Decoding Three-Dimensional Trajectory of Executed and Imagined Arm Movements From Electroencephalogram Signals

Handwritten character classification from EEG through continuous kinematic decoding

The classification of handwritten letters from invasive neural signals has lately been subject of research to restore communication abilities in people with limited movement capacities. This study explores the classification of ten letters (a,d,e,f,j,n,o,s,t,v) from non-invasive neural signals of 20 participants, offering new insights into the neural correlates of handwriting. Letters were classified with two methods: the direct classification from low-frequency and broadband electroencephalogram (EEG) and a two-step approach comprising the continuous decoding of hand kinematics and the application of those in subsequent classification. The two-step approach poses a novel application of continuous movement decoding for the classification of letters from EEG. When using low-frequency EEG, results show moderate accuracies of 23.1% for ten letters and 39.0% for a subset of five letters with highest discriminability of the trajectories. The two-step approach yielded significantly higher performances of 26.2% for ten letters and 46.7% for the subset of five letters. Hand kinematics could be reconstructed with a correlation of 0.10 to 0.57 (average chance level: 0.04) between the decoded and original kinematic. The study shows the general feasibility of extracting handwritten letters from non-invasively recorded neural signals and indicates that the proposed two-step approach can improve performances. As an exploratory investigation of the neural mechanisms of handwriting in EEG, we found significant influence of the written letter on the low-frequency components of neural signals. Differences between letters occurred mostly in central and occipital channels. Further, our results suggest movement speed as the most informative kinematic for the decoding of short hand movements.

SpeechBrain-MOABB: An open-source Python library for benchmarking deep neural networks applied to EEG signals

Deep learning has revolutionized EEG decoding, showcasing its ability to outperform traditional machine learning models. However, unlike other fields, EEG decoding lacks comprehensive open-source libraries dedicated to neural networks. Existing tools (MOABB and braindecode) prevent the creation of robust and complete decoding pipelines, as they lack support for hyperparameter search across the entire pipeline, and are sensitive to fluctuations in results due to network random initialization. Furthermore, the absence of a standardized experimental protocol exacerbates the reproducibility crisis in the field. To address these limitations, we introduce SpeechBrain-MOABB, a novel open-source toolkit carefully designed to facilitate the development of a comprehensive EEG decoding pipeline based on deep learning. SpeechBrain-MOABB incorporates a complete experimental protocol that standardizes critical phases, such as hyperparameter search and model evaluation. It natively supports multi-step hyperparameter search for finding the optimal hyperparameters in a high-dimensional space defined by the entire pipeline, and multi-seed training and evaluation for obtaining performance estimates robust to the variability caused by random initialization. SpeechBrain-MOABB outperforms other libraries, including MOABB and braindecode, with accuracy improvements of 14.9% and 25.2% (on average), respectively. By enabling easy-to-use and easy-to-share decoding pipelines, our toolkit can be exploited by neuroscientists for decoding EEG with neural networks in a replicable and trustworthy way.

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.

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.

Decoding movement frequencies and limbs based on steady-state movement-related rhythms from noninvasive EEG

Objective.Decoding different types of movements noninvasively from electroencephalography (EEG) is an essential topic in neural engineering, especially in brain-computer interface. Although the widely used sensorimotor rhythm (SMR) is efficient in limb decoding, it lacks efficacy in decoding movement frequencies. Accumulating evidence supports the notion that the movement frequency is encoded in the steady-state movement-related rhythm (SSMRR). Our study has two primary objectives: firstly, to investigate the spatial-spectral representation of SSMRR in EEG during voluntary movements; secondly, to assess whether movement frequencies and limbs can be effectively decoded based on SSMRR.Approach.To comprehensively examine the representation of SSMRR, we investigated the frequency characteristics and spatial patterns associated with various rhythmic finger movements. Coherence analysis was performed between the sensor or source domain EEG and finger movements recorded by data gloves. A fusion model based on spectral SNR features and filter-bank common spatial pattern features was utilized to decode movement frequencies and limbs.Main results.At the group-level, sensor domain, and source domain coherence maps demonstrated that the accurate movement frequency (f0) and its first harmonic (f1) were encoded in the contralateral motor cortex. For the four-class classification, including two movement frequencies for both hands, the decoding accuracies for externally paced and internally paced movements were 73.14 ± 15.86% and 66.30 ± 17.26% (averaged across ten subjects, chance levels at 31.05% and 30.96%). Notably, the average results of five subjects with the highest decoding accuracies reached 87.21 ± 7.44% and 80.44 ± 7.99%.Significance.Our results verified the EEG representation of SSMRR and proved that the movement frequency and limb could be effectively decoded based on spatial-spectral features extracted from SSMRR. We suggest that SSMRR can serve as a complement to SMR to expand the range of decodable movement types and the approaches of limb decoding.

