manual labeling is costly. This article: 1) provides a brief introduction to SSL; 2) describes some SSL techniques employed in recent studies, including EEG; 3) proposes current and potential SSL techniques for future investigations in EEG studies; 4) discusses the cons and pros of different SSL techniques; and 5) proposes holistic implementation tips and potential future directions for EEG SSL practices.

How Integration of a Brain-Machine Interface and Obstacle Detection System Can Improve Wheelchair Control via Movement Imagery

This study presents a human-computer interaction combined with a brain-machine interface (BMI) and obstacle detection system for remote control of a wheeled robot through movement imagery, providing a potential solution for individuals facing challenges with conventional vehicle operation. The primary focus of this work is the classification of surface EEG signals related to mental activity when envisioning movement and deep relaxation states. Additionally, this work presents a system for obstacle detection based on image processing. The implemented system constitutes a complementary part of the interface. The main contributions of this work include the proposal of a modified 10-20-electrode setup suitable for motor imagery classification, the design of two convolutional neural network (CNNs) models employed to classify signals acquired from sixteen EEG channels, and the implementation of an obstacle detection system based on computer vision integrated with a brain-machine interface. The models developed in this study achieved an accuracy of 83% in classifying EEG signals. The resulting classification outcomes were subsequently utilized to control the movement of a mobile robot. Experimental trials conducted on a designated test track demonstrated real-time control of the robot. The findings indicate the feasibility of integration of the obstacle detection system for collision avoidance with the classification of motor imagery for the purpose of brain-machine interface control of vehicles. The elaborated solution could help paralyzed patients to safely control a wheelchair through EEG and effectively prevent unintended vehicle movements.

An EEG motor imagery dataset for brain computer interface in acute stroke patients

The brain-computer interface (BCI) is a technology that involves direct communication with parts of the brain and has evolved rapidly in recent years; it has begun to be used in clinical practice, such as for patient rehabilitation. Patient electroencephalography (EEG) datasets are critical for algorithm optimization and clinical applications of BCIs but are rare at present. We collected data from 50 acute stroke patients with wireless portable saline EEG devices during the performance of two tasks: 1) imagining right-handed movements and 2) imagining left-handed movements. The dataset consists of four types of data: 1) the motor imagery instructions, 2) raw recording data, 3) pre-processed data after removing artefacts and other manipulations, and 4) patient characteristics. This is the first open dataset to address left- and right-handed motor imagery in acute stroke patients. We believe that the dataset will be very helpful for analysing brain activation and designing decoding methods that are more applicable for acute stroke patients, which will greatly facilitate research in the field of motor imagery-BCI.

Multimodal pre-screening can predict BCI performance variability: A novel subject-specific experimental scheme

BACKGROUND

Brain-computer interface (BCI) systems currently lack the required robustness for long-term daily use due to inter- and intra-subject performance variability. In this study, we propose a novel personalized scheme for a multimodal BCI system, primarily using functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG), to identify, predict, and compensate for factors affecting competence-related and interfering factors associated with performance.

METHOD

11 (out of 13 recruited) participants, including five participants with motor deficits, completed four sessions on average. During the training sessions, the subjects performed a short pre-screening phase, followed by three variations of a novel visou-mental (VM) protocol. Features extracted from the pre-screening phase were used to construct predictive platforms using stepwise multivariate linear regression (MLR) models. In the test sessions, we employed a task-correction phase where our predictive models were used to predict the ideal task variation to maximize performance, followed by an interference-correction phase. We then investigated the associations between predicted and actual performances and evaluated the outcome of correction strategies.

RESULT

The predictive models resulted in respective adjusted R-squared values of 0.942, 0.724, and 0.939 for the first, second, and third variation of the task, respectively. The statistical analyses showed significant associations between the performances predicted by predictive models and the actual performances for the first two task variations, with rhos of 0.7289 (p-value = 0.011) and 0.6970 (p-value = 0.017), respectively. For 81.82 % of the subjects, the task/workload correction stage correctly determined which task variation provided the highest accuracy, with an average performance gain of 5.18 % when applying the correction strategies.

CONCLUSION

Our proposed method can lead to an integrated multimodal predictive framework to compensate for BCI performance variability, particularly, for people with severe motor deficits.

EEG Amplitude Modulation Analysis across Mental Tasks: Towards Improved Active BCIs

Brain-computer interface (BCI) technology has emerged as an influential communication tool with extensive applications across numerous fields, including entertainment, marketing, mental state monitoring, and particularly medical neurorehabilitation. Despite its immense potential, the reliability of BCI systems is challenged by the intricacies of data collection, environmental factors, and noisy interferences, making the interpretation of high-dimensional electroencephalogram (EEG) data a pressing issue. While the current trends in research have leant towards improving classification using deep learning-based models, our study proposes the use of new features based on EEG amplitude modulation (AM) dynamics. Experiments on an active BCI dataset comprised seven mental tasks to show the importance of the proposed features, as well as their complementarity to conventional power spectral features. Through combining the seven mental tasks, 21 binary classification tests were explored. In 17 of these 21 tests, the addition of the proposed features significantly improved classifier performance relative to using power spectral density (PSD) features only. Specifically, the average kappa score for these classifications increased from 0.57 to 0.62 using the combined feature set. An examination of the top-selected features showed the predominance of the AM-based measures, comprising over 77% of the top-ranked features. We conclude this paper with an in-depth analysis of these top-ranked features and discuss their potential for use in neurophysiology.

