Upper limb movements can be decoded from the time-domain of low-frequency EEG

The Effect of Caffeine on Movement-Related Cortical Potential Morphology and Detection

Movement-related cortical potential (MRCP) is observed in EEG recordings prior to a voluntary movement. It has been used for e.g., quantifying motor learning and for brain-computer interfacing (BCIs). The MRCP amplitude is affected by various factors, but the effect of caffeine is underexplored. The aim of this study was to investigate if a cup of coffee with 85 mg caffeine modulated the MRCP amplitude and the classification of MRCPs versus idle activity, which estimates BCI performance. Twenty-six healthy participants performed 2 × 100 ankle dorsiflexion separated by a 10-min break before a cup of coffee was consumed, followed by another 100 movements. EEG was recorded during the movements and divided into epochs, which were averaged to extract three average MRCPs that were compared. Also, idle activity epochs were extracted. Features were extracted from the epochs and classified using random forest analysis. The MRCP amplitude did not change after consuming caffeine. There was a slight increase of two percentage points in the classification accuracy after consuming caffeine. In conclusion, a cup of coffee with 85 mg caffeine does not affect the MRCP amplitude, and improves MRCP-based BCI performance slightly. The findings suggest that drinking coffee is only a minor confounder in MRCP-related studies.

Multimodal decoding of error processing in a virtual reality flight simulation

Technological advances in head-mounted displays (HMDs) facilitate the acquisition of physiological data of the user, such as gaze, pupil size, or heart rate. Still, interactions with such systems can be prone to errors, including unintended behavior or unexpected changes in the presented virtual environments. In this study, we investigated if multimodal physiological data can be used to decode error processing, which has been studied, to date, with brain signals only. We examined the feasibility of decoding errors solely with pupil size data and proposed a hybrid decoding approach combining electroencephalographic (EEG) and pupillometric signals. Moreover, we analyzed if hybrid approaches can improve existing EEG-based classification approaches and focused on setups that offer increased usability for practical applications, such as the presented game-like virtual reality flight simulation. Our results indicate that classifiers trained with pupil size data can decode errors above chance. Moreover, hybrid approaches yielded improved performance compared to EEG-based decoders in setups with a reduced number of channels, which is crucial for many out-of-the-lab scenarios. These findings contribute to the development of hybrid brain-computer interfaces, particularly in combination with wearable devices, which allow for easy acquisition of additional physiological data.

Effect of the period of EEG signals on the decoding of motor information

Decoding movement information from electroencephalogram to construct brain-computer interface has promising applications. The EEG data during the entire motor imagery (MI) period or movement execution (ME) period is generally decoded, and calculation of numerous information and massive dataset is time-consuming. In order to improve decoding efficiency, the joint topographic maps of the brain activation state of 15 subjects were studied during different periods. The results showed that the activation intensity of the preparation period in the motor imagery experiment was higher than during the exercise period, while during the exercise period, the activation intensity was higher than in the preparation period in the movement execution experiment. Hence, the wavelet neural network was used to decode the six-class movements including elbow flexion/extension, forearm pronation/supination and hand open/close in periods of MI/ME. The experimental results show that the accuracy obtained in the preparation period is the highest in the motor imagery experiment, which is 80.77%. On the other hand, the highest accuracy obtained in the exercise period of the movement execution experiment is 79.26%. It further proves that the optimized period is a key decoding factor to reduce the cost of calculation, and this new decoding method is effective to build a more intelligent brain-computer interface system.

Towards unlocking motor control in spinal cord injured by applying an online EEG-based framework to decode motor intention, trajectory and error processing

Brain-computer interfaces (BCIs) can translate brain signals directly into commands for external devices. Electroencephalography (EEG)-based BCIs mostly rely on the classification of discrete mental states, leading to unintuitive control. The ERC-funded project "Feel Your Reach" aimed to establish a novel framework based on continuous decoding of hand/arm movement intention, for a more natural and intuitive control. Over the years, we investigated various aspects of natural control, however, the individual components had not yet been integrated. Here, we present a first implementation of the framework in a comprehensive online study, combining (i) goal-directed movement intention, (ii) trajectory decoding, and (iii) error processing in a unique closed-loop control paradigm. Testing involved twelve able-bodied volunteers, performing attempted movements, and one spinal cord injured (SCI) participant. Similar movement-related cortical potentials and error potentials to previous studies were revealed, and the attempted movement trajectories were overall reconstructed. Source analysis confirmed the involvement of sensorimotor and posterior parietal areas for goal-directed movement intention and trajectory decoding. The increased experiment complexity and duration led to a decreased performance than each single BCI. Nevertheless, the study contributes to understanding natural motor control, providing insights for more intuitive strategies for individuals with motor impairments.

A Few-Shot Transfer Learning Approach for Motion Intention Decoding from Electroencephalographic Signals

In this study, a few-shot transfer learning approach was introduced to decode movement intention from electroencephalographic (EEG) signals, allowing to recognize new tasks with minimal adaptation. To this end, a dataset of EEG signals recorded during the preparation of complex sub-movements was created from a publicly available data collection. The dataset was divided into two parts: the source domain dataset (including 5 classes) and the support (target domain) dataset, (including 2 classes) with no overlap between the two datasets in terms of classes. The proposed methodology consists in projecting EEG signals into the space-frequency-time domain, in processing such projections (rearranged in channels × frequency frames) by means of a custom EEG-based deep neural network (denoted as EEGframeNET5), and then adapting the system to recognize new tasks through a few-shot transfer learning approach. The proposed method achieved an average accuracy of 72.45 ± 4.19% in the 5-way classification of samples from the source domain dataset, outperforming comparable studies in the literature. In the second phase of the study, a few-shot transfer learning approach was proposed to adapt the neural system and make it able to recognize new tasks in the support dataset. The results demonstrated the system's ability to adapt and recognize new tasks with an average accuracy of 80 ± 0.12% in discriminating hand opening/closing preparation and outperforming reported results in the literature. This study suggests the effectiveness of EEG in capturing information related to the motor preparation of complex movements, potentially paving the way for BCI systems based on motion planning decoding. The proposed methodology could be straightforwardly extended to advanced EEG signal processing in other scenarios, such as motor imagery or neural disorder classification.

TSPNet: a time-spatial parallel network for classification of EEG-based multiclass upper limb motor imagery BCI

The classification of electroencephalogram (EEG) motor imagery signals has emerged as a prominent research focus within the realm of brain-computer interfaces. Nevertheless, the conventional, limited categories (typically just two or four) offered by brain-computer interfaces fail to provide an extensive array of control modes. To address this challenge, we propose the Time-Spatial Parallel Network (TSPNet) for recognizing six distinct categories of upper limb motor imagery. Within TSPNet, temporal and spatial features are extracted separately, with the time dimension feature extractor and spatial dimension feature extractor performing their respective functions. Following this, the Time-Spatial Parallel Feature Extractor is employed to decouple the connection between temporal and spatial features, thus diminishing feature redundancy. The Time-Spatial Parallel Feature Extractor deploys a gating mechanism to optimize weight distribution and parallelize time-spatial features. Additionally, we introduce a feature visualization algorithm based on signal occlusion frequency to facilitate a qualitative analysis of TSPNet. In a six-category scenario, TSPNet achieved an accuracy of 49.1% ± 0.043 on our dataset and 49.7% ± 0.029 on a public dataset. Experimental results conclusively establish that TSPNet outperforms other deep learning methods in classifying data from these two datasets. Moreover, visualization results vividly illustrate that our proposed framework can generate distinctive classifier patterns for multiple categories of upper limb motor imagery, discerned through signals of varying frequencies. These findings underscore that, in comparison to other deep learning methods, TSPNet excels in intention recognition, which bears immense significance for non-invasive brain-computer interfaces.