Neural Correlation of EEG and Eye Movement in Natural Grasping Intention Estimation

Decoding the user's natural grasp intent enhances the application of wearable robots, improving the daily lives of individuals with disabilities. Electroencephalogram (EEG) and eye movements are two natural representations when users generate grasp intent in their minds, with current studies decoding human intent by fusing EEG and eye movement signals. However, the neural correlation between these two signals remains unclear. Thus, this paper aims to explore the consistency between EEG and eye movement in natural grasping intention estimation. Specifically, six grasp intent pairs are decoded by combining feature vectors and utilizing the optimal classifier. Extensive experimental results indicate that the coupling between the EEG and eye movements intent patterns remains intact when the user generates a natural grasp intent, and concurrently, the EEG pattern is consistent with the eye movements pattern across the task pairs. Moreover, the findings reveal a solid connection between EEG and eye movements even when taking into account cortical EEG (originating from the visual cortex or motor cortex) and the presence of a suboptimal classifier. Overall, this work uncovers the coupling correlation between EEG and eye movements and provides a reference for intention estimation.

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.

Temporal-spatial convolutional residual network for decoding attempted movement related EEG signals of subjects with spinal cord injury

Brain Computer Interface (BCI) offers a promising approach to restoring hand functionality for people with cervical spinal cord injury (SCI). A reliable classification of brain activities based on appropriate flexibility in feature extraction could enhance BCI systems performance. In the present study, based on convolutional layers with temporal-spatial, Separable and Depthwise structures, we develop Temporal-Spatial Convolutional Residual Network)TSCR-Net(and Temporal-Spatial Convolutional Iterative Residual Network)TSCIR-Net(structures to classify electroencephalogram (EEG) signals. Using EEG signals in five different hand movement classes of SCI people, we compare the effectiveness of TSCIR-Net and TSCR-Net models with some competitive methods. We use the bayesian hyperparameter optimization algorithm to tune the hyperparameters of compact convolutional neural networks. In order to show the high generalizability of the proposed models, we compare the results of the models in different frequency ranges. Our proposed models decoded distinctive characteristics of different movement efforts and obtained higher classification accuracy than previous deep neural networks. Our findings indicate that TSCIR-Net and TSCR-Net models fulfills a better classification accuracy of 71.11%, and 64.55% for EEG_All and 57.74%, and 67.87% for EEG_Low frequency data sets than the compared methods in the literature.

Performance comparison of bio-inspired and learning-based clustering analysis with machine learning techniques for classification of EEG signals

A comprehensive analysis of an automated system for epileptic seizure detection is explained in this work. When a seizure occurs, it is quite difficult to differentiate the non-stationary patterns from the discharges occurring in a rhythmic manner. The proposed approach deals with it efficiently by clustering it initially for the sake of feature extraction by using six different techniques categorized under two different methods, e.g., bio-inspired clustering and learning-based clustering. Learning-based clustering includes K-means clusters and Fuzzy C-means (FCM) clusters, while bio-inspired clusters include Cuckoo search clusters, Dragonfly clusters, Firefly clusters, and Modified Firefly clusters. Clustered values were then classified with 10 suitable classifiers, and after the performance comparison analysis of the EEG time series, the results proved that this methodology flow achieved a good performance index and a high classification accuracy. A comparatively higher classification accuracy of 99.48% was achieved when Cuckoo search clusters were utilized with linear support vector machines (SVM) for epilepsy detection. A high classification accuracy of 98.96% was obtained when K-means clusters were classified with a naive Bayesian classifier (NBC) and Linear SVM, and similar results were obtained when FCM clusters were classified with Decision Trees yielding the same values. The comparatively lowest classification accuracy, at 75.5%, was obtained when Dragonfly clusters were classified with the K-nearest neighbor (KNN) classifier, and the second lowest classification accuracy of 75.75% was obtained when Firefly clusters were classified with NBC.