Brain-computer interface: trend, challenges, and threats

Brain-computer interface (BCI), an emerging technology that facilitates communication between brain and computer, has attracted a great deal of research in recent years. Researchers provide experimental results demonstrating that BCI can restore the capabilities of physically challenged people, hence improving the quality of their lives. BCI has revolutionized and positively impacted several industries, including entertainment and gaming, automation and control, education, neuromarketing, and neuroergonomics. Notwithstanding its broad range of applications, the global trend of BCI remains lightly discussed in the literature. Understanding the trend may inform researchers and practitioners on the direction of the field, and on where they should invest their efforts more. Noting this significance, we have analyzed 25,336 metadata of BCI publications from Scopus to determine advancement of the field. The analysis shows an exponential growth of BCI publications in China from 2019 onwards, exceeding those from the United States that started to decline during the same period. Implications and reasons for this trend are discussed. Furthermore, we have extensively discussed challenges and threats limiting exploitation of BCI capabilities. A typical BCI architecture is hypothesized to address two prominent BCI threats, privacy and security, as an attempt to make the technology commercially viable to the society.

A case for hybrid BCIs: combining optical and electrical modalities improves accuracy

Near-infrared spectroscopy (NIRS) is a promising research tool that found its way into the field of brain-computer interfacing (BCI). BCI is crucially dependent on maximized usability thus demanding lightweight, compact, and low-cost hardware. We designed, built, and validated a hybrid BCI system incorporating one optical and two electrical modalities ameliorating usability issues. The novel hardware consisted of a NIRS device integrated with an electroencephalography (EEG) system that used two different types of electrodes: Regular gelled gold disk electrodes and tri-polar concentric ring electrodes (TCRE). BCI experiments with 16 volunteers implemented a two-dimensional motor imagery paradigm in off- and online sessions. Various non-canonical signal processing methods were used to extract and classify useful features from EEG, tEEG (EEG through TCRE electrodes), and NIRS. Our analysis demonstrated evidence of improvement in classification accuracy when using the TCRE electrodes compared to disk electrodes and the NIRS system. Based on our synchronous hybrid recording system, we could show that the combination of NIRS-EEG-tEEG performed significantly better than either single modality only.

Decoding of the neural representation of the visual RGB color model

RGB color is a basic visual feature. Here we use machine learning and visual evoked potential (VEP) of electroencephalogram (EEG) data to investigate the decoding features of the time courses and space location that extract it, and whether they depend on a common brain cortex channel. We show that RGB color information can be decoded from EEG data and, with the task-irrelevant paradigm, features can be decoded across fast changes in VEP stimuli. These results are consistent with the theory of both event-related potential (ERP) and P300 mechanisms. The latency on time course is shorter and more temporally precise for RGB color stimuli than P300, a result that does not depend on a task-relevant paradigm, suggesting that RGB color is an updating signal that separates visual events. Meanwhile, distribution features are evident for the brain cortex of EEG signal, providing a space correlate of RGB color in classification accuracy and channel location. Finally, space decoding of RGB color depends on the channel classification accuracy and location obtained through training and testing EEG data. The result is consistent with channel power value distribution discharged by both VEP and electrophysiological stimuli mechanisms.

Motor Imagery Multi-Tasks Classification for BCIs Using the NVIDIA Jetson TX2 Board and the EEGNet Network

Nowadays, Brain-Computer Interfaces (BCIs) still captivate large interest because of multiple advantages offered in numerous domains, explicitly assisting people with motor disabilities in communicating with the surrounding environment. However, challenges of portability, instantaneous processing time, and accurate data processing remain for numerous BCI system setups. This work implements an embedded multi-tasks classifier based on motor imagery using the EEGNet network integrated into the NVIDIA Jetson TX2 card. Therefore, two strategies are developed to select the most discriminant channels. The former uses the accuracy based-classifier criterion, while the latter evaluates electrode mutual information to form discriminant channel subsets. Next, the EEGNet network is implemented to classify discriminant channel signals. Additionally, a cyclic learning algorithm is implemented at the software level to accelerate the model learning convergence and fully profit from the NJT2 hardware resources. Finally, motor imagery Electroencephalogram (EEG) signals provided by HaLT's public benchmark were used, in addition to the k-fold cross-validation method. Average accuracies of 83.7% and 81.3% were achieved by classifying EEG signals per subject and motor imagery task, respectively. Each task was processed with an average latency of 48.7 ms. This framework offers an alternative for online EEG-BCI systems' requirements, dealing with short processing times and reliable classification accuracy.

