Decoding Imagined 3D Hand Movement Trajectories From EEG: Evidence to Support the Use of Mu, Beta, and Low Gamma Oscillations

Dual model transfer learning to compensate for individual variability in brain-computer interface

BACKGROUND AND OBJECTIVE

Recent advancements in brain-computer interface (BCI) technology have seen a significant shift towards incorporating complex decoding models such as deep neural networks (DNNs) to enhance performance. These models are particularly crucial for sophisticated tasks such as regression for decoding arbitrary movements. However, these BCI models trained and tested on individual data often face challenges with limited performance and generalizability across different subjects. This limitation is primarily due to a tremendous number of parameters of DNN models. Training complex models demands extensive datasets. Nevertheless, group data from many subjects may not produce sufficient decoding performance because of inherent variability in neural signals both across individuals and over time METHODS: To address these challenges, this study proposed a transfer learning approach that could effectively adapt to subject-specific variability in cortical regions. Our method involved training two separate movement decoding models: one on individual data and another on pooled group data. We then created a salience map for each cortical region from the individual model, which helped us identify the input's contribution variance across subjects. Based on the contribution variance, we combined individual and group models using a modified knowledge distillation framework. This approach allowed the group model to be universally applicable by assigning greater weights to input data, while the individual model was fine-tuned to focus on areas with significant individual variance RESULTS: Our combined model effectively encapsulated individual variability. We validated this approach with nine subjects performing arm-reaching tasks, with our method outperforming (mean correlation coefficient, r = 0.75) both individual (r = 0.70) and group models (r = 0.40) in decoding performance. In particular, there were notable improvements in cases where individual models showed low performances (e.g., r = 0.50 in the individual decoder to r = 0.61 in the proposed decoder) CONCLUSIONS: These results not only demonstrate the potential of our method for robust BCI, but also underscore its ability to generalize individual data for broader applicability.

Macroscopic brain dynamics beyond contralateral primary motor cortex for movement prediction

This study investigates the complex relationship between upper limb movement direction and macroscopic neural signals in the brain, which is critical for understanding brain-computer interfaces (BCI). Conventional BCI research has primarily focused on a local area, such as the contralateral primary motor cortex (M1), relying on the population-based decoding method with microelectrode arrays. In contrast, macroscopic approaches such as electroencephalography (EEG) and magnetoencephalography (MEG) utilize numerous electrodes to cover broader brain regions. This study probes the potential differences in the mechanisms of microscopic and macroscopic methods. It is important to determine which neural activities effectively predict movements. To investigate this, we analyzed MEG data from nine right-handed participants while performing arm-reaching tasks. We employed dynamic statistical parametric mapping (dSPM) to estimate source activity and built a decoding model composed of long short-term memory (LSTM) and a multilayer perceptron to predict movement trajectories. This model achieved a high correlation coefficient of 0.79 between actual and predicted trajectories. Subsequently, we identified brain regions sensitive to predicting movement direction using the integrated gradients (IG) method, which assesses the predictive contribution of each source activity. The resulting salience map demonstrated a distribution without significant differences across motor-related regions, including M1. Predictions based solely on M1 activity yielded a correlation coefficient of 0.42, nearly half as effective as predictions incorporating all source activities. This suggests that upper limb movements are influenced by various factors such as movement coordination, planning, body and target position recognition, and control, beyond simple muscle activity. All of the activities are needed in the decoding model using macroscopic signals. Our findings also revealed that contralateral and ipsilateral hemispheres contribute equally to movement prediction, implying that BCIs could potentially benefit patients with brain damage in the contralateral hemisphere by utilizing brain signals from the ipsilateral hemisphere. In conclusion, this study demonstrates that macroscopic activity from large brain regions significantly contributes to predicting upper limb movement. Non-invasive BCI systems would require a comprehensive collection of neural signals from multiple brain regions.

Decoding temporal muscle synergy patterns based on brain activity for upper extremity in ADL movements

Muscle synergies have been hypothesized as specific predefined motor primitives that the central nervous system can reduce the complexity of motor control by using them, but how these are expressed in brain activity is ambiguous yet. The main purpose of this paper is to develop synergy-based neural decoding of motor primitives, so for the first time, brain activity and muscle synergy map of the upper extremity was investigated in the activity of daily living movements. To find the relationship between brain activities and muscle synergies, electroencephalogram (EEG) and electromyogram (EMG) signals were acquired simultaneously during activities of daily living. To extract the maximum correlation of neural commands with muscle synergies, application of a combined partial least squares and canonical correlation analysis (PLS-CCA) method was proposed. The Elman neural network was used to decode the relationship between extracted motor commands and muscle synergies. The performance of proposed method was evaluated with tenfold cross-validation and muscle synergy estimation of brain activity with R, VAF, and MSE of 84 ± 2.6%, 70 ± 4.7%, and 0.00011 ± 0.00002 were quantified respectively. Furthermore, the similarity between actual and reconstructed muscle activations was achieved more than 92% for correlation coefficient. To compare with the existing methods, our results showed significantly more accuracy of the model performance. Our results confirm that use of the expression of muscle synergies in brain activity can estimate the neural decoding performance for motor control that can be used to develop neurorehabilitation tools such as neuroprosthesis.

Decoding movement kinematics from EEG using an interpretable convolutional neural network

Continuous decoding of hand kinematics has been recently explored for the intuitive control of electroencephalography (EEG)-based Brain-Computer Interfaces (BCIs). Deep neural networks (DNNs) are emerging as powerful decoders, for their ability to automatically learn features from lightly pre-processed signals. However, DNNs for kinematics decoding lack in the interpretability of the learned features and are only used to realize within-subject decoders without testing other training approaches potentially beneficial for reducing calibration time, such as transfer learning. Here, we aim to overcome these limitations by using an interpretable convolutional neural network (ICNN) to decode 2-D hand kinematics (position and velocity) from EEG in a pursuit tracking task performed by 13 participants. The ICNN is trained using both within-subject and cross-subject strategies, and also testing the feasibility of transferring the knowledge learned on other subjects on a new one. Moreover, the network eases the interpretation of learned spectral and spatial EEG features. Our ICNN outperformed most of the other state-of-the-art decoders, showing the best trade-off between performance, size, and training time. Furthermore, transfer learning improved kinematics prediction in the low data regime. The network attributed the highest relevance for decoding to the delta-band across all subjects, and to higher frequencies (alpha, beta, low-gamma) for a cluster of them; contralateral central and parieto-occipital sites were the most relevant, reflecting the involvement of sensorimotor, visual and visuo-motor processing. The approach improved the quality of kinematics prediction from the EEG, at the same time allowing interpretation of the most relevant spectral and spatial features.