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.

Subject-independent EEG classification based on a hybrid neural network

A brain-computer interface (BCI) based on the electroencephalograph (EEG) signal is a novel technology that provides a direct pathway between human brain and outside world. For a traditional subject-dependent BCI system, a calibration procedure is required to collect sufficient data to build a subject-specific adaptation model, which can be a huge challenge for stroke patients. In contrast, subject-independent BCI which can shorten or even eliminate the pre-calibration is more time-saving and meets the requirements of new users for quick access to the BCI. In this paper, we design a novel fusion neural network EEG classification framework that uses a specially designed generative adversarial network (GAN), called a filter bank GAN (FBGAN), to acquire high-quality EEG data for augmentation and a proposed discriminative feature network for motor imagery (MI) task recognition. Specifically, multiple sub-bands of MI EEG are first filtered using a filter bank approach, then sparse common spatial pattern (CSP) features are extracted from multiple bands of filtered EEG data, which constrains the GAN to maintain more spatial features of the EEG signal, and finally we design a convolutional recurrent network classification method with discriminative features (CRNN-DF) to recognize MI tasks based on the idea of feature enhancement. The hybrid neural network proposed in this study achieves an average classification accuracy of 72.74 ± 10.44% (mean ± std) in four-class tasks of BCI IV-2a, which is 4.77% higher than the state-of-the-art subject-independent classification method. A promising approach is provided to facilitate the practical application of BCI.

Deep-Learning-Based Automatic Selection of Fewest Channels for Brain-Machine Interfaces

Due to the development of convenient brain-machine interfaces (BMIs), the automatic selection of a minimum channel (electrode) set has attracted increasing interest because the decrease in the number of channels increases the efficiency of BMIs. This study proposes a deep-learning-based technique to automatically search for the minimum number of channels applicable to general BMI paradigms using a compact convolutional neural network for electroencephalography (EEG)-based BMIs. For verification, three types of BMI paradigms are assessed: 1) the typical P300 auditory oddball; 2) the new top-down steady-state visually evoked potential; and 3) the endogenous motor imagery. We observe that the optimized minimal EEG-channel sets are automatically selected in all three cases. Their decoding accuracies using the minimal channels are statistically equivalent to (or even higher than) those based on all channels. The brain areas of the selected channel set are neurophysiologically interpretable for all of these cognitive task paradigms. This study shows that the minimal EEG channel set can be automatically selected, irrespective of the types of BMI paradigms or EEG input features using a deep-learning approach, which also contributes to their portability.

High-Frequency Vibrating Stimuli Using the Low-Cost Coin-Type Motors for SSSEP-Based BCI

Steady-state somatosensory-evoked potential- (SSSEP-) based brain-computer interfaces (BCIs) have been applied for assisting people with physical disabilities since it does not require gaze fixation or long-time training. Despite the advancement of various noninvasive electroencephalogram- (EEG-) based BCI paradigms, researches on SSSEP with the various frequency range and related classification algorithms are relatively unsettled. In this study, we investigated the feasibility of classifying the SSSEP within high-frequency vibration stimuli induced by a versatile coin-type eccentric rotating mass (ERM) motor. Seven healthy subjects performed selective attention (SA) tasks with vibration stimuli attached to the left and right index fingers. Three EEG feature extraction methods, followed by a support vector machine (SVM) classifier, have been tested: common spatial pattern (CSP), filter-bank CSP (FBCSP), and mutual information-based best individual feature (MIBIF) selection after the FBCSP. Consequently, the FBCSP showed the highest performance at $71.5\pm 2.5$ % for classifying the left and right-hand SA tasks than the other two methods (i.e., CSP and FBCSP-MIBIF). Based on our findings and approach, the high-frequency vibration stimuli using low-cost coin motors with the FBCSP-based feature selection can be potentially applied to developing practical SSSEP-based BCI systems.