Review of public motor imagery and execution datasets in brain-computer interfaces

The demand for public datasets has increased as data-driven methodologies have been introduced in the field of brain-computer interfaces (BCIs). Indeed, many BCI datasets are available in various platforms or repositories on the web, and the studies that have employed these datasets appear to be increasing. Motor imagery is one of the significant control paradigms in the BCI field, and many datasets related to motor tasks are open to the public already. However, to the best of our knowledge, these studies have yet to investigate and evaluate the datasets, although data quality is essential for reliable results and the design of subject- or system-independent BCIs. In this study, we conducted a thorough investigation of motor imagery/execution EEG datasets recorded from healthy participants published over the past 13 years. The 25 datasets were collected from six repositories and subjected to a meta-analysis. In particular, we reviewed the specifications of the recording settings and experimental design, and evaluated the data quality measured by classification accuracy from standard algorithms such as Common Spatial Pattern (CSP) and Linear Discriminant Analysis (LDA) for comparison and compatibility across the datasets. As a result, we found that various stimulation types, such as text, figure, or arrow, were used to instruct subjects what to imagine and the length of each trial also differed, ranging from 2.5 to 29 s with a mean of 9.8 s. Typically, each trial consisted of multiple sections: pre-rest (2.38 s), imagination ready (1.64 s), imagination (4.26 s, ranging from 1 to 10 s), the post-rest (3.38 s). In a meta-analysis of the total of 861 sessions from all datasets, the mean classification accuracy of the two-class (left-hand vs. right-hand motor imagery) problem was 66.53%, and the population of the BCI poor performers, those who are unable to reach proficiency in using a BCI system, was 36.27% according to the estimated accuracy distribution. Further, we analyzed the CSP features and found that each dataset forms a cluster, and some datasets overlap in the feature space, indicating a greater similarity among them. Finally, we checked the minimal essential information (continuous signals, event type/latency, and channel information) that should be included in the datasets for convenient use, and found that only 71% of the datasets met those criteria. Our attempts to evaluate and compare the public datasets are timely, and these results will contribute to understanding the dataset's quality and recording settings as well as the use of using public datasets for future work on BCIs.

EEG-Based BCIs on Motor Imagery Paradigm Using Wearable Technologies: A Systematic Review

In recent decades, the automatic recognition and interpretation of brain waves acquired by electroencephalographic (EEG) technologies have undergone remarkable growth, leading to a consequent rapid development of brain-computer interfaces (BCIs). EEG-based BCIs are non-invasive systems that allow communication between a human being and an external device interpreting brain activity directly. Thanks to the advances in neurotechnologies, and especially in the field of wearable devices, BCIs are now also employed outside medical and clinical applications. Within this context, this paper proposes a systematic review of EEG-based BCIs, focusing on one of the most promising paradigms based on motor imagery (MI) and limiting the analysis to applications that adopt wearable devices. This review aims to evaluate the maturity levels of these systems, both from the technological and computational points of view. The selection of papers has been performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), leading to 84 publications considered in the last ten years (from 2012 to 2022). Besides technological and computational aspects, this review also aims to systematically list experimental paradigms and available datasets in order to identify benchmarks and guidelines for the development of new applications and computational models.

Considerate motion imagination classification method using deep learning

In order to improve the classification accuracy of motion imagination, a considerate motion imagination classification method using deep learning is proposed. Specifically, based on a graph structure suitable for electroencephalography as input, the proposed model can accurately represent the distribution of electroencephalography electrodes in non-Euclidean space and fully consider the spatial correlation between electrodes. In addition, the spatial-spectral-temporal multi-dimensional feature information was extracted from the spatial-temporal graph representation and spatial-spectral graph representation transformed from the original electroencephalography signal using the dual branch architecture. Finally, the attention mechanism and global feature aggregation module were designed and combined with graph convolution to adaptively capture the dynamic correlation intensity and effective feature of electroencephalography signals in various dimensions. A series of contrast experiments and ablation experiments on several different public brain-computer interface datasets demonstrated that the excellence of proposed method. It is worth mentioning that, the proposed model is a general framework for the classification of electroencephalography signals, which is suitable for emotion recognition, sleep staging and other fields based on electroencephalography research. Moreover, the model has the potential to be applied in the medical field of motion imagination rehabilitation in real life.

A large EEG dataset for studying cross-session variability in motor imagery brain-computer interface

In building a practical and robust brain-computer interface (BCI), the classification of motor imagery (MI) from electroencephalography (EEG) across multiple days is a long-standing challenge due to the large variability of the EEG signals. We collected a large dataset of MI from 5 different days with 25 subjects, the first open-access dataset to address BCI issues across 5 different days with a large number of subjects. The dataset includes 5 session data from 5 different days (2–3 days apart) for each subject. Each session contains 100 trials of left-hand and right-hand MI. In this report, we provide the benchmarking classification accuracy for three conditions, namely, within-session classification (WS), cross-session classification (CS), and cross-session adaptation (CSA), with subject-specific models. WS achieves an average classification accuracy of up to 68.8%, while CS degrades the accuracy to 53.7% due to the cross-session variability. However, by adaptation, CSA improves the accuracy to 78.9%. We anticipate this new dataset will significantly push further progress in MI BCI research in addressing the cross-session and cross-subject challenge.