Pallidal and Cortical Oscillations in Freely Moving Patients With Dystonia

OBJECTIVES

To evaluate the correlation between the pallidal local field potentials (LFPs) activity and the cortical oscillations (at rest and during several motor tasks) in two freely moving patients with generalized dystonia and pallidal deep brain stimulation (DBS).

MATERIALS AND METHODS

Two women with isolated generalized dystonia were selected for bilateral globus pallidus internus (GPi) DBS. After the electrodes' implantation, cortical activity was recorded by a portable electroencephalography (EEG) system simultaneously with GPi LFPs activity, during several motor tasks, gait, and rest condition. Recordings were not performed during stimulation. EEG and LFPs signals relative to each specific movement were coupled together and grouped in neck/upper limbs movements and gait. Power spectral density (PSD), EEG-LFP coherence (through envelope of imaginary coherence operator), and 1/f exponent of LFP-PSD background were calculated.

RESULTS

In both patients, the pallidal LFPs PSD at rest was characterized by prominent 4-12 Hz activity. Voluntary movements increased activity in the theta (θ) band (4-7 Hz) compared to rest, in both LFPs and EEG signals. Gait induced a drastic raise of θ activity in both patients' pallidal activity, less marked for the EEG signal. A coherence peak within the 8-13 Hz range was found between pallidal LFPs and EEG recorded at rest.

CONCLUSIONS

Neck/upper limbs voluntary movements and gait suppressed the GPi-LFPs-cortical-EEG coherence and differently impacted both EEG and LFPs low frequency activity. These findings suggest a selective modulation of the cortico-basal ganglia network activity in dystonia.

Motor Imagery EEG Classification Based on a Weighted Multi-Branch Structure Suitable for Multisubject Data

OBJECTIVE

Electroencephalogram (EEG) signal recognition based on deep learning technology requires the support of sufficient data. However, training data scarcity usually occurs in subject-specific motor imagery tasks unless multisubject data can be used to enlarge training data. Unfortunately, because of the large discrepancies between data distributions from different subjects, model performance could only be improved marginally or even worsened by simply training on multisubject data.

METHOD

This article proposes a novel weighted multi-branch (WMB) structure for handling multisubject data to solve the problem, in which each branch is responsible for fitting a pair of source-target subject data and adaptive weights are used to integrate all branches or select branches with the largest weights to make the final decision. The proposed WMB structure was applied to six well-known deep learning models (EEGNet, Shallow ConvNet, Deep ConvNet, ResNet, MSFBCNN, and EEG_TCNet) and comprehensive experiments were conducted on EEG datasets BCICIV-2a, BCICIV-2b, high gamma dataset (HGD) and two supplementary datasets.

RESULT

Superior results against the state-of-the-art models have demonstrated the efficacy of the proposed method in subject-specific motor imagery EEG classification. For example, the proposed WMB_EEGNet achieved classification accuracies of 84.14%, 90.23%, and 97.81% on BCICIV-2a, BCICIV-2b and HGD, respectively.

CONCLUSION

It is clear that the proposed WMB structure is capable to make good use of multisubject data with large distribution discrepancies for subject-specific EEG classification.

Recognition of motor intentions from EEGs of the same upper limb by signal traceability and Riemannian geometry features

Introduction

The electroencephalographic (EEG) based on the motor imagery task is derived from the physiological electrical signal caused by the autonomous activity of the brain. Its weak potential difference changes make it easy to be overwhelmed by noise, and the EEG acquisition method has a natural limitation of low spatial resolution. These have brought significant obstacles to high-precision recognition, especially the recognition of the motion intention of the same upper limb.

Methods

This research proposes a method that combines signal traceability and Riemannian geometric features to identify six motor intentions of the same upper limb, including grasping/holding of the palm, flexion/extension of the elbow, and abduction/adduction of the shoulder. First, the EEG data of electrodes irrelevant to the task were screened out by low-resolution brain electromagnetic tomography. Subsequently, tangential spatial features are extracted by the Riemannian geometry framework in the covariance matrix estimated from the reconstructed EEG signals. The learned Riemannian geometric features are used for pattern recognition by a support vector machine with a linear kernel function.

Results

The average accuracy of the six classifications on the data set of 15 participants is 22.47%, the accuracy is 19.34% without signal traceability, the accuracy is 18.07% when the features are the filter bank common spatial pattern (FBCSP), and the accuracy is 16.7% without signal traceability and characterized by FBCSP.

Discussion

The results show that the proposed method can significantly improve the accuracy of intent recognition. In addressing the issue of temporal variability in EEG data for active Brain-Machine Interfaces, our method achieved an average standard deviation of 2.98 through model transfer on different days' data.

TDLNet: Transfer Data Learning Network for Cross-Subject Classification Based on Multiclass Upper Limb Motor Imagery EEG

The limited number of brain-computer interface based on motor imagery (MI-BCI) instruction sets for different movements of single limbs makes it difficult to meet practical application requirements. Therefore, designing a single-limb, multi-category motor imagery (MI) paradigm and effectively decoding it is one of the important research directions in the future development of MI-BCI. Furthermore, one of the major challenges in MI-BCI is the difficulty of classifying brain activity across different individuals. In this article, the transfer data learning network (TDLNet) is proposed to achieve the cross-subject intention recognition for multiclass upper limb motor imagery. In TDLNet, the Transfer Data Module (TDM) is used to process cross-subject electroencephalogram (EEG) signals in groups and then fuse cross-subject channel features through two one-dimensional convolutions. The Residual Attention Mechanism Module (RAMM) assigns weights to each EEG signal channel and dynamically focuses on the EEG signal channels most relevant to a specific task. Additionally, a feature visualization algorithm based on occlusion signal frequency is proposed to qualitatively analyze the proposed TDLNet. The experimental results show that TDLNet achieves the best classification results on two datasets compared to CNN-based reference methods and transfer learning method. In the 6-class scenario, TDLNet obtained an accuracy of 65%±0.05 on the UML6 dataset and 63%±0.06 on the GRAZ dataset. The visualization results demonstrate that the proposed framework can produce distinct classifier patterns for multiple categories of upper limb motor imagery through signals of different frequencies. The ULM6 dataset is available at https://dx.doi.org/10.21227/8qw6-f578.

Challenges of neural interfaces for stroke motor rehabilitation

More than 85% of stroke survivors suffer from different degrees of disability for the rest of their lives. They will require support that can vary from occasional to full time assistance. These conditions are also associated to an enormous economic impact for their families and health care systems. Current rehabilitation treatments have limited efficacy and their long-term effect is controversial. Here we review different challenges related to the design and development of neural interfaces for rehabilitative purposes. We analyze current bibliographic evidence of the effect of neuro-feedback in functional motor rehabilitation of stroke patients. We highlight the potential of these systems to reconnect brain and muscles. We also describe all aspects that should be taken into account to restore motor control. Our aim with this work is to help researchers designing interfaces that demonstrate and validate neuromodulation strategies to enforce a contingent and functional neural linkage between the central and the peripheral nervous system. We thus give clues to design systems that can improve or/and re-activate neuroplastic mechanisms and open a new recovery window for stroke patients.