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.

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

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

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.

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.

Upper-Limb Electromyogram Classification of Reaching-to-Grasping Tasks Based on Convolutional Neural Networks for Control of a Prosthetic Hand

In recent years, myoelectric interfaces using surface electromyogram (EMG) signals have been developed for assisting people with physical disabilities. Especially, in the myoelectric interfaces for robotic hands or arms, decoding the user’s upper-limb movement intentions is cardinal to properly control the prosthesis. However, because previous experiments were implemented with only healthy subjects, the possibility of classifying reaching-to-grasping based on the EMG signals from the residual limb without the below-elbow muscles was not investigated yet. Therefore, we aimed to investigate the possibility of classifying reaching-to-grasping tasks using the EMG from the upper arm and upper body without considering wrist muscles for prosthetic users. In our study, seven healthy subjects, one trans-radial amputee, and one wrist amputee were participated and performed 10 repeatable 12 reaching-to-grasping tasks based on the Southampton Hand Assessment Procedure (SHAP) with 12 different weighted (light and heavy) objects. The acquired EMG was processed using the principal component analysis (PCA) and convolutional neural network (CNN) to decode the tasks. The PCA–CNN method showed that the average accuracies of the healthy subjects were 69.4 ± 11.4%, using only the EMG signals by the upper arm and upper body. The result with the PCA–CNN method showed 8% significantly higher accuracies than the result with the widely used time domain and auto-regressive-support vector machine (TDAR–SVM) method as 61.6 ± 13.7%. However, in the cases of the amputees, the PCA–CNN showed slightly lower performance. In addition, in the aspects of assistant daily living, because grip force is also important when grasping an object after reaching, the possibility of classifying the two light and heavy objects in each reaching-to-grasping task was also investigated. Consequently, the PCA–CNN method showed higher accuracy at 70.1 ± 9.8%. Based on our results, the PCA–CNN method can help to improve the performance of classifying reaching-to-grasping tasks without wrist EMG signals. Our findings and decoding method can be implemented to further develop a practical human–machine interface using EMG signals.

Motor Intention Decoding from the Upper Limb by Graph Convolutional Network Based on Functional Connectivity

Decoding brain intention from noninvasively measured neural signals has recently been a hot topic in brain-computer interface (BCI). The motor commands about the movements of fine parts can increase the degrees of freedom under control and be applied to external equipment without stimulus. In the decoding process, the classifier is one of the key factors, and the graph information of the EEG was ignored by most researchers. In this paper, a graph convolutional network (GCN) based on functional connectivity was proposed to decode the motor intention of four fine parts movements (shoulder, elbow, wrist, hand). First, event-related desynchronization was analyzed to reveal the differences between the four classes. Second, functional connectivity was constructed by using synchronization likelihood (SL), phase-locking value (PLV), H index (H), mutual information (MI), and weighted phase-lag index (WPLI) to acquire the electrode pairs with a difference. Subsequently, a GCN and convolutional neural networks (CNN) were performed based on functional topological structures and time points, respectively. The results demonstrated that the proposed method achieved a decoding accuracy of up to 92.81% in the four-class task. Besides, the combination of GCN and functional connectivity can promote the development of BCI.

A Hybrid-Domain Deep Learning-Based BCI For Discriminating Hand Motion Planning From EEG Sources