Measurement(s)	Electroencephalography
Technology Type(s)	motor imagery

Data augmentation strategies for EEG-based motor imagery decoding

The wide use of motor imagery as a paradigm for brain-computer interfacing (BCI) points to its characteristic ability to generate discriminatory signals for communication and control. In recent times, deep learning techniques have increasingly been explored, in motor imagery decoding. While deep learning techniques are promising, a major challenge limiting their wide adoption is the amount of data available for decoding. To combat this challenge, data augmentation can be performed, to enhance decoding performance. In this study, we performed data augmentation by synthesizing motor imagery (MI) electroencephalography (EEG) trials, following six approaches. Data generated using these methods were evaluated based on four criteria, namely – the accuracy of prediction, the Frechet Inception distance (FID), the t-distributed Stochastic Neighbour Embedding (t-SNE) plots and topographic head plots. We show, based on these, that the synthesized data exhibit similar characteristics with real data, gaining up to 3% and 12% increases in mean accuracies across two public datasets. Finally, we believe these approaches should be utilized in applying deep learning techniques, as they not only have the potential to improve prediction performances, but also to save time spent on subject data collection.

2020 International brain-computer interface competition: A review

The brain-computer interface (BCI) has been investigated as a form of communication tool between the brain and external devices. BCIs have been extended beyond communication and control over the years. The 2020 international BCI competition aimed to provide high-quality neuroscientific data for open access that could be used to evaluate the current degree of technical advances in BCI. Although there are a variety of remaining challenges for future BCI advances, we discuss some of more recent application directions: (i) few-shot EEG learning, (ii) micro-sleep detection (iii) imagined speech decoding, (iv) cross-session classification, and (v) EEG(+ear-EEG) detection in an ambulatory environment. Not only did scientists from the BCI field compete, but scholars with a broad variety of backgrounds and nationalities participated in the competition to address these challenges. Each dataset was prepared and separated into three data that were released to the competitors in the form of training and validation sets followed by a test set. Remarkable BCI advances were identified through the 2020 competition and indicated some trends of interest to BCI researchers.

Overview of the EEG-Based Classification of Motor Imagery Activities Using Machine Learning Methods and Inference Acceleration with FPGA-Based Cards

In this article, we provide a brief overview of the EEG-based classification of motor imagery activities using machine learning methods. We examined the effect of data segmentation and different neural network structures. By applying proper window size and using a purely convolutional neural network, we achieved 97.7% recognition accuracy on data from twenty subjects in three classes. The proposed architecture outperforms several networks used in previous research and makes the motor imagery-based BCI more efficient in some applications. In addition, we examined the performance of the neural network on a FPGA-based card and compared it with the inference speed and accuracy provided by a general-purpose processor.

Mental State Classification Using Multi-Graph Features

We consider the problem of extracting features from passive, multi-channel electroencephalogram (EEG) devices for downstream inference tasks related to high-level mental states such as stress and cognitive load. Our proposed feature extraction method uses recently developed spectral-based multi-graph tools and applies them to the time series of graphs implied by the statistical dependence structure (e.g., correlation) amongst the multiple sensors. We study the features in the context of two datasets each consisting of at least 30 participants and recorded using multi-channel EEG systems. We compare the classification performance of a classifier trained on the proposed features to a classifier trained on the traditional band power-based features in three settings and find that the two feature sets offer complementary predictive information. We conclude by showing that the importance of particular channels and pairs of channels for classification when using the proposed features is neuroscientifically valid.

Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning Architecture

Recently, motor imagery EEG signals have been widely applied in Brain–Computer Interfaces (BCI). These signals are typically observed in the first motor cortex of the brain, resulting from the imagination of body limb movements. For non-invasive BCI systems, it is not apparent how to locate the electrodes, optimizing the accuracy for a given task. This study proposes a comparative analysis of channel signals exploiting the Deep Learning (DL) technique and a public dataset to locate the most discriminant channels. EEG channels are usually selected based on the function and nomenclature of electrode location from international standards. Instead, the most suitable configuration for a given paradigm must be determined by analyzing the proper selection of the channels. Therefore, an EEGNet network was implemented to classify signals from different channel location using the accuracy metric. Achieved results were then contrasted with results from the state-of-the-art. As a result, the proposed method improved BCI classification accuracy.

Metric Learning in Freewill EEG Pre-Movement and Movement Intention Classification for Brain Machine Interfaces

Decoding movement related intentions is a key step to implement BMIs. Decoding EEG has been challenging due to its low spatial resolution and signal to noise ratio. Metric learning allows finding a representation of data in a way that captures a desired notion of similarity between data points. In this study, we investigate how metric learning can help finding a representation of the data to efficiently classify EEG movement and pre-movement intentions. We evaluate the effectiveness of the obtained representation by comparing classification the performance of a Support Vector Machine (SVM) as a classifier when trained on the original representation, called Euclidean, and representations obtained with three different metric learning algorithms, including Conditional Entropy Metric Learning (CEML), Neighborhood Component Analysis (NCA), and the Entropy Gap Metric Learning (EGML) algorithms. We examine different types of features, such as time and frequency components, which input to the metric learning algorithm, and both linear and non-linear SVM are applied to compare the classification accuracies on a publicly available EEG data set for two subjects (Subject B and C). Although metric learning algorithms do not increase the classification accuracies, their interpretability using an importance measure we define here, helps understanding data organization and how much each EEG channel contributes to the classification. In addition, among the metric learning algorithms we investigated, EGML shows the most robust performance due to its ability to compensate for differences in scale and correlations among variables. Furthermore, from the observed variations of the importance maps on the scalp and the classification accuracy, selecting an appropriate feature such as clipping the frequency range has a significant effect on the outcome of metric learning and subsequent classification. In our case, reducing the range of the frequency components to 0-5 Hz shows the best interpretability in both Subject B and C and classification accuracy for Subject C. Our experiments support potential benefits of using metric learning algorithms by providing visual explanation of the data projections that explain the inter class separations, using importance. This visualizes the contribution of features that can be related to brain function.