A comprehensive review on motion trajectory reconstruction for EEG-based brain-computer interface

The advance in neuroscience and computer technology over the past decades have made brain-computer interface (BCI) a most promising area of neurorehabilitation and neurophysiology research. Limb motion decoding has gradually become a hot topic in the field of BCI. Decoding neural activity related to limb movement trajectory is considered to be of great help to the development of assistive and rehabilitation strategies for motor-impaired users. Although a variety of decoding methods have been proposed for limb trajectory reconstruction, there does not yet exist a review that covers the performance evaluation of these decoding methods. To alleviate this vacancy, in this paper, we evaluate EEG-based limb trajectory decoding methods regarding their advantages and disadvantages from a variety of perspectives. Specifically, we first introduce the differences in motor execution and motor imagery in limb trajectory reconstruction with different spaces (2D and 3D). Then, we discuss the limb motion trajectory reconstruction methods including experiment paradigm, EEG pre-processing, feature extraction and selection, decoding methods, and result evaluation. Finally, we expound on the open problem and future outlooks.

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.

Microstate feature fusion for distinguishing AD from MCI

Electroencephalogram (EEG) microstates provide powerful tools for identifying EEG features due to their rich temporal information. In this study, we tested whether microstates can measure the severity of Alzheimer's disease (AD) and mild cognitive impairment (MCI) in patients and effectively distinguish AD from MCI. We defined two features using transition probabilities (TPs), and one was used to evaluate between-group differences in microstate parameters to assess the within-group consistency of TPs and MMSE scores. Another feature was used to distinguish AD from MCI in machine learning models. Tests showed that there were between-group differences in the temporal characteristics of microstates, and some kinds of TPs were significantly correlated with MMSE scores within groups. Based on our newly defined time-factor transition probabilities (TTPs) feature and partial accumulation strategy, we obtained promising scores for accuracy, sensitivity, and specificity of 0.938, 0.923, and 0.947, respectively. These results provide evidence for microstates as a neurobiological marker of AD.

Feature stability and setup minimization for EEG-EMG-enabled monitoring systems

Delivering health care at home emerged as a key advancement to reduce healthcare costs and infection risks, as during the SARS-Cov2 pandemic. In particular, in motor training applications, wearable and portable devices can be employed for movement recognition and monitoring of the associated brain signals. This is one of the contexts where it is essential to minimize the monitoring setup and the amount of data to collect, process, and share. In this paper, we address this challenge for a monitoring system that includes high-dimensional EEG and EMG data for the classification of a specific type of hand movement. We fuse EEG and EMG into the magnitude squared coherence (MSC) signal, from which we extracted features using different algorithms (one from the authors) to solve binary classification problems. Finally, we propose a mapping-and-aggregation strategy to increase the interpretability of the machine learning results. The proposed approach provides very low mis-classification errors ( < 0.1 ), with very few and stable MSC features ( < 10 % of the initial set of available features). Furthermore, we identified a common pattern across algorithms and classification problems, i.e., the activation of the centro-parietal brain areas and arm's muscles in 8-80 Hz frequency band, in line with previous literature. Thus, this study represents a step forward to the minimization of a reliable EEG-EMG setup to enable gesture recognition.

Decoding trajectories of imagined hand movement using electrocorticograms for brain-machine interface

OBJECTIVE

Reaching hand movement is an important motor skill actively examined in brain-computer interface (BCI). Among various components of movement analyzed is the hand's trajectory, which describes the hand's continuous positions in three-dimensional space. While a large body of studies have investigated the decoding of real movements and the reconstruction of real hand movement trajectories from neural signals, fewer studies have attempted to decode the trajectory of imagined hand movement. To develop BCI systems for patients with hand motor dysfunctions, the systems essentially require to achieve movement-free control of external devices, which is only possible through successful decoding of purely imagined hand movement.

APPROACH

To achieve this goal, this study used a machine learning technique (i.e., the variational Bayesian least square) to analyze the electrocorticogram (ECoG) of eighteen epilepsy patients obtained from when they performed movement execution (ME) and kinesthetic movement imagination (KMI) of the reach-and-grasp hand action.

MAIN RESULTS

The variational Bayesian decoding model was able to successfully predict the imagined trajectories of hand movement significantly above chance level. The Pearson's correlation coefficient between imagined and predicted trajectories was 0.3393 and 0.4936 for the KMI (KMI trials only) and MEKMI paradigm (alternating trials of ME and KMI) respectively.

SIGNIFICANCE

This study demonstrated a high accuracy of prediction for trajectories of imagined hand movement, and more importantly, higher decoding accuracy of imagined trajectories in the MEKMI paradigm than in the KMI paradigm solely.

Direction decoding of imagined hand movements using subject-specific features from parietal EEG

OBJECTIVE

Research on decoding brain signals for controlling external devices is rapidly emerging, owing to its versatile potential applications including neuro-prosthetic control and neurorehabilitation. Electroencephalogram (EEG)-based non-invasive Brain Computer Interface (BCI) systems decode brain signals to establish an augmented communication and control pathway between the brain and the computer. The development of an efficient BCI system requires accurate decoding of neural activity underlying user's intentions. This study investigates the directional tuning of Electroencephalogram (EEG) characteristics from posterior parietal region, associated with bidirectional hand movement imagination (motor imagery) in left and right directions.

APPROACH

The imagined movement directions of the chosen hand were decoded using a combination of envelope and phase features derived from parietal EEG of both hemispheres. The proposed algorithm uses wavelet for spectral decomposition, and discriminative subject-specific subband levels are identified based on Fisher analysis of envelope and phase features. The selected features from the discriminative subband levels are used for classifying left and right motor imagery directions of the hand using Support Vector Machine Classifier. Furthermore, the performance of the proposed algorithm is evaluated by incorporating a maximum variance-based EEG time bin selection algorithm.

MAIN RESULTS

With the time bin selection approach using subject-specific features, the proposed algorithm yielded an average left vs right motor imagery direction decoding accuracy of 73.33% across 15 healthy subjects. In addition, decoding accuracy offered by the phase features was higher than that of the envelope features, indicating the importance of phase features in MI kinematics decoding.

SIGNIFICANCE

The results reveal the significance of parietal EEG in decoding imagined kinematics and open new possibilities for future BCI research.