Multi-Class Classification of Upper Limb Movements With Filter Bank Task-Related Component Analysis

The classification of limb movements can provide with control commands in non-invasive brain-computer interface. Previous studies on the classification of limb movements have focused on the classification of left/right limbs; however, the classification of different types of upper limb movements has often been ignored despite that it provides more active-evoked control commands in the brain-computer interface. Nevertheless, few machine learning method can be used as the state-of-the-art method in the multi-class classification of limb movements. This work focuses on the multi-class classification of upper limb movements and proposes the multi-class filter bank task-related component analysis (mFBTRCA) method, which consists of three steps: spatial filtering, similarity measuring and filter bank selection. The spatial filter, namely the task-related component analysis, is first used to remove noise from EEG signals. The canonical correlation measures the similarity of the spatial-filtered signals and is used for feature extraction. The correlation features are extracted from multiple low-frequency filter banks. The minimum-redundancy maximum-relevance selects the essential features from all the correlation features, and finally, the support vector machine is used to classify the selected features. The proposed method compared against previously used models is evaluated using two datasets. mFBTRCA achieved a classification accuracy of 0.4193 ± 0.0780 (7 classes) and 0.4032 ± 0.0714 (5 classes), respectively, which improves on the best accuracies achieved using the compared methods (0.3590 ± 0.0645 and 0.3159 ± 0.0736, respectively). The proposed method is expected to provide more control commands in the applications of non-invasive brain-computer interfaces.

Spinal Cord Injury Patients Exhibit Changes in Motor-Related Activity and Topographic Distribution

Spinal Cord Injury (SCI) is a common disease that usually limits the patient's independence by affecting their motor function. SCI patients usually present neuroplasticity, which allows brain signals transmission through spread pathways. Some innovative rehabilitation therapies, such as functional electrical stimulation (FES) or Brain-computer interfaces (BCIs) jointly with motor neuroprostheses, provide hope for functional restoration. BCIs require the analysis of event-related EEG potentials (ERPs). Movement-related cortical potentials (MRCPs) and event-related desynchroni-zation and synchronization (ERD/ERS) are the most commonly studied ERPs during motor activity. ERPs of healthy subjects may vary from SCI patients. Thus, this study aimed to compare ERPs between healthy subjects and SCI patients during upper-limb movements (forearm supination and pronation, and hand open). Differences between controls and SCI patients were shown in terms of ERPs' amplitude as well as in topographic maps. Changes in amplitude were more substantial in ERD potentials than in MRCPs, while topographic maps showed better localization of all features in healthy patients. The level of SCI injury determines the patients' mobility. A comparison between complete, partial and no motor function subjects showed lower values of feature's amplitudes in the latter group.Clinical Relevance- This demonstrates the existence of significant statistical differences between healthy and SCI subjects, and might be helpful when performing SCI rehabilitation techniques such as designing BCI and neuroprostheses, or analyzing and understanding the brain plasticity process.

Upper Limb Movement Execution Classification using Electroencephalography for Brain Computer Interface

An accurate classification of upper limb movements using electroencephalogram (EEG) signals is gaining significant importance in recent years due to the prevalence of brain-computer interfaces. The upper limbs in the human body are crucial since different skeletal segments combine to make a range of motions that helps us in our trivial daily tasks. Decoding EEG-based upper limb movements can be of great help to people with spinal cord injury (SCI) or other neuro-muscular diseases such as amyotrophic lateral sclerosis (ALS), primary lateral sclerosis, and periodic paralysis. This can manifest in a loss of sensory and motor function, which could make a person reliant on others to provide care in day-to-day activities. We can detect and classify upper limb movement activities, whether they be executed or imagined using an EEG-based brain-computer interface (BCI). Toward this goal, we focus our attention on decoding movement execution (ME) of the upper limb in this study. For this purpose, we utilize a publicly available EEG dataset that contains EEG signal recordings from fifteen subjects acquired using a 61-channel EEG device. We propose a method to classify four ME classes for different subjects using spectrograms of the EEG data through pre-trained deep learning (DL) models. Our proposed method of using EEG spectrograms for the classification of ME has shown significant results, where the highest average classification accuracy (for four ME classes) obtained is 87.36%, with one subject achieving the best classification accuracy of 97.03%.Clinical relevance- This research shows that movement execution of upper limbs is classified with significant accuracy by employing a spectrogram of the EEG signals and a pre-trained deep learning model which is fine-tuned for the downstream task.

Motor Imagery Classification Based on EEG Sensing with Visual and Vibrotactile Guidance

Motor imagery (MI) is a technique of imagining the performance of a motor task without actually using the muscles. When employed in a brain-computer interface (BCI) supported by electroencephalographic (EEG) sensors, it can be used as a successful method of human-computer interaction. In this paper, the performance of six different classifiers, namely linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF), and three classifiers from the family of convolutional neural networks (CNN), is evaluated using EEG MI datasets. The study investigates the effectiveness of these classifiers on MI, guided by a static visual cue, dynamic visual guidance, and a combination of dynamic visual and vibrotactile (somatosensory) guidance. The effect of filtering passband during data preprocessing was also investigated. The results show that the ResNet-based CNN significantly outperforms the competing classifiers on both vibrotactile and visually guided data when detecting different directions of MI. Preprocessing the data using low-frequency signal features proves to be a better solution to achieve higher classification accuracy. It has also been shown that vibrotactile guidance has a significant impact on classification accuracy, with the associated improvement particularly evident for architecturally simpler classifiers. These findings have important implications for the development of EEG-based BCIs, as they provide valuable insight into the suitability of different classifiers for different contexts of use.

Detection of motor imagery based on short-term entropy of time-frequency representations

BACKGROUND

Motor imagery is a cognitive process of imagining a performance of a motor task without employing the actual movement of muscles. It is often used in rehabilitation and utilized in assistive technologies to control a brain-computer interface (BCI). This paper provides a comparison of different time-frequency representations (TFR) and their Rényi and Shannon entropies for sensorimotor rhythm (SMR) based motor imagery control signals in electroencephalographic (EEG) data. The motor imagery task was guided by visual guidance, visual and vibrotactile (somatosensory) guidance or visual cue only.

RESULTS

When using TFR-based entropy features as an input for classification of different interaction intentions, higher accuracies were achieved (up to 99.87%) in comparison to regular time-series amplitude features (for which accuracy was up to 85.91%), which is an increase when compared to existing methods. In particular, the highest accuracy was achieved for the classification of the motor imagery versus the baseline (rest state) when using Shannon entropy with Reassigned Pseudo Wigner-Ville time-frequency representation.

CONCLUSIONS

Our findings suggest that the quantity of useful classifiable motor imagery information (entropy output) changes during the period of motor imagery in comparison to baseline period; as a result, there is an increase in the accuracy and F1 score of classification when using entropy features in comparison to the accuracy and the F1 of classification when using amplitude features, hence, it is manifested as an improvement of the ability to detect motor imagery.

Getting off track: Cortical feedback processing network modulated by continuous error signal during target-feedback mismatch

Performance monitoring and feedback processing - especially in the wake of erroneous outcomes - represent a crucial aspect of everyday life, allowing us to deal with imminent threats in the short term but also promoting necessary behavioral adjustments in the long term to avoid future conflicts. Over the last thirty years, research extensively analyzed the neural correlates of processing discrete error stimuli, unveiling the error-related negativity (ERN) and error positivity (Pe) as two main components of the cognitive response. However, the connection between the ERN/Pe and distinct stages of error processing, ranging from action monitoring to subsequent corrective behavior, remains ambiguous. Furthermore, mundane actions such as steering a vehicle already transgress the scope of discrete erroneous events and demand fine-tuned feedback control, and thus, the processing of continuous error signals - a topic scarcely researched at present. We analyzed two electroencephalography datasets to investigate the processing of continuous erroneous signals during a target tracking task, employing feedback in various levels and modalities. We observed significant differences between correct (slightly delayed) and erroneous feedback conditions in the larger one of the two datasets that we analyzed, both in sensor and source space. Furthermore, we found strong error-induced modulations that appeared consistent across datasets and error conditions, indicating a clear order of engagement of specific brain regions that correspond to individual components of error processing.

Transfer Learning in Trajectory Decoding: Sensor or Source Space?