Kernel Temporal Differences for EEG-based Reinforcement Learning Brain Machine Interfaces

Kernel temporal differences (KTD) (λ) algorithm integrated in Q-learning (Q-KTD) has shown its applicability and feasibility for reinforcement learning brain machine interfaces (RLBMIs). RLBMI with its unique learning strategy based on trial-error allows continuous learning and adaptation in BMIs. Q-KTD has shown good performance in both open and closed-loop experiments for finding a proper mapping from neural intention to control commands of an external device. However, previous studies have been limited to intracortical BMIs where monkey's firing rates from primary motor cortex were used as inputs to the neural decoder. This study provides the first attempt to investigate Q-KTD algorithm's applicability in EEG-based RLBMIs. Two different publicly available EEG data sets are considered, we refer to them as Data set A and Data set B. EEG motor imagery tasks are integrated in a single step center-out reaching task, and we observe the open-loop RLBMI experiments reach 100% average success rates after sufficient learning experience. Data set A converges after approximately 20 epochs for raw features and Data set B shows convergence after approximately 40 epochs for both raw and Fourier transform features. Although there still exist challenges to overcome in EEG-based RLBMI using Q-KTD, including increasing the learning speed, and optimization of a continuously growing number of kernel units, the results encourage further investigation of Q-KTD in closed-loop RLBMIs using EEG. Clinical Relevance- This study supports feasibility of noninvasive EEG-based RLBMI implementations and addresses benefits and challenges of RLBMI using EEG.

Development of an Adaptive Artifact Subspace Reconstruction Based on Hebbian/Anti-Hebbian Learning Networks for Enhancing BCI Performance

Brain-computer interface (BCI) actively translates the brain signals into executable actions by establishing direct communication between the human brain and external devices. Recording brain activity through electroencephalography (EEG) is generally contaminated with both physiological and nonphysiological artifacts, which significantly hinders the BCI performance. Artifact subspace reconstruction (ASR) is a well-known statistical technique that automatically removes artifact components by determining the rejection threshold based on the initial reference EEG segment in multichannel EEG recordings. In real-world applications, the fixed threshold may limit the efficacy of the artifact correction, especially when the quality of the reference data is poor. This study proposes an adaptive online ASR technique by integrating the Hebbian/anti-Hebbian neural networks into the ASR algorithm, namely, principle subspace projection ASR (PSP-ASR) and principal subspace whitening ASR (PSW-ASR) that segmentwise self-organize the artifact subspace by updating the synaptic weights according to the Hebbian and anti-Hebbian learning rules. The effectiveness of the proposed algorithm is compared to the conventional ASR approaches on benchmark EEG dataset and three BCI frameworks, including steady-state visual evoked potential (SSVEP), rapid serial visual presentation (RSVP), and motor imagery (MI) by evaluating the root-mean-square error (RMSE), the signal-to-noise ratio (SNR), the Pearson correlation, and classification accuracy. The results demonstrated that the PSW-ASR algorithm effectively removed the EEG artifacts and retained the activity-specific brain signals compared to the PSP-ASR, standard ASR (Init-ASR), and moving-window ASR (MW-ASR) methods, thereby enhancing the SSVEP, RSVP, and MI BCI performances. Finally, our empirical results from the PSW-ASR algorithm suggested the choice of an aggressive cutoff range of c = 1-10 for activity-specific BCI applications and a moderate range of for the benchmark dataset and general BCI applications.

A Comprehensive Survey on Affinity Analysis, Bibliomining, and Technology Mining: Past, Present, and Future Research

Recent advancements in high-speed communications and high-capacity computing systems have contributed to major growth in the data volume of databases. Data mining is a crucial part of information retrieval; it is often termed as database knowledge discovery. It consists of techniques for examining massive data sets, to find hidden (but possibly important) information. Three interesting fields in data mining are affinity analysis, bibliomining, and technology mining. Affinity analysis provides data mining techniques to determine the similarity among objects; bibliomining is a combination of data mining, bibliometrics, and data warehousing; technology mining is a research topic that is an obstacle to many scientists in the fields of time association, enterprise association, and computer programming. We present a systematic review of the notable research articles in the fields of affinity analysis, bibliomining, and technology mining published between 2000 and December 2021. We provide a systematic analysis of the selected literature by specifying the major contributions, used data sets, performance evaluations, and limitations. Our findings demonstrate that affinity analysis interoperability extends well beyond market basket analysis. We also demonstrate that, in the age of big data, the personalized needs of users are the driving forces behind the evolution of the digital library from a resource-sharing service to a user-centered service. Finally, this article provides insight into major advances and outstanding challenges in the fields of affinity analysis, bibliomining, and technology mining.