Reconstructing Synergy-Based Hand Grasp Kinematics from Electroencephalographic Signals

Brain-machine interfaces (BMIs) have become increasingly popular in restoring the lost motor function in individuals with disabilities. Several research studies suggest that the CNS may employ synergies or movement primitives to reduce the complexity of control rather than controlling each DoF independently, and the synergies can be used as an optimal control mechanism by the CNS in simplifying and achieving complex movements. Our group has previously demonstrated neural decoding of synergy-based hand movements and used synergies effectively in driving hand exoskeletons. In this study, ten healthy right-handed participants were asked to perform six types of hand grasps representative of the activities of daily living while their neural activities were recorded using electroencephalography (EEG). From half of the participants, hand kinematic synergies were derived, and a neural decoder was developed, based on the correlation between hand synergies and corresponding cortical activity, using multivariate linear regression. Using the synergies and the neural decoder derived from the first half of the participants and only cortical activities from the remaining half of the participants, their hand kinematics were reconstructed with an average accuracy above 70%. Potential applications of synergy-based BMIs for controlling assistive devices in individuals with upper limb motor deficits, implications of the results in individuals with stroke and the limitations of the study were discussed.

Coupled versus decoupled visuomotor feedback: Differential frontoparietal activity during curved reach planning on simultaneous functional near-infrared spectroscopy and electroencephalography

INTRODUCTION

Interacting with the environment requires the planning and execution of reach-to-target movements along given reach trajectory paths. Human neural mechanisms for the motor planning of linear, or point-to-point, reaching movements are relatively well studied. However, the corresponding representations for curved and more complex reaching movements require further investigation. Additionally, the visual and proprioceptive feedback of hand positioning can be spatially and sequentially coupled in alignment (e.g., directly reaching for an object), termed coupled visuomotor feedback, or spatially decoupled (e.g., dragging the computer mouse forward to move the cursor upward), termed decoupled visuomotor feedback. During reach planning, visuomotor processing routes may differ across feedback types.

METHODS

We investigated the involvement of the frontoparietal regions, including the superior parietal lobule (SPL), dorsal premotor cortex (PMd), and dorsolateral prefrontal cortex (dlPFC), in curved reach planning under different feedback conditions. Participants engaged in two delayed-response reaching tasks with identical starting and target position sets but different reach trajectory paths (linear or curved) under two feedback conditions (coupled or decoupled). Neural responses in frontoparietal regions were analyzed using a combination of functional near-infrared spectroscopy and electroencephalography.

RESULTS

The results revealed that, regarding the cue period, curved reach planning had a higher hemodynamic response in the left SPL and bilateral PMd and a smaller high-beta power in the left parietal regions than linear reach planning. Regarding the delay period, higher hemodynamic responses during curved reach planning were observed in the right dlPFC for decoupled feedback than those for coupled feedback.

CONCLUSION

These findings suggest the crucial involvement of both SPL and PMd activities in trajectory-path processing for curved reach planning. Moreover, the dlPFC may be especially involved in the planning of curved reaching movements under decoupled feedback conditions. Thus, this study provides insight into the neural mechanisms underlying reaching function via different feedback conditions.

Continuous Decoding of Hand Movement From EEG Signals Using Phase-Based Connectivity Features

The principal goal of the brain-computer interface (BCI) is to translate brain signals into meaningful commands to control external devices or neuroprostheses to restore lost functions of patients with severe motor disabilities. The invasive recording of brain signals involves numerous health issues. Therefore, BCIs based on non-invasive recording modalities such as electroencephalography (EEG) are safer and more comfortable for the patients. The BCI requires reconstructing continuous movement parameters such as position or velocity for practical application of neuroprostheses. The BCI studies in continuous decoding have extensively relied on extracting features from the amplitude of brain signals, whereas the brain connectivity features have rarely been explored. This study aims to investigate the feasibility of using phase-based connectivity features in decoding continuous hand movements from EEG signals. To this end, the EEG data were collected from seven healthy subjects performing a 2D center-out hand movement task in four orthogonal directions. The phase-locking value (PLV) and magnitude-squared coherence (MSC) are exploited as connectivity features along with multiple linear regression (MLR) for decoding hand positions. A brute-force search approach is employed to find the best channel pairs for extracting features related to hand movements. The results reveal that the regression models based on PLV and MSC features achieve the average Pearson correlations of 0.43 ± 0.03 and 0.42 ± 0.06, respectively, between predicted and actual trajectories over all subjects. The delta and alpha band features have the most contribution in regression analysis. The results also demonstrate that both PLV and MSC decoding models lead to superior results on our data compared to two recently proposed feature extraction methods solely based on the amplitude or phase of recording signals (p < 0.05). This study verifies the ability of PLV and MSC features in the continuous decoding of hand movements with linear regression. Thus, our findings suggest that extracting features based on brain connectivity can improve the accuracy of trajectory decoder BCIs.

Using Non-linear Dynamics of EEG Signals to Classify Primary Hand Movement Intent Under Opposite Hand Movement

Decoding human hand movement from electroencephalograms (EEG) signals is essential for developing an active human augmentation system. Although existing studies have contributed much to decoding single-hand movement direction from EEG signals, decoding primary hand movement direction under the opposite hand movement condition remains open. In this paper, we investigated the neural signatures of the primary hand movement direction from EEG signals under the opposite hand movement and developed a novel decoding method based on non-linear dynamics parameters of movement-related cortical potentials (MRCPs). Experimental results showed significant differences in MRCPs between hand movement directions under an opposite hand movement. Furthermore, the proposed method performed well with an average binary decoding accuracy of 89.48 ± 5.92% under the condition of the opposite hand movement. This study may lay a foundation for the future development of EEG-based human augmentation systems for upper limbs impaired patients and healthy people and open a new avenue to decode other hand movement parameters (e.g., velocity and position) from EEG signals.

Continuous 2D trajectory decoding from attempted movement: across-session performance in able-bodied and feasibility in a spinal cord injured participant

OBJECTIVE

In people with a cervical spinal cord injury (SCI) or degenerative diseases leading to limited motor function, restoration of upper limb movement has been a goal of the brain-computer interface (BCI) field for decades. Recently, research from our group investigated non-invasive and real-time decoding of continuous movement in able-bodied participants from low-frequency brain signals during a target-tracking task. To advance our setup towards motor-impaired end users, we consequently chose a new paradigm based on attempted movement.

APPROACH

Here, we present the results of two studies. During the first study, data of ten able-bodied participants completing a target-tracking/shape-tracing task on-screen were investigated in terms of improvements in decoding performance due to user training. In a second study, a spinal cord injured participant underwent the same tasks. To investigate the merit of employing attempted movement in end users with SCI, data of the spinal cord injured participant were recorded twice; once within an observation only condition, and once while simultaneously attempting movement.

MAIN RESULTS

We observed mean correlation well above chance level for continuous motor decoding based on attempted movement in able-bodied participants. No global improvement over three sessions, both in sensor and source space, could be observed across all participants and movement parameters. In the participant with SCI, decoding performance well above chance was found.