In this study, across-participant and across-session transfer learning was investigated to minimize the calibration time of the brain-computer interface (BCI) system in the context of continuous hand trajectory decoding. We reanalyzed data from a study with 10 able-bodied participants across three sessions. A leave-one-participant-out (LOPO) model was utilized as a starting model. Recursive exponentially weighted partial least squares regression (REW-PLS) was employed to overcome the memory limitation due to the large pool of training data. We considered four scenarios: generalized with no update (Gen), generalized with cumulative update (GenC), and individual models with cumulative (IndC) and non-cumulative (Ind) updates, with each one trained with sensor-space features or source-space features. The decoding performance in generalized models (Gen and GenC) was lower than the chance level. In individual models, the cumulative update (IndC) showed no significant improvement over the non-cumulative model (Ind). The performance showed the decoder's incapability to generalize across participants and sessions in this task. The results suggested that the best correlation could be achieved with the sensor-space individual model, despite additional anatomical information in the source-space features. The decoding pattern showed a more localized pattern around the precuneus over three sessions in Ind models.

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.

Recognition of single upper limb motor imagery tasks from EEG using multi-branch fusion convolutional neural network

Motor imagery-based brain-computer interfaces (MI-BCI) have important application values in the field of neurorehabilitation and robot control. At present, MI-BCI mostly use bilateral upper limb motor tasks, but there are relatively few studies on single upper limb MI tasks. In this work, we conducted studies on the recognition of motor imagery EEG signals of the right upper limb and proposed a multi-branch fusion convolutional neural network (MF-CNN) for learning the features of the raw EEG signals as well as the two-dimensional time-frequency maps at the same time. The dataset used in this study contained three types of motor imagery tasks: extending the arm, rotating the wrist, and grasping the object, 25 subjects were included. In the binary classification experiment between the grasping object and the arm-extending tasks, MF-CNN achieved an average classification accuracy of 78.52% and kappa value of 0.57. When all three tasks were used for classification, the accuracy and kappa value were 57.06% and 0.36, respectively. The comparison results showed that the classification performance of MF-CNN is higher than that of single CNN branch algorithms in both binary-class and three-class classification. In conclusion, MF-CNN makes full use of the time-domain and frequency-domain features of EEG, can improve the decoding accuracy of single limb motor imagery tasks, and it contributes to the application of MI-BCI in motor function rehabilitation training after stroke.

NeuroGrasp: Real-Time EEG Classification of High-Level Motor Imagery Tasks Using a Dual-Stage Deep Learning Framework

Brain-computer interfaces (BCIs) have been widely employed to identify and estimate a user's intention to trigger a robotic device by decoding motor imagery (MI) from an electroencephalogram (EEG). However, developing a BCI system driven by MI related to natural hand-grasp tasks is challenging due to its high complexity. Although numerous BCI studies have successfully decoded large body parts, such as the movement intention of both hands, arms, or legs, research on MI decoding of high-level behaviors such as hand grasping is essential to further expand the versatility of MI-based BCIs. In this study, we propose NeuroGrasp, a dual-stage deep learning framework that decodes multiple hand grasping from EEG signals under the MI paradigm. The proposed method effectively uses an EEG and electromyography (EMG)-based learning, such that EEG-based inference at test phase becomes possible. The EMG guidance during model training allows BCIs to predict hand grasp types from EEG signals accurately. Consequently, NeuroGrasp improved classification performance offline, and demonstrated a stable classification performance online. Across 12 subjects, we obtained an average offline classification accuracy of 0.68 (±0.09) in four-grasp-type classifications and 0.86 (±0.04) in two-grasp category classifications. In addition, we obtained an average online classification accuracy of 0.65 (±0.09) and 0.79 (±0.09) across six high-performance subjects. Because the proposed method has demonstrated a stable classification performance when evaluated either online or offline, in the future, we expect that the proposed method could contribute to different BCI applications, including robotic hands or neuroprosthetics for handling everyday objects.

Improving pre-movement pattern detection with filter bank selection

Objective. Pre-movement decoding plays an important role in detecting the onsets of actions using low-frequency electroencephalography (EEG) signals before the movement of an upper limb. In this work, a binary classification method is proposed between two different states.Approach. The proposed method, referred to as filter bank standard task-related component analysis (FBTRCA), is to incorporate filter bank selection into the standard task-related component analysis (STRCA) method. In FBTRCA, the EEG signals are first divided into multiple sub-bands which start at specific fixed frequencies and end frequencies that follow in an arithmetic sequence. The STRCA method is then applied to the EEG signals in these bands to extract CCPs. The minimum redundancy maximum relevance feature selection method is used to select essential features from these correlation patterns in all sub-bands. Finally, the selected features are classified using the binary support vector machine classifier. A convolutional neural network (CNN) is an alternative approach to select canonical correlation patterns.Main Results. Three methods were evaluated using EEG signals in the time window from 2 s before the movement onset to 1 s after the movement onset. In the binary classification between a movement state and the resting state, the FBTRCA achieved an average accuracy of 0.8968 ± 0.0847 while the accuracies of STRCA and CNN were 0.8228 ± 0.1149 and 0.8828 ± 0.0917, respectively. In the binary classification between two actions, the accuracies of STRCA, CNN, and FBTRCA were 0.6611 ± 0.1432, 0.6993 ± 0.1271, 0.7178 ± 0.1274, respectively. Feature selection using filter banks, as in FBTRCA, produces comparable results to STRCA.Significance. The proposed method provides a way to select filter banks in pre-movement decoding, and thus it improves the classification performance. The improved pre-movement decoding of single upper limb movements is expected to provide people with severe motor disabilities with a more natural, non-invasive control of their external devices.

Motor imagery training of goal-directed reaching in relation to imagery of reaching and grasping in healthy people

The study aimed to determine whether four weeks of motor imagery training (MIT) of goal-directed reaching (reaching to grasp task) would affect the cortical activity during motor imagery of reaching (MIR) and grasping (MIG) in the same way. We examined cortical activity regarding event-related potentials (ERPs) in healthy young participants. Our study also evaluated the subjective vividness of the imagery. Furthermore, we aimed to determine the relationship between the subjective assessment of motor imagery (MI) ability to reach and grasp and the cortical activity during those tasks before and after training to understand the underlying neuroplasticity mechanisms. Twenty-seven volunteers participated in MIT of goal-directed reaching and two measurement sessions before and after MIT. During the sessions 128-channel electroencephalography (EEG) was recorded during MIR and MIG. Also, participants assessed the vividness of the MI tasks using a visual analog scale (VAS). The vividness of imagination improved significantly (P < .05) after MIT. A repeated measures ANOVA showed that the task (MIR/MIG) and the location of electrodes had a significant effect on the ERP's amplitude (P < .05). The interaction between the task, location, and session (before/after MIT) also had a significant effect on the ERP's amplitude (P < .05). Finally, the location of electrodes and the interaction between location and session had a significant effect on the ERP's latency (P < .05). We found that MIT influenced the EEG signal associated with reaching differently than grasping. The effect was more pronounced for MIR than for MIG. Correlation analysis showed that changes in the assessed parameters due to MIT reduced the relationship between the subjective evaluation of imagining and the EEG signal. This finding means that the subjective evaluation of imagining cannot be a simple, functional insight into the bioelectrical activity of the cerebral cortex expressed by the ERPs in mental training. The changes we noted in ERPs after MIT may benefit the use of non-invasive EEG in the brain-computer interface (BCI) context.Trial registration: NCT04048083.