Auto-Denoising for EEG Signals Using Generative Adversarial Network

The brain-computer interface (BCI) has many applications in various fields. In EEG-based research, an essential step is signal denoising. In this paper, a generative adversarial network (GAN)-based denoising method is proposed to denoise the multichannel EEG signal automatically. A new loss function is defined to ensure that the filtered signal can retain as much effective original information and energy as possible. This model can imitate and integrate artificial denoising methods, which reduces processing time; hence it can be used for a large amount of data processing. Compared to other neural network denoising models, the proposed model has one more discriminator, which always judges whether the noise is filtered out. The generator is constantly changing the denoising way. To ensure the GAN model generates EEG signals stably, a new normalization method called sample entropy threshold and energy threshold-based (SETET) normalization is proposed to check the abnormal signals and limit the range of EEG signals. After the denoising system is established, although the denoising model uses the different subjects' data for training, it can still apply to the new subjects' data denoising. The experiments discussed in this paper employ the HaLT public dataset. Correlation and root mean square error (RMSE) are used as evaluation criteria. Results reveal that the proposed automatic GAN denoising network achieves the same performance as the manual hybrid artificial denoising method. Moreover, the GAN network makes the denoising process automatic, representing a significant reduction in time.

Thinking out loud, an open-access EEG-based BCI dataset for inner speech recognition

Surface electroencephalography is a standard and noninvasive way to measure electrical brain activity. Recent advances in artificial intelligence led to significant improvements in the automatic detection of brain patterns, allowing increasingly faster, more reliable and accessible Brain-Computer Interfaces. Different paradigms have been used to enable the human-machine interaction and the last few years have broad a mark increase in the interest for interpreting and characterizing the "inner voice" phenomenon. This paradigm, called inner speech, raises the possibility of executing an order just by thinking about it, allowing a "natural" way of controlling external devices. Unfortunately, the lack of publicly available electroencephalography datasets, restricts the development of new techniques for inner speech recognition. A ten-participant dataset acquired under this and two others related paradigms, recorded with an acquisition system of 136 channels, is presented. The main purpose of this work is to provide the scientific community with an open-access multiclass electroencephalography database of inner speech commands that could be used for better understanding of the related brain mechanisms.

Imaginary Finger Movements Decoding Using Empirical Mode Decomposition and a Stacked BiLSTM Architecture

Motor Imagery Electroencephalogram (MI-EEG) signals are widely used in Brain-Computer Interfaces (BCI). MI-EEG signals of large limbs movements have been explored in recent researches because they deliver relevant classification rates for BCI systems. However, smaller and noisy signals corresponding to hand-finger imagined movements are less frequently used because they are difficult to classify. This study proposes a method for decoding finger imagined movements of the right hand. For this purpose, MI-EEG signals from C3, Cz, P3, and Pz sensors were carefully selected to be processed in the proposed framework. Therefore, a method based on Empirical Mode Decomposition (EMD) is used to tackle the problem of noisy signals. At the same time, the sequence classification is performed by a stacked Bidirectional Long Short-Term Memory (BiLSTM) network. The proposed method was evaluated using k-fold cross-validation on a public dataset, obtaining an accuracy of 82.26%.

EEGdenoiseNet: a benchmark dataset for deep learning solutions of EEG denoising

Objective.Deep learning (DL) networks are increasingly attracting attention across various fields, including electroencephalography (EEG) signal processing. These models provide comparable performance to that of traditional techniques. At present, however, there is a lack of well-structured and standardized datasets with specific benchmark limit the development of DL solutions for EEG denoising.Approach.Here, we present EEGdenoiseNet, a benchmark EEG dataset that is suited for training and testing DL-based denoising models, as well as for performance comparisons across models. EEGdenoiseNet contains 4514 clean EEG segments, 3400 ocular artifact segments and 5598 muscular artifact segments, allowing users to synthesize contaminated EEG segments with the ground-truth clean EEG.Main results.We used EEGdenoiseNet to evaluate denoising performance of four classical networks (a fully-connected network, a simple and a complex convolution network, and a recurrent neural network). Our results suggested that DL methods have great potential for EEG denoising even under high noise contamination.Significance.Through EEGdenoiseNet, we hope to accelerate the development of the emerging field of DL-based EEG denoising. The dataset and code are available athttps://github.com/ncclabsustech/EEGdenoiseNet.

Brain-Computer Interface: Advancement and Challenges

Brain-Computer Interface (BCI) is an advanced and multidisciplinary active research domain based on neuroscience, signal processing, biomedical sensors, hardware, etc. Since the last decades, several groundbreaking research has been conducted in this domain. Still, no comprehensive review that covers the BCI domain completely has been conducted yet. Hence, a comprehensive overview of the BCI domain is presented in this study. This study covers several applications of BCI and upholds the significance of this domain. Then, each element of BCI systems, including techniques, datasets, feature extraction methods, evaluation measurement matrices, existing BCI algorithms, and classifiers, are explained concisely. In addition, a brief overview of the technologies or hardware, mostly sensors used in BCI, is appended. Finally, the paper investigates several unsolved challenges of the BCI and explains them with possible solutions.