SIGNIFICANCE

No presence of a learning effect in continuous attempted movement decoding in able-bodied participants could be observed. In contrast, non-significantly varying decoding patterns may promote the use of source space decoding in terms of generalized decoders utilizing transfer learning. Furthermore, above-chance correlations for attempted movement decoding ranging between those of observation only and executed movement were seen in one spinal cord injured participant, suggesting attempted movement decoding as a possible link between feasibility studies in able-bodied and actual applications in motor impaired end users.

Decoding ECoG signal into 3D hand translation using deep learning

Objective.Motor brain-computer interfaces (BCIs) are a promising technology that may enable motor-impaired people to interact with their environment. BCIs would potentially compensate for arm and hand function loss, which is the top priority for individuals with tetraplegia. Designing real-time and accurate BCI is crucial to make such devices useful, safe, and easy to use by patients in a real-life environment. Electrocorticography (ECoG)-based BCIs emerge as a good compromise between invasiveness of the recording device and good spatial and temporal resolution of the recorded signal. However, most ECoG signal decoders used to predict continuous hand movements are linear models. These models have a limited representational capacity and may fail to capture the relationship between ECoG signal features and continuous hand movements. Deep learning (DL) models, which are state-of-the-art in many problems, could be a solution to better capture this relationship.Approach.In this study, we tested several DL-based architectures to predict imagined 3D continuous hand translation using time-frequency features extracted from ECoG signals. The dataset used in the analysis is a part of a long-term clinical trial (ClinicalTrials.gov identifier: NCT02550522) and was acquired during a closed-loop experiment with a tetraplegic subject. The proposed architectures include multilayer perceptron, convolutional neural networks (CNNs), and long short-term memory networks (LSTM). The accuracy of the DL-based and multilinear models was compared offline using cosine similarity.Main results.Our results show that CNN-based architectures outperform the current state-of-the-art multilinear model. The best architecture exploited the spatial correlation between neighboring electrodes with CNN and benefited from the sequential character of the desired hand trajectory by using LSTMs. Overall, DL increased the average cosine similarity, compared to the multilinear model, by up to 60%, from 0.189 to 0.302 and from 0.157 to 0.249 for the left and right hand, respectively.Significance.This study shows that DL-based models could increase the accuracy of BCI systems in the case of 3D hand translation prediction in a tetraplegic subject.

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.

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.

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.

Neurofeedback with low-cost, wearable electroencephalography (EEG) reduces symptoms in chronic Post-Traumatic Stress Disorder

BACKGROUND

The study examines the effectiveness of both neurofeedback and motor-imagery brain-computer interface (BCI) training, which promotes self-regulation of brain activity, using low-cost electroencephalography (EEG)-based wearable neurotechnology outside a clinical setting, as a potential treatment for post-traumatic stress disorder (PTSD) in Rwanda.

METHODS

Participants received training/treatment sessions along with a pre- and post- intervention clinical assessment, (N = 29; control n = 9, neurofeedback (NF, 7 sessions) n = 10, and motor-imagery (MI, 6 sessions) n = 10). Feedback was presented visually via a videogame. Participants were asked to regulate (NF) or intentionally modulate (MI) brain activity to affect/control the game.

RESULTS

The NF group demonstrated an increase in resting-state alpha 8-12 Hz bandpower following individual training sessions, termed alpha 'rebound' (Pz channel, p = 0.025, all channels, p = 0.024), consistent with previous research findings. This alpha 'rebound', unobserved in the MI group, produced a clinically relevant reduction in symptom severity in NF group, as revealed in three of seven clinical outcome measures: PCL-5 (p = 0.005), PTSD screen (p = 0.005), and HTQ (p = 0.005).

LIMITATIONS

Data collection took place in environments that posed difficulties in controlling environmental factors. Nevertheless, this limitation improves ecological validity, as neurotechnology treatments must be deployable outside controlled environments, to be a feasible technological treatment.

CONCLUSIONS

The study produced the first evidence to support a low-cost, neurotechnological solution for neurofeedback as an effective treatment of PTSD for victims of acute trauma in conflict zones in a developing country.

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.

Reconstruction of hand, elbow and shoulder actual and imagined trajectories in 3D space using EEG current source dipoles

OBJECTIVE

Growing evidence suggests that EEG electrode (sensor) potential time series (PTS) of slow cortical potentials (SCPs) hold motor neural correlates that can be used for motion trajectory prediction (MTP), commonly by multiple linear regression (mLR). It is not yet known whether arm-joint trajectories can be reliably decoded from current sources, computed from sensor data, from which brain areas they can be decoded and using which neural features.

APPROACH

In this study, the PTS of 44 sensors were fed into sLORETA source localization software to compute current source activity in 30 regions of interest (ROIs) found in a recent meta-analysis to be engaged in action execution, motor imagery and motor preparation. The current sources PTS and band-power time series (BTS) in several frequency bands and time lags were used to predict actual and imagined trajectories in 3D space of the three velocity components of the hand, elbow and shoulder of nine subjects using an mLR model.

MAIN RESULTS

For all arm joints and movement types, current source SCPs PTS contributed most to trajectory reconstruction with time lags 150ms, 116ms and 84ms providing the highest contribution, and current source BTS in any of the tested frequency bands was not informative. Person's correlation coefficient (r) averaged across movement types, arm joints and velocity components using source data was slightly lower than using sensor data (r=0.25 and r=0.28, respectively). For each ROI, the three current source dipoles had different contribution to the reconstruction of each of the three velocity components.

SIGNIFICANCE

Overall, our results demonstrate the feasibility of predicting of actual and imagined 3D trajectories of all arm joints from current sources, computed from scalp EEG. These findings may be used by developers of a future BCI as a validated set of contributing ROIs.

Distance- and speed-informed kinematics decoding improves M/EEG based upper-limb movement decoder accuracy

OBJECTIVE

One of the main goals in brain-computer interface (BCI) research is the replacement or restoration of lost function in individuals with paralysis. One line of research investigates the inference of movement kinematics from brain activity during different volitional states. A growing number of electroencephalography (EEG) and magnetoencephalography (MEG) studies suggest that information about directional (e.g. velocity) and nondirectional (e.g. speed) movement kinematics is accessible noninvasively. We sought to assess if the neural information associated with both types of kinematics can be combined to improve the decoding accuracy.

APPROACH

In an offline analysis, we reanalyzed the data of two previous experiments containing the recordings of 34 healthy participants (15 EEG, 19 MEG). We decoded 2D movement trajectories from low-frequency M/EEG signals in executed and observed tracking movements, and compared the accuracy of an unscented Kalman filter (UKF) that explicitly modeled the nonlinear relation between directional and nondirectional kinematics to the accuracies of linear Kalman (KF) and Wiener filters which did not combine both types of kinematics.