Individual finger movement decoding using a novel ultra-high-density electroencephalography-based brain-computer interface system

Brain-Computer Interface (BCI) technology enables users to operate external devices without physical movement. Electroencephalography (EEG) based BCI systems are being actively studied due to their high temporal resolution, convenient usage, and portability. However, fewer studies have been conducted to investigate the impact of high spatial resolution of EEG on decoding precise body motions, such as finger movements, which are essential in activities of daily living. Low spatial sensor resolution, as found in common EEG systems, can be improved by omitting the conventional standard of EEG electrode distribution (the international 10-20 system) and ordinary mounting structures (e.g., flexible caps). In this study, we used newly proposed flexible electrode grids attached directly to the scalp, which provided ultra-high-density EEG (uHD EEG). We explored the performance of the novel system by decoding individual finger movements using a total of 256 channels distributed over the contralateral sensorimotor cortex. Dense distribution and small-sized electrodes result in an inter-electrode distance of 8.6 mm (uHD EEG), while that of conventional EEG is 60 to 65 mm on average. Five healthy subjects participated in the experiment, performed single finger extensions according to a visual cue, and received avatar feedback. This study exploits mu (8-12 Hz) and beta (13-25 Hz) band power features for classification and topography plots. 3D ERD/S activation plots for each frequency band were generated using the MNI-152 template head. A linear support vector machine (SVM) was used for pairwise finger classification. The topography plots showed regular and focal post-cue activation, especially in subjects with optimal signal quality. The average classification accuracy over subjects was 64.8 (6.3)%, with the middle versus ring finger resulting in the highest average accuracy of 70.6 (9.4)%. Further studies are required using the uHD EEG system with real-time feedback and motor imagery tasks to enhance classification performance and establish the basis for BCI finger movement control of external devices.

Influence of the number of trials on evoked motor cortical activity in EEG recordings

OBJECTIVE

Improvements in electroencephalography enable the study of the localization of active brain regions during motor tasks. Movement-related cortical potentials (MRCPs), and event-related desynchronization (ERD) and synchronization (ERS) are the main motor-related cortical phenomena/neural correlates observed when a movement is elicited. When assessing neurological diseases, averaging techniques are commonly applied to characterize motor related processes better. In this case, a large number of trials is required to obtain a motor potential that is representative enough of the subject's condition. This study aimed to assess the effect of a limited number of trials on motor-related activity corresponding to different upper limb movements (elbow flexion/extension, pronation/supination and hand open/close).

APPROACH

An open dataset consisting on 15 healthy subjects was used for the analysis. A Monte Carlo simulation approach was applied to analyse, in a robust way, different typical time- and frequency-domain features, topography, and low-resolution tomography (LORETA).

MAIN RESULTS

Grand average potentials, and topographic and tomographic maps showed few differences when using fewer trials, but shifts in the localization of motor-related activity were found for several individuals. MRCP and beta ERD features were more robust to a limited number of trials, yielding differences lower than 20% for cases with 50 trials or more. Strong correlations between features were obtained for subsets above 50 trials. However, the inter-subject variability increased as the number of trials decreased. The elbow flexion/extension movement showed a more robust performance for a limited number of trials, both in population and in individual-based analysis.

SIGNIFICANCE

Our findings suggested that 50 trials can be an appropriate number to obtain stable motor-related features in terms of differences in the averaged motor features, correlation, and changes in topography and tomography.

Learning neural decoders without labels using multiple data streams

OBJECTIVE

Recent advances in neural decoding have accelerated the development of brain-computer interfaces aimed at assisting users with everyday tasks such as speaking, walking, and manipulating objects. However, current approaches for training neural decoders commonly require large quantities of labeled data, which can be laborious or infeasible to obtain in real-world settings. Alternatively, self-supervised models that share self-generated pseudo-labels between two data streams have shown exceptional performance on unlabeled audio and video data, but it remains unclear how well they extend to neural decoding.

APPROACH

We learn neural decoders without labels by leveraging multiple simultaneously recorded data streams, including neural, kinematic, and physiological signals. Specifically, we apply cross-modal, self-supervised deep clustering to train decoders that can classify movements from brain recordings. After training, we then isolate the decoders for each input data stream and compare the accuracy of decoders trained using cross-modal deep clustering against supervised and unimodal, self-supervised models.

MAIN RESULTS

We find that sharing pseudo-labels between two data streams during training substantially increases decoding performance compared to unimodal, self-supervised models, with accuracies approaching those of supervised decoders trained on labeled data. Next, we extend cross-modal decoder training to three or more modalities, achieving state-of-the-art neural decoding accuracy that matches or slightly exceeds the performance of supervised models. Significance: We demonstrate that cross-modal, self-supervised decoding can be applied to train neural decoders when few or no labels are available and extend the cross-modal framework to share information among three or more data streams, further improving self-supervised training.

Flexible coding scheme for robotic arm control driven by motor imagery decoding

OBJECTIVE

Brain computer interface (BCI) technology is a new way of information exchange, which can effectively convert physiological signals into control instructions of machines. Due to its spontaneity and device-independence, motor imagery (MI) electroencephalography (EEG) signal is used as a common BCI signal source to achieve direct control of external devices. However, the generalization ability of current classification model of MI tasks is still limited. Moreover, the real time prototype is far from established in practice.

APPROACH

In order to solve these problems, this paper proposed an optimized neural network architecture based on our previous work. Firstly, the artifact components in MI-EEG signal are removed by using the threshold and threshold function related to the artifact removal evaluation index, and then the data is augmented by the empirical mode decomposition (EMD) algorithm. Furthermore, ensemble learning (EL) method and fine-tuning strategy in transfer learning (TL) are used to optimize the classification model. Finally, combined with the flexible binary encoding strategy, the EEG signal recognition results are mapped to the control commands of the robotic arm, which realizes the multiple degree of freedom control of the robotic arm.

MAIN RESULTS

The results show that EMD has an obvious data amount enhancement effect on small dataset, and the EL and TL can improve intra-subject and inter-subject model evaluation performance, respectively. The use of binary coding method realizes the expansion of control instructions, i.e., four kinds of MI-EEG signals are used to complete the control of 7 degrees of freedom of the robotic arm.

SIGNIFICANCE

Our work not only improves the classification accuracy of subject and the generality of classification model, but also extends the BCI control instruction set.

Decoding of Turning Intention during Walking Based on EEG Biomarkers

In the EEG literature, there is a lack of asynchronous intention models that realistically propose interfaces for applications that must operate in real time. In this work, a novel BMI approach to detect in real time the intention to turn is proposed. For this purpose, an offline, pseudo-online and online analysis is presented to validate the EEG as a biomarker for the intention to turn. This article presents a methodology for the creation of a BMI that could differentiate two classes: monotonous walk and intention to turn. A comparison of some of the most popular algorithms in the literature is conducted. To filter the signal, two relevant algorithms are used: H∞ filter and ASR. For processing and classification, the mean of the covariance matrices in the Riemannian space was calculated and then, with various classifiers of different types, the distance of the test samples to each class in the Riemannian space was estimated. This dispenses with power-based models and the necessary baseline correction, which is a problem in realistic scenarios. In the cross-validation for a generic selection (valid for any subject) and a personalized one, the results were, on average, 66.2% and 69.6% with the best filter H∞. For the pseudo-online, the custom configuration for each subject was an average of 40.2% TP and 9.3 FP/min; the best subject obtained 43.9% TP and 2.9 FP/min. In the final validation test, this subject obtained 2.5 FP/min and an accuracy rate of 71.43%, and the turn anticipation was 0.21 s on average.

Pseudo-online detection and classification for upper-limb movements

Objective. This study analyzed detection (movement vs. non-movement) and classification (different types of movements) to decode upper-limb movement volitions in a pseudo-online fashion.Approach. Nine healthy subjects executed four self-initiated movements: left wrist extension, right wrist extension, left index finger extension, and right index finger extension. For detection, we investigated the performance of three individual classifiers (support vector machine (SVM), EEGNET, and Riemannian geometry featured SVM) on three frequency bands (0.05-5 Hz, 5-40 Hz, 0.05-40 Hz). The best frequency band and the best classifier combinations were constructed to realize an ensemble processing pipeline using majority voting. For classification, we used adaptive boosted Riemannian geometry model to differentiate contra-lateral and ipsilateral movements.Main results. The ensemble model achieved 79.6 ± 8.8% true positive rate and 3.1 ± 1.2 false positives per minute with 75.3 ± 112.6 ms latency on a pseudo-online detection task. The following classification gave around 67% accuracy to differentiate contralateral movements.Significance. The newly proposed ensemble method and pseudo-online testing procedure could provide a robust brain-computer interface design for movement decoding.