CNN based classification of motor imaginary using variational mode decomposed EEG-spectrum image

A novel approach of preprocessing EEG signals by generating spectrum image for effective Convolutional Neural Network (CNN) based classification for Motor Imaginary (MI) recognition is proposed. The approach involves extracting the Variational Mode Decomposition (VMD) modes of EEG signals, from which the Short Time Fourier Transform (STFT) of all the modes are arranged to form EEG spectrum images. The EEG spectrum images generated are provided as input image to CNN. The two generic CNN architectures for MI classification (EEGNet and DeepConvNet) and the architectures for pattern recognition (AlexNet and LeNet) are used in this study. Among the four architectures, EEGNet provides average accuracies of 91.37%, 94.41%, 85.67% and 90.21% for the four datasets used to validate the proposed approach. Consistently better results in comparison with results in recent literature demonstrate that the EEG spectrum image generation using VMD-STFT is a promising method for the time frequency analysis of EEG signals.

Changes in EEG Brain Connectivity Caused by Short-Term BCI Neurofeedback-Rehabilitation Training: A Case Study

Background

In combined with neurofeedback, Motor Imagery (MI) based Brain-Computer Interface (BCI) has been an effective long-term treatment therapy for motor dysfunction caused by neurological injury in the brain (e.g., post-stroke hemiplegia). However, individual neurological differences have led to variability in the single sessions of rehabilitation training. Research on the impact of short training sessions on brain functioning patterns can help evaluate and standardize the short duration of rehabilitation training. In this paper, we use the electroencephalogram (EEG) signals to explore the brain patterns’ changes after a short-term rehabilitation training.

Materials and Methods

Using an EEG-BCI system, we analyzed the changes in short-term (about 1-h) MI training data with and without visual feedback, respectively. We first examined the EEG signal’s Mu band power’s attenuation caused by Event-Related Desynchronization (ERD). Then we use the EEG’s Event-Related Potentials (ERP) features to construct brain networks and evaluate the training from multiple perspectives: small-scale based on single nodes, medium-scale based on hemispheres, and large-scale based on all-brain.

Results

Results showed no significant difference in the ERD power attenuation estimation in both groups. But the neurofeedback group’s ERP brain network parameters had substantial changes and trend properties compared to the group without feedback. The neurofeedback group’s Mu band power’s attenuation increased but not significantly (fitting line slope = 0.2, t-test value p > 0.05) after the short-term MI training, while the non-feedback group occurred an insignificant decrease (fitting line slope = −0.4, t-test value p > 0.05). In the ERP-based brain network analysis, the neurofeedback group’s network parameters were attenuated in all scales significantly (t-test value: p < 0.01); while the non-feedback group’s most network parameters didn’t change significantly (t-test value: p > 0.05).

Conclusion

The MI-BCI training’s short-term effects does not show up in the ERD analysis significantly but can be detected by ERP-based network analysis significantly. Results inspire the efficient evaluation of short-term rehabilitation training and provide a useful reference for subsequent studies.

Benefits of deep learning classification of continuous noninvasive brain-computer interface control

Objective. Noninvasive brain-computer interfaces (BCIs) assist paralyzed patients by providing access to the world without requiring surgical intervention. Prior work has suggested that EEG motor imagery based BCI can benefit from increased decoding accuracy through the application of deep learning methods, such as convolutional neural networks (CNNs).Approach. Here, we examine whether these improvements can generalize to practical scenarios such as continuous control tasks (as opposed to prior work reporting one classification per trial), whether valuable information remains latent outside of the motor cortex (as no prior work has compared full scalp coverage to motor only electrode montages), and the existing challenges to the practical implementation of deep-learning based continuous BCI control.Main results. We report that: (1) deep learning methods significantly increase offline performance compared to standard methods on an independent, large, and longitudinal online motor imagery BCI dataset with up to 4-classes and continuous 2D feedback; (2) our results suggest that a variety of neural biomarkers for BCI, including those outside the motor cortex, can be detected and used to improve performance through deep learning methods, and (3) tuning neural network output will be an important step in optimizing online BCI control, as we found the CNN models trained with full scalp EEG also significantly reduce the average trial length in a simulated online cursor control environment.Significance. This work demonstrates the benefits of CNNs classification during BCI control while providing evidence that electrode montage selection and the mapping of CNN output to device control will be important design choices in CNN based BCIs.

Cross-correlation based discriminant criterion for channel selection in motor imagery BCI systems

Objective.Many electroencephalogram (EEG)-based brain-computer interface (BCI) systems use a large amount of channels for higher performance, which is time-consuming to set up and inconvenient for practical applications. Finding an optimal subset of channels without compromising the performance is a necessary and challenging task.Approach.In this article, we proposed a cross-correlation based discriminant criterion (XCDC) which assesses the importance of a channel for discriminating the mental states of different motor imagery (MI) tasks. Channels are ranked and selected according to the proposed criterion. The efficacy of XCDC is evaluated on two MI EEG datasets.Main results.On the two datasets, the proposed method reduces the channel number from 71 and 15 to under 18 and 11 respectively without compromising the classification accuracy on unseen data. Under the same constraint of accuracy, the proposed method requires fewer channels than existing channel selection methods based on Pearson's correlation coefficient and common spatial pattern. Visualization of XCDC shows consistent results with neurophysiological principles.Significance.This work proposes a quantitative criterion for assessing and ranking the importance of EEG channels in MI tasks and provides a practical method for selecting the ranked channels in the calibration phase of MI BCI systems, which alleviates the computational complexity and configuration difficulty in the subsequent steps, leading to real-time and more convenient BCI systems.