MAIN RESULTS

At the group level, posterior-parietal and parieto-occipital (executed and observed movements) and sensorimotor areas (executed movements) encoded kinematic information. Correlations between the recorded position and velocity trajectories and the UKF decoded ones were on average 0.49 during executed and 0.36 during observed movements. Compared to the other filters, the UKF could achieve the best trade-off between maximizing the signal to noise ratio and minimizing the amplitude mismatch between the recorded and decoded trajectories.

SIGNIFICANCE

We present direct evidence that directional and nondirectional kinematic information is simultaneously detectable in low-frequency M/EEG signals. Moreover, combining directional and nondirectional kinematic information significantly improves the decoding accuracy upon a linear KF.

Evaluation of Hyperparameter Optimization in Machine and Deep Learning Methods for Decoding Imagined Speech EEG

Classification of electroencephalography (EEG) signals corresponding to imagined speech production is important for the development of a direct-speech brain-computer interface (DS-BCI). Deep learning (DL) has been utilized with great success across several domains. However, it remains an open question whether DL methods provide significant advances over traditional machine learning (ML) approaches for classification of imagined speech. Furthermore, hyperparameter (HP) optimization has been neglected in DL-EEG studies, resulting in the significance of its effects remaining uncertain. In this study, we aim to improve classification of imagined speech EEG by employing DL methods while also statistically evaluating the impact of HP optimization on classifier performance. We trained three distinct convolutional neural networks (CNN) on imagined speech EEG using a nested cross-validation approach to HP optimization. Each of the CNNs evaluated was designed specifically for EEG decoding. An imagined speech EEG dataset consisting of both words and vowels facilitated training on both sets independently. CNN results were compared with three benchmark ML methods: Support Vector Machine, Random Forest and regularized Linear Discriminant Analysis. Intra- and inter-subject methods of HP optimization were tested and the effects of HPs statistically analyzed. Accuracies obtained by the CNNs were significantly greater than the benchmark methods when trained on both datasets (words: 24.97%, p < 1 × 10^-7, chance: 16.67%; vowels: 30.00%, p < 1 × 10^-7, chance: 20%). The effects of varying HP values, and interactions between HPs and the CNNs were both statistically significant. The results of HP optimization demonstrate how critical it is for training CNNs to decode imagined speech.

Non-linear online low-frequency EEG decoding of arm movements during a pursuit tracking task

Decoding upper-limb movements in invasive recordings has become a reality, but neural tuning in non-invasive low-frequency recordings is still under discussion. Recent studies managed to decode movement positions and velocities using linear decoders, even developing an online system. The decoded signals, however, exhibited smaller amplitudes than actual movements, affecting feedback and user experience. Recently, we showed that a non-linear offline decoder can combine directional (e.g., velocity) and non-directional (e.g., speed) information. In this study, it is assessed if the non-linear decoder can be used online to provide real-time feedback. Five healthy subjects were asked to track a moving target by controlling a robotic arm. Initially, the robot was controlled by their right hand; then, the control was gradually switched until it was entirely controlled by the electroencephalogram (EEG). Correlations between actual and decoded movements were generally above chance level. Results suggest that information about speed was also encoded in the EEG, demonstrating that the proposed non-linear decoder is suitable for decoding real-time arm movements.

A Systematic Review Establishing the Current State-of-the-Art, the Limitations, and the DESIRED Checklist in Studies of Direct Neural Interfacing With Robotic Gait Devices in Stroke Rehabilitation

Background: Stroke is a disease with a high associated disability burden. Robotic-assisted gait training offers an opportunity for the practice intensity levels associated with good functional walking outcomes in this population. Neural interfacing technology, electroencephalography (EEG), or electromyography (EMG) can offer new strategies for robotic gait re-education after a stroke by promoting more active engagement in movement intent and/or neurophysiological feedback. Objectives: This study identifies the current state-of-the-art and the limitations in direct neural interfacing with robotic gait devices in stroke rehabilitation. Methods: A pre-registered systematic review was conducted using standardized search operators that included the presence of stroke and robotic gait training and neural biosignals (EMG and/or EEG) and was not limited by study type. Results: From a total of 8,899 papers identified, 13 articles were considered for the final selection. Only five of the 13 studies received a strong or moderate quality rating as a clinical study. Three studies recorded EEG activity during robotic gait, two of which used EEG for BCI purposes. While demonstrating utility for decoding kinematic and EMG-related gait data, no EEG study has been identified to close the loop between robot and human. Twelve of the studies recorded EMG activity during or after robotic walking, primarily as an outcome measure. One study used multisource information fusion from EMG, joint angle, and force to modify robotic commands in real time, with higher error rates observed during active movement. A novel study identified used EMG data during robotic gait to derive the optimal, individualized robot-driven step trajectory. Conclusions: Wide heterogeneity in the reporting and the purpose of neurobiosignal use during robotic gait training after a stroke exists. Neural interfacing with robotic gait after a stroke demonstrates promise as a future field of study. However, as a nascent area, direct neural interfacing with robotic gait after a stroke would benefit from a more standardized protocol for biosignal collection and processing and for robotic deployment. Appropriate reporting for clinical studies of this nature is also required with respect to the study type and the participants' characteristics.

Distinct cortical networks for hand movement initiation and directional processing: An EEG study

Movement preparation and initiation have been shown to involve large scale brain networks. Recent findings suggest that movement preparation and initiation are represented in functionally distinct cortical networks. In electroencephalographic (EEG) recordings, movement initiation is reflected as a strong negative potential at medial central channels that is phase-locked to the movement onset - the movement-related cortical potential (MRCP). Movement preparation describes the process of transforming high level movement goals to low level commands. An integral part of this transformation process is directional processing (i.e., where to move). The processing of movement direction during visuomotor and oculomotor tasks is associated with medial parieto-occipital cortex (PO) activity, phase-locked to the presentation of potential movement goals. We surmised that the network generating the MRCP (movement initiation) would encode less information about movement direction than the parieto-occipital network processing movement direction. Here, we studied delta band EEG activity during center-out reaching movements (2D; 4 directions) in visuomotor and oculomotor tasks. In 15 healthy participants, we found a consistent representation of movement direction in PO 300–400 ​ms after the direction cue irrespective of the task. Despite generating the MRCP, sensorimotor areas (SM) encoded less information about the movement direction than PO. Moreover, the encoded directional information in SM was less consistent across participants and specific to the visuomotor task. In a classification approach, we could infer the four movement directions from the delta band EEG activity with moderate accuracies up to 55.9%. The accuracies for cue-aligned data were significantly higher than for movement onset-aligned data in either task, which also suggests a stronger representation of movement direction during movement preparation. Therefore, we present direct evidence that EEG delta band amplitude modulations carry information about both arm movement initiation and movement direction, and that they are represented in two distinct cortical networks.