How to successfully classify EEG in motor imagery BCI: a metrological analysis of the state of the art

Objective. Processing strategies are analysed with respect to the classification of electroencephalographic signals related to brain-computer interfaces based on motor imagery. A review of literature is carried out to understand the achievements in motor imagery classification, the most promising trends, and the challenges in replicating these results. Main focus is placed on performance by means of a rigorous metrological analysis carried out in compliance with the international vocabulary of metrology. Hence, classification accuracy and its uncertainty are considered, as well as repeatability and reproducibility.Approach. The paper works included in the review concern the classification of electroencephalographic signals in motor-imagery- based brain-computer interfaces. Article search was carried out in accordance with the PRISMA standard and 89 studies were included.Main results. Statistically-based analyses show that brain-inspired approaches are increasingly proposed, and that these are particularly successful in discriminating against multiple classes. Notably, many proposals involve convolutional neural networks. Instead, classical machine learning approaches are still effective for binary classifications. Many proposals combine common spatial pattern, least absolute shrinkage and selection operator, and support vector machines. Regarding reported classification accuracies, performance above the upper quartile is in the 85 % to 100 % range for the binary case and in the 83 % to 93 % range for multi-class one. Associated uncertainties are up to 6 % while repeatability for a predetermined dataset is up to 8 %. Reproducibility assessment was instead prevented by lack of standardization in experiments.Significance. By relying on the analysed studies, the reader is guided towards the development of a successful processing strategy as a crucial part of a brain-computer interface. Moreover, it is suggested that future studies should extend these approaches on data from more subjects and with custom experiments, even by investigating online operation. This would also enable the quantification of results reproducibility.

Applying Dimensionality Reduction Techniques in Source-Space Electroencephalography via Template and Magnetic Resonance Imaging-Derived Head Models to Continuously Decode Hand Trajectories

Several studies showed evidence supporting the possibility of hand trajectory decoding from low-frequency electroencephalography (EEG). However, the decoding in the source space via source localization is scarcely investigated. In this study, we tried to tackle the problem of collinearity due to the higher number of signals in the source space by two folds: first, we selected signals in predefined regions of interest (ROIs); second, we applied dimensionality reduction techniques to each ROI. The dimensionality reduction techniques were computing the mean (Mean), principal component analysis (PCA), and locality preserving projections (LPP). We also investigated the effect of decoding between utilizing a template head model and a subject-specific head model during the source localization. The results indicated that applying source-space decoding with PCA yielded slightly higher correlations and signal-to-noise (SNR) ratios than the sensor-space approach. We also observed slightly higher correlations and SNRs when applying the subject-specific head model than the template head model. However, the statistical tests revealed no significant differences between the source-space and sensor-space approaches and no significant differences between subject-specific and template head models. The decoder with Mean and PCA utilizes information mainly from precuneus and cuneus to decode the velocity kinematics similarly in the subject-specific and template head models.

Feel Your Reach: An EEG-Based Framework to Continuously Detect Goal-Directed Movements and Error Processing to Gate Kinesthetic Feedback Informed Artificial Arm Control

Establishing the basic knowledge, methodology, and technology for a framework for the continuous decoding of hand/arm movement intention was the aim of the ERC-funded project “Feel Your Reach”. In this work, we review the studies and methods we performed and implemented in the last 6 years, which build the basis for enabling severely paralyzed people to non-invasively control a robotic arm in real-time from electroencephalogram (EEG). In detail, we investigated goal-directed movement detection, decoding of executed and attempted movement trajectories, grasping correlates, error processing, and kinesthetic feedback. Although we have tested some of our approaches already with the target populations, we still need to transfer the “Feel Your Reach” framework to people with cervical spinal cord injury and evaluate the decoders’ performance while participants attempt to perform upper-limb movements. While on the one hand, we made major progress towards this ambitious goal, we also critically discuss current limitations.

Time-Distributed Attention Network for EEG-based Motor Imagery Decoding from the Same Limb

A brain-computer interface (BCI) based on motor imagery (MI) from the same limb can provide an intuitive control pathway but has received limited attention. It is still a challenge to classify multiple MI tasks from the same limb. The goal of this study is to propose a novel decoding method to classify the MI tasks of four joints of the same upper limb and the resting state. EEG signals were collected from 20 participants. A time-distributed attention network (TD-Atten) was proposed to adaptively assign different weights to different classes and frequency bands of the input multiband Common Spatial Pattern (CSP) features. The long short-term memory (LSTM) and dense layers were then used to learn sequential information from the reweight features and perform the classification. Our proposed method outperformed other baseline and deep learning-based methods and obtained the accuracies of 46.8% in the 5-class scenario and 53.4% in the 4-class scenario. The visualization results of attention weights indicated that the proposed framework can adaptively pay attention to alpha-band related features in MI tasks, which was consistent with the analysis of brain activation patterns. These results demonstrated the feasibility and interpretability of the attention mechanism in MI decoding and the potential of this fine MI paradigm to be applied for the control of a robotic arm or a neural prosthesis.

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.

Measurement(s)	brain activity • inner speech command
Technology Type(s)	electroencephalography
Sample Characteristic - Organism	Homo sapiens

Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.16783987

Workshops of the Eighth International Brain-Computer Interface Meeting: BCIs: The Next Frontier

The Eighth International Brain-Computer Interface (BCI) Meeting was held June 7-9th, 2021 in a virtual format. The conference continued the BCI Meeting series' interactive nature with 21 workshops covering topics in BCI (also called brain-machine interface) research. As in the past, workshops covered the breadth of topics in BCI. Some workshops provided detailed examinations of specific methods, hardware, or processes. Others focused on specific BCI applications or user groups. Several workshops continued consensus building efforts designed to create BCI standards and increase the ease of comparisons between studies and the potential for meta-analysis and large multi-site clinical trials. Ethical and translational considerations were both the primary topic for some workshops or an important secondary consideration for others. The range of BCI applications continues to expand, with more workshops focusing on approaches that can extend beyond the needs of those with physical impairments. This paper summarizes each workshop, provides background information and references for further study, presents an overview of the discussion topics, and describes the conclusion, challenges, or initiatives that resulted from the interactions and discussion at the workshop.

SSA with CWT and k-Means for Eye-Blink Artifact Removal from Single-Channel EEG Signals

Recently, the use of portable electroencephalogram (EEG) devices to record brain signals in both health care monitoring and in other applications, such as fatigue detection in drivers, has been increased due to its low cost and ease of use. However, the measured EEG signals always mix with the electrooculogram (EOG), which are results due to eyelid blinking or eye movements. The eye-blinking/movement is an uncontrollable activity that results in a high-amplitude slow-time varying component that is mixed in the measured EEG signal. The presence of these artifacts misled our understanding of the underlying brain state. As the portable EEG devices comprise few EEG channels or sometimes a single EEG channel, classical artifact removal techniques such as blind source separation methods cannot be used to remove these artifacts from a single-channel EEG signal. Hence, there is a demand for the development of new single-channel-based artifact removal techniques. Singular spectrum analysis (SSA) has been widely used as a single-channel-based eye-blink artifact removal technique. However, while removing the artifact, the low-frequency components from the non-artifact region of the EEG signal are also removed by SSA. To preserve these low-frequency components, in this paper, we have proposed a new methodology by integrating the SSA with continuous wavelet transform (CWT) and the k-means clustering algorithm that removes the eye-blink artifact from the single-channel EEG signals without altering the low frequencies of the EEG signal. The proposed method is evaluated on both synthetic and real EEG signals. The results also show the superiority of the proposed method over the existing methods.