A novel convolutional neural network method for subject-independent driver drowsiness detection based on single-channel data and EEG alpha spindles

A significant number of fatal accidents are caused by drowsy drivers worldwide. Driver drowsiness detection based on electroencephalography (EEG) signals has high accuracy and is known as a reference method for evaluating drowsiness. Among brain waves, EEG alpha spindle activity is a silent feature of decreasing alertness levels. In this paper, based on the detection of EEG alpha spindles, a novel driver drowsiness detection method is presented. The EEG spindles were detected using Continuous Wavelet Transform (CWT) analysis and the Morlet function. To do so, the signal is divided into 30-s epochs, and the observer rating of drowsiness determines the drowsiness level in each epoch. Tests were conducted on 17 healthy males in a driving simulator with a monotonous driving scenario. The Convolutional Neural Network (CNN) is used for classifying EEG signals and automatically learns features of the early drowsy state. The subject-independent classification results for single-channel P4 show 94% accuracy.

Continuous sensorimotor rhythm based brain computer interface learning in a large population

Brain computer interfaces (BCIs) are valuable tools that expand the nature of communication through bypassing traditional neuromuscular pathways. The non-invasive, intuitive, and continuous nature of sensorimotor rhythm (SMR) based BCIs enables individuals to control computers, robotic arms, wheel-chairs, and even drones by decoding motor imagination from electroencephalography (EEG). Large and uniform datasets are needed to design, evaluate, and improve the BCI algorithms. In this work, we release a large and longitudinal dataset collected during a study that examined how individuals learn to control SMR-BCIs. The dataset contains over 600 hours of EEG recordings collected during online and continuous BCI control from 62 healthy adults, (mostly) right hand dominant participants, across (up to) 11 training sessions per participant. The data record consists of 598 recording sessions, and over 250,000 trials of 4 different motor-imagery-based BCI tasks. The current dataset presents one of the largest and most complex SMR-BCI datasets publicly available to date and should be useful for the development of improved algorithms for BCI control.

Motor Imagery Classification Based on a Recurrent-Convolutional Architecture to Control a Hexapod Robot

Advances in the field of Brain-Computer Interfaces (BCIs) aim, among other applications, to improve the movement capacities of people suffering from the loss of motor skills. The main challenge in this area is to achieve real-time and accurate bio-signal processing for pattern recognition, especially in Motor Imagery (MI). The significant interaction between brain signals and controllable machines requires instantaneous brain data decoding. In this study, an embedded BCI system based on fist MI signals is developed. It uses an Emotiv EPOC+ Brainwear®, an Altera SoCKit® development board, and a hexapod robot for testing locomotion imagery commands. The system is tested to detect the imagined movements of closing and opening the left and right hand to control the robot locomotion. Electroencephalogram (EEG) signals associated with the motion tasks are sensed on the human sensorimotor cortex. Next, the SoCKit processes the data to identify the commands allowing the controlled robot locomotion. The classification of MI-EEG signals from the F3, F4, FC5, and FC6 sensors is performed using a hybrid architecture of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. This method takes advantage of the deep learning recognition model to develop a real-time embedded BCI system, where signal processing must be seamless and precise. The proposed method is evaluated using k-fold cross-validation on both created and public Scientific-Data datasets. Our dataset is comprised of 2400 trials obtained from four test subjects, lasting three seconds of closing and opening fist movement imagination. The recognition tasks reach 84.69% and 79.2% accuracy using our data and a state-of-the-art dataset, respectively. Numerical results support that the motor imagery EEG signals can be successfully applied in BCI systems to control mobile robots and related applications such as intelligent vehicles.

Deep Learning in Mining Biological Data

Recent technological advancements in data acquisition tools allowed life scientists to acquire multimodal data from different biological application domains. Categorized in three broad types (i.e. images, signals, and sequences), these data are huge in amount and complex in nature. Mining such enormous amount of data for pattern recognition is a big challenge and requires sophisticated data-intensive machine learning techniques. Artificial neural network-based learning systems are well known for their pattern recognition capabilities, and lately their deep architectures-known as deep learning (DL)-have been successfully applied to solve many complex pattern recognition problems. To investigate how DL-especially its different architectures-has contributed and been utilized in the mining of biological data pertaining to those three types, a meta-analysis has been performed and the resulting resources have been critically analysed. Focusing on the use of DL to analyse patterns in data from diverse biological domains, this work investigates different DL architectures' applications to these data. This is followed by an exploration of available open access data sources pertaining to the three data types along with popular open-source DL tools applicable to these data. Also, comparative investigations of these tools from qualitative, quantitative, and benchmarking perspectives are provided. Finally, some open research challenges in using DL to mine biological data are outlined and a number of possible future perspectives are put forward.