•

Delta band EEG carries information about arm movement initiation and direction.

•

Movement initiation and direction are represented in two distinct cortical networks.

•

Information about movement direction is primarily encoded in parieto-occipital areas.

•

The activity in parieto-occipital areas is phase-locked to the direction cue.

Trajectory Decoding of Arm Reaching Movement Imageries for Brain-Controlled Robot Arm System

Development of noninvasive brain-machine interface (BMI) systems based on electroencephalography (EEG), driven by spontaneous movement intentions, is a useful tool for controlling external devices or supporting a neuro- rehabilitation. In this study, we present the possibility of brain-controlled robot arm system using arm trajectory decoding. To do that, we first constructed the experimental system that can acquire the EEG data for not only movement execution (ME) task but also movement imagery (MI) tasks. Five subjects participated in our experiments and performed four directional reaching tasks (Left, right, forward, and backward) in the 3D plane. For robust arm trajectory decoding, we propose a subject-dependent deep neural network (DNN) architecture. The decoding model applies the principle of bi-directional long short-term memory (LSTM) network. As a result, we confirmed the decoding performance (r-value: >0.8) for all X-, Y-, and Z-axis across all subjects in the MI as well as ME tasks. These results show the feasibility of the EEG-based intuitive robot arm control system for high-level tasks (e.g., drink water or moving some objects). Also, we confirm that the proposed method has no much decoding performance variations between ME and MI tasks for the offline analysis. Hence, we will demonstrate that the decoding model is capable of robust trajectory decoding even in a real-time environment.

Induced Gamma-Band Activity during Actual and Imaginary Movements: EEG Analysis

The purpose of this paper is to record and analyze induced gamma-band activity (GBA) (30-60 Hz) in cerebral motor areas during imaginary movement and to compare it quantitatively with activity recorded in the same areas during actual movement using a simplified electroencephalogram (EEG). Brain activity (basal activity, imaginary motor task and actual motor task) is obtained from 12 healthy volunteer subjects using an EEG (Cz channel). GBA is analyzed using the mean power spectral density (PSD) value. Event-related synchronization (ERS) is calculated from the PSD values of the basal GBA (GBAb), the GBA of the imaginary movement (GBAim) and the GBA of the actual movement (GBAac). The mean GBAim and GBAac values for the right and left hands are significantly higher than the GBAb value (p = 0.007). No significant difference is detected between mean GBA values during the imaginary and actual movement (p = 0.242). The mean ERS values for the imaginary movement (ERSimM (%) = 23.52) and for the actual movement (ERSacM = 27.47) do not present any significant difference (p = 0.117). We demonstrated that ERS could provide a useful way of indirectly checking the function of neuronal motor circuits activated by voluntary movement, both imaginary and actual. These results, as a proof of concept, could be applied to physiology studies, brain-computer interfaces, and diagnosis of cognitive or motor pathologies.

Using machine learning to reveal the population vector from EEG signals

OBJECTIVE

Since the discovery of the population vector that directly relates neural spiking activity with arm movement direction, it has become feasible to control robotic arms and neuroprostheses using invasively recorded brain signals. For non-invasive approaches, a direct relation between human brain signals and arm movement direction is yet to be established.

APPROACH

Here, we investigated electroencephalographic (EEG) signals in temporal and spectral domains in a continuous, circular arm movement task. Using machine learning methods that respect the linear mixture of brain activity within EEG signals, we show that directional information is represented in the temporal domain in amplitude modulations of the same frequency as the arm movement, and in the spectral domain in power modulations of the 20-24 Hz frequency band.

MAIN RESULTS

In the temporal domain, the directional information was mainly expressed in primary sensorimotor cortex (SM1) and posterior parietal cortex (PPC) contralateral to the moving arm, while in the spectral domain SM1 and PPC of both hemispheres predicted arm movement direction. The different cortical representations suggest distinct neural representations in both domains.

SIGNIFICANCE

This direct relation between neural activity and arm movement direction in both domains demonstrates the potential of machine learning to reveal neuroscientific insights about the dynamics of human arm movements.

Semi-Autonomous Robotic Arm Reaching With Hybrid Gaze-Brain Machine Interface

Recent developments in the non-muscular human-robot interface (HRI) and shared control strategies have shown potential for controlling the assistive robotic arm by people with no residual movement or muscular activity in upper limbs. However, most non-muscular HRIs only produce discrete-valued commands, resulting in non-intuitive and less effective control of the dexterous assistive robotic arm. Furthermore, the user commands and the robot autonomy commands usually switch in the shared control strategies of such applications. This characteristic has been found to yield a reduced sense of agency as well as frustration for the user according to previous user studies. In this study, we firstly propose an intuitive and easy-to-learn-and-use hybrid HRI by combing the Brain-machine interface (BMI) and the gaze-tracking interface. For the proposed hybrid gaze-BMI, the continuous modulation of the movement speed via the motor intention occurs seamlessly and simultaneously to the unconstrained movement direction control with the gaze signals. We then propose a shared control paradigm that always combines user input and the autonomy with the dynamic combination regulation. The proposed hybrid gaze-BMI and shared control paradigm were validated for a robotic arm reaching task performed with healthy subjects. All the users were able to employ the hybrid gaze-BMI for moving the end-effector sequentially to reach the target across the horizontal plane while also avoiding collisions with obstacles. The shared control paradigm maintained as much volitional control as possible, while providing the assistance for the most difficult parts of the task. The presented semi-autonomous robotic system yielded continuous, smooth, and collision-free motion trajectories for the end effector approaching the target. Compared to a system without assistances from robot autonomy, it significantly reduces the rate of failure as well as the time and effort spent by the user to complete the tasks.

Reconstructing Degree of Forearm Rotation from Imagined movements for BCI-based Robot Hand Control

Brain-computer interface (BCI) is an important tool for rehabilitation and control of an external device (e.g., robot arm or home appliances). Fully reconstruction of upper limb movement from brain signals is one of the critical issues for intuitive BCI. However, decoding of forearm rotation from imagined movements using electroencephalography (EEG) is difficult to decode degree of rotation accurately. In this paper, we reconstructed imagined forearm rotation from low- frequency (0.3-3 Hz) of EEG signals. We selected 20 EEG channel on motor cortex for analysis. Ten healthy subjects participated in our experiment. The subjects performed actual and imagined forearm rotation to reach different targets. We trained a reconstruction decoder which used the EEG signals measured from actual movements and the kinematic information only. Additionally, we applied a long short-term memory (LSTM) network to enhance decoding performances. As a result, we achieved the high correlation performance (Average: 0.67) to decode imagined forearm rotation angle. This result has demonstrated that the reconstruction decoder which is trained by the EEG data from actual movement has effective to decode robustly for the imagined forearm rotation angle.