Motor Imagery Classification Using Inter-Task Transfer Learning via A Channel-Wise Variational Autoencoder-based Convolutional Neural Network

Highly sophisticated control based on a brain-computer interface (BCI) requires decoding kinematic information from brain signals. The forearm is a region of the upper limb that is often used in everyday life, but intuitive movements within the same limb have rarely been investigated in previous BCI studies. In this study, we focused on various forearm movement decoding from electroencephalography (EEG) signals using a small number of samples. Ten healthy participants took part in an experiment and performed motor execution (ME) and motor imagery (MI) of the intuitive movement tasks (Dataset I). We propose a convolutional neural network using a channel-wise variational autoencoder (CVNet) based on inter-task transfer learning. We approached that training the reconstructed ME-EEG signals together will also achieve more sufficient classification performance with only a small amount of MI-EEG signals. The proposed CVNet was validated on our own Dataset I and a public dataset, BNCI Horizon 2020 (Dataset II). The classification accuracies of various movements are confirmed to be 0.83 (±0.04) and 0.69 (±0.04) for Dataset I and II, respectively. The results show that the proposed method exhibits performance increases of approximately 0.09~0.27 and 0.08~0.24 compared with the conventional models for Dataset I and II, respectively. The outcomes suggest that the training model for decoding imagined movements can be performed using data from ME and a small number of data samples from MI. Hence, it is presented the feasibility of BCI learning strategies that can sufficiently learn deep learning with a few amount of calibration dataset and time only, with stable performance.

On the Extraction of Purely Motor EEG Neural Correlates during an Upper Limb Visuomotor Task

Deciphering and analyzing the neural correlates of different movements from the same limb using electroencephalography (EEG) would represent a notable breakthrough in the field of sensorimotor neurophysiology. Functional movements involve concurrent posture co-ordination and head and eye movements, which create electrical activity that affects EEG recordings. In this paper, we revisit the identification of brain signatures of different reaching movements using EEG and present, test, and validate a protocol to separate the effect of head and eye movements from a reaching task-related visuomotor brain activity. Ten healthy participants performed reaching movements under two different conditions: avoiding head and eye movements and moving with no constrains. Reaching movements can be identified from EEG with unconstrained eye and head movement, whereas the discriminability of the signals drops to chance level otherwise. These results show that neural patterns associated with different arm movements could only be extracted from EEG if the eye and head movements occurred concurrently with the task, polluting the recordings. Although these findings do not imply that brain correlates of reaching directions cannot be identified from EEG, they show the consequences that ignoring these events can have in any EEG study that includes a visuomotor task.

Electroencephalogram Source Imaging and Brain Network Based Natural Grasps Decoding

Studying the decoding process of complex grasping movement is of great significance to the field of motor rehabilitation. This study aims to decode five natural reach-and-grasp types using sources of movement-related cortical potential (MRCP) and investigate their difference in cortical signal characteristics and network structures. Electroencephalogram signals were gathered from 40 channels of eight healthy subjects. In an audio cue-based experiment, subjects were instructed to keep no-movement condition or perform five natural reach-and-grasp movements: palmar, pinch, push, twist and plug. We projected MRCP into source space and used average source amplitudes in 24 regions of interest as classification features. Besides, functional connectivity was calculated using phase locking value. Six-class classification results showed that a similar grand average peak performance of 49.35% can be achieved using source features, with only two-thirds of the number of channel features. Besides, source imaging maps and brain networks presented different patterns between each condition. Grasping pattern analysis indicated that the modules in the execution stage focus more on internal communication than in the planning stage. The former stage was related to the parietal lobe, whereas the latter was associated with the frontal lobe. This study demonstrates the superiority and effectiveness of source imaging technology and reveals the spread mechanism and network structure of five natural reach-and-grasp movements. We believe that our work will contribute to the understanding of the generation mechanism of grasping movement and promote a natural and intuitive control of brain–computer interface.

Robust anticipation of continuous steering actions from electroencephalographic data during simulated driving

Driving a car requires high cognitive demands, from sustained attention to perception and action planning. Recent research investigated the neural processes reflecting the planning of driving actions, aiming to better understand the factors leading to driving errors and to devise methodologies to anticipate and prevent such errors by monitoring the driver’s cognitive state and intention. While such anticipation was shown for discrete driving actions, such as emergency braking, there is no evidence for robust neural signatures of continuous action planning. This study aims to fill this gap by investigating continuous steering actions during a driving task in a car simulator with multimodal recordings of behavioural and electroencephalography (EEG) signals. System identification is used to assess whether robust neurophysiological signatures emerge before steering actions. Linear decoding models are then used to determine whether such cortical signals can predict continuous steering actions with progressively longer anticipation. Results point to significant EEG signatures of continuous action planning. Such neural signals show consistent dynamics across participants for anticipations up to 1 s, while individual-subject neural activity could reliably decode steering actions and predict future actions for anticipations up to 1.8 s. Finally, we use canonical correlation analysis to attempt disentangling brain and non-brain contributors to the EEG-based decoding. Our results suggest that low-frequency cortical dynamics are involved in the planning of steering actions and that EEG is sensitive to that neural activity. As a result, we propose a framework to investigate anticipatory neural activity in realistic continuous motor tasks.

Response of the Cerebral Cortex to Resistance and Non-resistance Exercise Under Different Trajectories: A Functional Near-Infrared Spectroscopy Study

Background: At present, the effects of upper limb movement are generally evaluated from the level of motor performance. The purpose of this study is to evaluate the response of the cerebral cortex to different upper limb movement patterns from the perspective of neurophysiology.

Method: Thirty healthy adults (12 females, 18 males, mean age 23.9 ± 0.9 years) took resistance and non-resistance exercises under four trajectories (T1: left and right straight-line movement; T2: front and back straight-line movement; T3: clockwise and anticlockwise drawing circle movement; and T4: clockwise and anticlockwise character ⁕ movement). Each movement included a set of periodic motions composed of a 30-s task and a 30-s rest. Functional near-infrared spectroscopy (fNIRS) was used to measure cerebral blood flow dynamics. Primary somatosensory cortex (S1), supplementary motor area (SMA), pre-motor area (PMA), primary motor cortex (M1), and dorsolateral prefrontal cortex (DLPFC) were chosen as regions of interests (ROIs). Activation maps and symmetric heat maps were applied to assess the response of the cerebral cortex to different motion patterns.

Result: The activation of the brain cortex was significantly increased during resistance movement for each participant. Specifically, S1, SMA, PMA, and M1 had higher participation during both non-resistance movement and resistance movement. Compared to non-resistance movement, the resistance movement caused an obvious response in the cerebral cortex. The task state and the resting state were distinguished more obviously in the resistance movement. Four trajectories can be distinguished under non-resistance movement.

Conclusion: This study confirmed that the response of the cerebral motor cortex to different motion patterns was different from that of the neurophysiological level. It may provide a reference for the evaluation of resistance training effects in the future.