The Application of EEG Mu Rhythm Measures to Neurophysiological Research in Stuttering

Deficits in basal ganglia-based inhibitory and timing circuits along with sensorimotor internal modeling mechanisms are thought to underlie stuttering. However, much remains to be learned regarding the precise manner how these deficits contribute to disrupting both speech and cognitive functions in those who stutter. Herein, we examine the suitability of electroencephalographic (EEG) mu rhythms for addressing these deficits. We review some previous findings of mu rhythm activity differentiating stuttering from non-stuttering individuals and present some new preliminary findings capturing stuttering-related deficits in working memory. Mu rhythms are characterized by spectral peaks in alpha (8-13 Hz) and beta (14-25 Hz) frequency bands (mu-alpha and mu-beta). They emanate from premotor/motor regions and are influenced by basal ganglia and sensorimotor function. More specifically, alpha peaks (mu-alpha) are sensitive to basal ganglia-based inhibitory signals and sensory-to-motor feedback. Beta peaks (mu-beta) are sensitive to changes in timing and capture motor-to-sensory (i.e., forward model) projections. Observing simultaneous changes in mu-alpha and mu-beta across the time-course of specific events provides a rich window for observing neurophysiological deficits associated with stuttering in both speech and cognitive tasks and can provide a better understanding of the functional relationship between these stuttering symptoms. We review how independent component analysis (ICA) can extract mu rhythms from raw EEG signals in speech production tasks, such that changes in alpha and beta power are mapped to myogenic activity from articulators. We review findings from speech production and auditory discrimination tasks demonstrating that mu-alpha and mu-beta are highly sensitive to capturing sensorimotor and basal ganglia deficits associated with stuttering with high temporal precision. Novel findings from a non-word repetition (working memory) task are also included. They show reduced mu-alpha suppression in a stuttering group compared to a typically fluent group. Finally, we review current limitations and directions for future research.

Decoding Imagined 3D Arm Movement Trajectories From EEG to Control Two Virtual Arms-A Pilot Study

Background: Realization of online control of an artificial or virtual arm using information decoded from EEG normally occurs by classifying different activation states or voluntary modulation of the sensorimotor activity linked to different overt actions of the subject. However, using a more natural control scheme, such as decoding the trajectory of imagined 3D arm movements to move a prosthetic, robotic, or virtual arm has been reported in a limited amount of studies, all using offline feed-forward control schemes.

Objective: In this study, we report the first attempt to realize online control of two virtual arms generating movements toward three targets/arm in 3D space. The 3D trajectory of imagined arm movements was decoded from power spectral density of mu, low beta, high beta, and low gamma EEG oscillations using multiple linear regression. The analysis was performed on a dataset recorded from three subjects in seven sessions wherein each session comprised three experimental blocks: an offline calibration block and two online feedback blocks. Target classification accuracy using predicted trajectories of the virtual arms was computed and compared with results of a filter-bank common spatial patterns (FBCSP) based multi-class classification method involving mutual information (MI) selection and linear discriminant analysis (LDA) modules.

Main Results: Target classification accuracy from predicted trajectory of imagined 3D arm movements in the offline runs for two subjects (mean 45%, std 5%) was significantly higher (p < 0.05) than chance level (33.3%). Nevertheless, the accuracy during real-time control of the virtual arms using the trajectory decoded directly from EEG was in the range of chance level (33.3%). However, the results of two subjects show that false-positive feedback may increase the accuracy in closed-loop. The FBCSP based multi-class classification method distinguished imagined movements of left and right arm with reasonable accuracy for two of the three subjects (mean 70%, std 5% compared to 50% chance level). However, classification of the imagined arm movement toward three targets was not successful with the FBCSP classifier as the achieved accuracy (mean 33%, std 5%) was similar to the chance level (33.3%). Sub-optimal components of the multi-session experimental paradigm were identified, and an improved paradigm proposed.

Unimanual and Bimanual Reach-and-Grasp Actions Can Be Decoded From Human EEG

While most tasks of daily life can be handled through a small number of different grasps, many tasks require the action of both hands. In these bimanual tasks, the second hand has either a supporting role (e.g. for fixating a jar) or a more active role (e.g. grasping a pot on both handles). In this study we attempt to discriminate the neural correlates of unimanual (performed with left and right hand) from bimanual reach-and-grasp actions using the low-frequency time-domain electroencephalogram (EEG). In a self-initiated movement task, 15 healthy participants were asked to perform unimanual (palmar and lateral grasps with left and right hand) and bimanual (double lateral, mixed palmar/lateral) reach-and-grasps on objects of daily life. Using EEG time-domain features in the frequency range of 0.3-3 Hz, we achieved multiclass-classification accuracies of 38.6 ± 6.6% (7 classes, 17.1% chance level) for a combination of 6 movements and 1 rest condition. The grand average confusion matrix shows highest true positive rates (TPR) for the rest (63%) condition while TPR for the movement classes varied between 33 to 41%. The underlying movement-related cortical potentials (MRCPs) show significant differences between unimanual (e.g left hand vs. right hand grasps) as well unimanual vs. bimanual conditions which both can be attributed to lateralization effects. We believe that these findings can be exploited and further used for attempts in providing persons with spinal cord injury a form of natural control for bimanual neuroprostheses.

Detection of reaching intention using EEG signals and nonlinear dynamic system identification

BACKGROUND AND OBJECTIVES

Low frequency electroencephalography (EEG) signals are associated with preparation of movement and thus provide valuable information for brain-machine interface applications. The purpose of this study was to detect movement intention from EEG signals before execution of self-paced arm reaching movements.

METHODS

Ten healthy individuals were recruited. Movement onset was determined from surface electromyography recordings time-locked with EEG signals. Unlike previous studies, which employed feature extraction and classification for decoding, a nonlinear dynamic multiple-input/single output (MISO) model was developed. The MISO model consisted of a cascade of Volterra structures and a threshold block, generating the binary output corresponding to intention/no-intention. The modeling process included input selection from a pool of different EEG channels. The predictive performance of the model was evaluated using the receiver operating characteristics curve, from which the optimum threshold was also selected. The Mann-Whitney statistics was employed to select the significant EEG channels for the output by examining the statistical significance of improvement in the predictive capability of the model when the respective channels were included.

RESULTS

With the proposed approach, movement intention was detected approximately 500 ms before the movement onset and on average, with an accuracy of 96.37 ± 0.94%, a sensitivity of 77.93 ± 4.40% and a specificity of 98.52 ± 1.19%.

CONCLUSIONS

The model output can be converted to motion commands for neuroprosthetic devices and exoskeletons in future applications.

Decoding electroencephalographic signals for direction in brain-computer interface using echo state network and Gaussian readouts

BACKGROUND

Noninvasive brain-computer interfaces (BCI) for movement control via an electroencephalogram (EEG) have been extensively investigated. However, most previous studies decoded user intention for movement directions based on sensorimotor rhythms during motor imagery. BCI systems based on mapping imagery movement of body parts (e.g., left or right hands) to movement directions (left or right directional movement of a machine or cursor) are less intuitive and less convenient due to the complex training procedures. Thus, direct decoding methods for detecting user intention about movement directions are urgently needed.

METHODS

Here, we describe a novel direct decoding method for user intention about the movement directions using the echo state network and Gaussian readouts. Importantly parameters in the network were optimized using the genetic algorithm method to achieve better decoding performance. We tested the decoding performance of this method with four healthy subjects and an inexpensive wireless EEG system containing 14 channels and then compared the performance outcome with that of a conventional machine learning method.

RESULTS

We showed that this decoding method successfully classified eight directions of intended movement (approximately 95% of an accuracy).

CONCLUSIONS

We suggest that the echo state network and Gaussian readouts can be a useful decoding method to directly read user intention of movement directions even using an inexpensive and portable EEG system.

Spectral and topological analyses of the cortical representation of the head position: Does hypnotizability matter?

INTRODUCTION

The aim of this exploratory study was to assess the EEG correlates of head positions (which have never been studied in humans) in participants with different psychophysiological characteristics, as encoded by their hypnotizability scores. This choice is motivated by earlier studies suggesting different processing of vestibular/neck proprioceptive information in subjects with high (highs) and low (lows) hypnotizability scores maintaining their head rotated toward one side (RH).

METHODS

We analyzed EEG signals recorded in 20 highs and 19 lows in basal conditions (head forward) and during RH using spectral analysis, which captures changes localized to specific recording sites, and topological data analysis (TDA), which instead describes large-scale differences in processing and representing sensorimotor information.

RESULTS

Spectral analysis revealed significant differences related to head position for alpha 1, beta 2, beta 3, and gamma bands, but not to hypnotizability. TDA instead revealed global hypnotizability-related differences in the strengths of the correlations among recording sites during RH. Significant changes were observed in lows on the left parieto-occipital side and in highs in right frontoparietal region. Significant differences between the two groups were found in the occipital region, where changes were larger in lows than in highs.

CONCLUSIONS

This study reports finding of the EEG correlates of changes in the head posture for the first time, indicating that hypnotizability is related to the head posture representation/processing on large-scale networks and that spectral and topological data analyses provide complementary results.

The Advantage of Low-Delta Electroencephalogram Phase Feature for Reconstructing the Center-Out Reaching Hand Movements

It is an emerging frontier of research on the use of neural signals for prosthesis control, in order to restore lost function to amputees and patients after spinal cord injury. Compared to the invasive neural signal based brain-machine interface (BMI), a non-invasive alternative, i.e., the electroencephalogram (EEG)-based BMI would be more widely accepted by the patients above. Ideally, a real-time continuous neuroprosthestic control is required for practical applications. However, conventional EEG-based BMIs mainly deal with the discrete brain activity classification. Until recently, the literature has reported several attempts for achieving the real-time continuous control by reconstructing the continuous movement parameters (e.g., speed, position, etc.) from the EEG recordings, and the low-frequency band EEG is consistently reported to encode the continuous motor control information. Previous studies with executed movement tasks have extensively relied on the amplitude representation of such slow oscillations of EEG signals for building models to decode kinematic parameters. Inspired by the recent successes of instantaneous phase of low-frequency invasive brain signals in the motor control and sensory processing domains, this study examines the extension of such a slow-oscillation phase representation to the reconstructing two-dimensional hand movements, with the non-invasive EEG signals for the first time. The data for analysis are collected on five healthy subjects performing 2D hand center-out reaching along four directions in two sessions. On representative channels over the cortices encoding the execution information of reaching movements, we show that the low-delta EEG phase representation is characterized by higher signal-to-noise ratio and stronger modulation by the movement tasks, compared to the low-delta EEG amplitude representation. Furthermore, we have tested the low-delta EEG phase representation with two commonly used linear decoding models. The results demonstrate that the low-delta EEG phase based decoders lead to superior performance for 2D executed movement reconstruction to its amplitude based counterparts, as well as the other-frequency band amplitude and power based features. Thus, our study contributes to improve the movement reconstruction from EEG by introducing a new feature set based on the low-delta EEG phase patterns, and demonstrates its potential for continuous fine motion control of neuroprostheses.

Attempted Arm and Hand Movements can be Decoded from Low-Frequency EEG from Persons with Spinal Cord Injury

We show that persons with spinal cord injury (SCI) retain decodable neural correlates of attempted arm and hand movements. We investigated hand open, palmar grasp, lateral grasp, pronation, and supination in 10 persons with cervical SCI. Discriminative movement information was provided by the time-domain of low-frequency electroencephalography (EEG) signals. Based on these signals, we obtained a maximum average classification accuracy of 45% (chance level was 20%) with respect to the five investigated classes. Pattern analysis indicates central motor areas as the origin of the discriminative signals. Furthermore, we introduce a proof-of-concept to classify movement attempts online in a closed loop, and tested it on a person with cervical SCI. We achieved here a modest classification performance of 68.4% with respect to palmar grasp vs hand open (chance level 50%).

Decoding Steady-State Visual Evoked Potentials From Electrocorticography

We report on a unique electrocorticography (ECoG) experiment in which Steady-State Visual Evoked Potentials (SSVEPs) to frequency- and phase-tagged stimuli were recorded from a large subdural grid covering the entire right occipital cortex of a human subject. The paradigm is popular in EEG-based Brain Computer Interfacing where selectable targets are encoded by different frequency- and/or phase-tagged stimuli. We compare the performance of two state-of-the-art SSVEP decoders on both ECoG- and scalp-recorded EEG signals, and show that ECoG-based decoding is more accurate for very short stimulation lengths (i.e., less than 1 s). Furthermore, whereas the accuracy of scalp-EEG decoding benefits from a multi-electrode approach, to address interfering EEG responses and noise, ECoG decoding enjoys only a marginal improvement as even a single electrode, placed over the posterior part of the primary visual cortex, seems to suffice. This study shows, for the first time, that EEG-based SSVEP decoders can in principle be applied to ECoG, and can be expected to yield faster decoding speeds using less electrodes.