Development of Machine-Learning Algorithms for Recognition of Subjects' Upper Limb Movement Intention Using Electroencephalogram Signals

This study aims to classify rest and upper limb movements execution and intention using electroencephalogram (EEG) signals by developing machine-learning (ML) algorithms. Five different MLs are implemented, including k-Nearest Neighbor (KNN), Linear Discriminant Analysis (LDA), Naïve Bayes (NB), Support Vector Machine (SVM), and Random Forest (RF). The EEG data from fifteen healthy subjects during motor execution (ME) and motor imagination (MI) are preprocessed with Independent Component Analysis (ICA) to reduce eye-blinking associated artifacts. A sliding window technique varying from 1 s to 2 s is used to segment the signals. The majority voting (MV) strategy is employed during the post-processing stage. The results show that the application of ICA increases the accuracy of MI up to 6%, which is improved further by 1-2% using the MV (p<0.05). However, the improvement in the accuracies is more significant in MI (>5%) than in ME (<1%), indicating a more significant influence of eye-blinking artifacts in the EEG signals during MI than ME. Among the MLs, both RF and SVM consistently produced better accuracies in both ME and MI. Using RF, the 2 s window size produced the highest accuracies in both ME and MI than the smaller window sizes.

Noise-assisted Multivariate Empirical Mode Decomposition based Causal Decomposition for Detecting Upper Limb Movement in EEG-EMG Hybrid Brain Computer Interface

EEG-EMG based hybrid Brain Computer Interface (hBCI) utilizes the brain-muscle physiological system to interpret and identify motor behaviors, and transmit human intelligence to automated machines in AI applications such as neurorehabilitations and brain-like intelligence. The study introduces a hBCI method for motor behaviors, where multiple time series of the brain neuromuscular network are introduced to indicate brain-muscle causal interactions, and features are extracted based on Relative Causal Strengths (RCSs) derived by Noise-assisted Multivariate Empirical Mode Decomposition (NA-MEMD) based Causal Decomposition. The complex process in brain neuromuscular interactions is specifically investigated towards a monitoring task of upper limb movement, whose 63-channel EEGs and 2-channel EMGs are composed of data inputs. The energy and frequency factors counted from RCSs were extracted as Core Features (CFs). Results showed accuracies of 91.4% and 81.4% with CFs for identifying cascaded (No Movement and Movement Execution) and 3-class (No Movement, Right Movement, and Left Movement) using Naive Bayes classifier, respectively. Moreover, those reached 100% and 94.3% when employing CFs combined with eigenvalues processed by Common Spatial Pattern (CSP). This initial work implies a novel causality inference based hBCI solution for the detection of human upper limb movement.

Decoding Different Reach-and-Grasp Movements Using Noninvasive Electroencephalogram

Grasping is one of the most indispensable functions of humans. Decoding reach-and-grasp actions from electroencephalograms (EEGs) is of great significance for the realization of intuitive and natural neuroprosthesis control, and the recovery or reconstruction of hand functions of patients with motor disorders. In this paper, we investigated decoding five different reach-and-grasp movements closely related to daily life using movement-related cortical potentials (MRCPs). In the experiment, nine healthy subjects were asked to naturally execute five different reach-and-grasp movements on the designed experimental platform, namely palmar, pinch, push, twist, and plug grasp. A total of 480 trials per subject (80 trials per condition) were recorded. The MRCPs amplitude from low-frequency (0.3-3 Hz) EEG signals were used as decoding features for further offline analysis. Average binary classification accuracy for grasping vs. the no-movement condition peaked at 75.06 ± 6.8%. Peak average accuracy for grasping vs. grasping conditions of 64.95 ± 7.4% could be reached. Grand average peak accuracy of multiclassification for five grasping conditions reached 36.7 ± 6.8% at 1.45 s after the movement onset. The analysis of MRCPs indicated that all the grasping conditions are more pronounced than the no-movement condition, and there are also significant differences between the grasping conditions. These findings clearly proved the feasibility of decoding multiple reach-and-grasp actions from noninvasive EEG signals. This work is significant for the natural and intuitive BCI application, particularly for neuroprosthesis control or developing an active human-machine interaction system, such as rehabilitation robot.

Directional Decoding From EEG in a Center-Out Motor Imagery Task With Visual and Vibrotactile Guidance

Motor imagery is a popular technique employed as a motor rehabilitation tool, or to control assistive devices to substitute lost motor function. In both said areas of application, artificial somatosensory input helps to mirror the sensorimotor loop by providing kinesthetic feedback or guidance in a more intuitive fashion than via visual input. In this work, we study directional and movement-related information in electroencephalographic signals acquired during a visually guided center-out motor imagery task in two conditions, i.e., with and without additional somatosensory input in the form of vibrotactile guidance. Imagined movements to the right and forward could be discriminated in low-frequency electroencephalographic amplitudes with group level peak accuracies of 70% with vibrotactile guidance, and 67% without vibrotactile guidance. The peak accuracies with and without vibrotactile guidance were not significantly different. Furthermore, the motor imagery could be classified against a resting baseline with group level accuracies between 76 and 83%, using either low-frequency amplitude features or μ and β power spectral features. On average, accuracies were higher with vibrotactile guidance, while this difference was only significant in the latter set of features. Our findings suggest that directional information in low-frequency electroencephalographic amplitudes is retained in the presence of vibrotactile guidance. Moreover, they hint at an enhancing effect on motor-related μ and β spectral features when vibrotactile guidance is provided.

Corticomuscular and Intermuscular Coupling in Simple Hand Movements to Enable a Hybrid Brain-Computer Interface

Hybrid Brain-Computer Interfaces (BCIs) for upper limb rehabilitation after stroke should enable the reinforcement of "more normal" brain and muscular activity. Here, we propose the combination of corticomuscular coherence (CMC) and intermuscular coherence (IMC) as control features for a novel hybrid BCI for rehabilitation purposes. Multiple electroencephalographic (EEG) signals and surface electromyography (EMG) from 5 muscles per side were collected in 20 healthy participants performing finger extension (Ext) and grasping (Grasp) with both dominant and non-dominant hand. Grand average of CMC and IMC patterns showed a bilateral sensorimotor area as well as multiple muscles involvement. CMC and IMC values were used as features to classify each task versus rest and Ext versus Grasp. We demonstrated that a combination of CMC and IMC features allows for classification of both movements versus rest with better performance (Area Under the receiver operating characteristic Curve, AUC) for the Ext movement (0.97) with respect to Grasp (0.88). Classification of Ext versus Grasp also showed high performances (0.99). All in all, these preliminary findings indicate that the combination of CMC and IMC could provide for a comprehensive framework for simple hand movements to eventually be employed in a hybrid BCI system for post-stroke rehabilitation.

Predicting motor behavior: an efficient EEG signal processing pipeline to detect brain states with potential therapeutic relevance for VR-based neurorehabilitation

Virtual reality (VR)-based motor therapy is an emerging approach in neurorehabilitation. The combination of VR with electroencephalography (EEG) presents further opportunities to improve therapeutic efficacy by personalizing the paradigm. Specifically, the idea is to synchronize the choice and timing of stimuli in the perceived virtual world with fluctuating brain states relevant to motor behavior. Here, we present an open source EEG single-trial based classification pipeline that is designed to identify ongoing brain states predictive of the planning and execution of movements. 9 healthy volunteers each performed 1080 trials of a repetitive reaching task with an implicit two-alternative forced choice, i.e., use of the right or left hand, in response to the appearance of a visual target. The performance of the EEG decoding pipeline was assessed with respect to classification accuracy of right vs. left arm use, based on the EEG signal at the time of the stimulus. Different features, feature extraction methods, and classifiers were compared at different time windows; the number and location of informative EEG channels and the number of calibration trials needed were also quantified, as well as any benefits from individual-level optimization of pipeline parameters. This resulted in a set of recommended parameters that achieved an average 83.3% correct prediction on never-before-seen testing data, and a state-of-the-art 77.1% in a real-time simulation. Neurophysiological plausibility of the resulting classifiers was assessed by time-frequency and event-related potential analyses, as well as by Independent Component Analysis topographies and cortical source localization. We expect that this pipeline will facilitate the identification of relevant brain states as prospective therapeutic targets in closed-loop EEG-VR motor neurorehabilitation.