In this paper, a hybrid-domain deep learning (DL)-based neural system is proposed to decode hand movement preparation phases from electroencephalographic (EEG) recordings. The system exploits information extracted from the temporal-domain and time-frequency-domain, as part of a hybrid strategy, to discriminate the temporal windows (i.e. EEG epochs) preceding hand sub-movements (open/close) and the resting state. To this end, for each EEG epoch, the associated cortical source signals in the motor cortex and the corresponding time-frequency (TF) maps are estimated via beamforming and Continuous Wavelet Transform (CWT), respectively. Two Convolutional Neural Networks (CNNs) are designed: specifically, the first CNN is trained over a dataset of temporal (T) data (i.e. EEG sources), and is referred to as T-CNN; the second CNN is trained over a dataset of TF data (i.e. TF-maps of EEG sources), and is referred to as TF-CNN. Two sets of features denoted as T-features and TF-features, extracted from T-CNN and TF-CNN, respectively, are concatenated in a single features vector (denoted as TTF-features vector) which is used as input to a standard multi-layer perceptron for classification purposes. Experimental results show a significant performance improvement of our proposed hybrid-domain DL approach as compared to temporal-only and time-frequency-only-based benchmark approaches, achieving an average accuracy of [Formula: see text]%.

Review of brain encoding and decoding mechanisms for EEG-based brain-computer interface

A brain-computer interface (BCI) can connect humans and machines directly and has achieved successful applications in the past few decades. Many new BCI paradigms and algorithms have been developed in recent years. Therefore, it is necessary to review new progress in BCIs. This paper summarizes progress for EEG-based BCIs from the perspective of encoding paradigms and decoding algorithms, which are two key elements of BCI systems. Encoding paradigms are grouped by their underlying neural meachanisms, namely sensory- and motor-related, vision-related, cognition-related and hybrid paradigms. Decoding algorithms are reviewed in four categories, namely decomposition algorithms, Riemannian geometry, deep learning and transfer learning. This review will provide a comprehensive overview of both modern primary paradigms and algorithms, making it helpful for those who are developing BCI systems.

Nonlinear Modeling of Cortical Responses to Mechanical Wrist Perturbations Using the NARMAX Method

OBJECTIVE

Nonlinear modeling of cortical responses (EEG) to wrist perturbations allows for the quantification of cortical sensorimotor function in healthy and neurologically impaired individuals. A common model structure reflecting key characteristics shared across healthy individuals may provide a reference for future clinical studies investigating abnormal cortical responses associated with sensorimotor impairments. Thus, the goal of our study is to identify this common model structure and therefore to build a nonlinear dynamic model of cortical responses, using nonlinear autoregressive-moving-average model with exogenous inputs (NARMAX).

METHODS

EEG was recorded from ten participants when receiving continuous wrist perturbations. A common model structure detection method was developed for identifying a common NARMAX model structure across all participants, with individualized parameter values. The results were compared to conventional subject-specific models.

RESULTS

The proposed method achieved 93.91% variance accounted for (VAF) when implementing a one-step-ahead prediction and around 50% VAF for a k-step ahead prediction (k = 3), without a substantial drop of VAF as compare to subject-specific models. The estimated common structure suggests that the measured cortical response is a mixed outcome of the nonlinear transformation of external inputs and local neuronal interactions or inherent neuronal dynamics at the cortex.

CONCLUSION

The proposed method well determined the common characteristics across subjects in the cortical responses to wrist perturbations.

SIGNIFICANCE

It provides new insights into the human sensorimotor nervous system in response to somatosensory inputs and paves the way for future translational studies on assessments of sensorimotor impairments using our modeling approach.

Neural decoding of continuous upper limb movements: a meta-analysis

OBJECTIVE

EEG-based motion trajectory decoding makes a promising approach for neurotechnology which can be used for neural control of motion reconstruction and neurorehabilitation tools. However, the feasibility and validity of continuous motion decoding by non-invasive brain activity are not clear. The main aim of this study was to perform a meta-analysis across studies that examined the ability of EEG-based continuous motion decoding of upper limb movements.

APPROACH

Pearson's correlation coefficient (CC) was used to evaluate the model performance of the studies and considered as an effect size. To estimate the overall effect size of neural decoding of motion trajectory across studies, characteristics of included studies were addressed and the random effect model was applied to the heterogeneous studies which estimated overall effect size distribution. Furthermore, the significant difference between the two subgroups of imagined and executed movements was analysed.

MAIN RESULTS

The mean of the overall effect size was computed 0.46 across the nonhomogeneous studies. The results showed no significant difference between imagined and executed movements (Chi²=0.28, df = 1, p = 0.60).

SIGNIFICANCE

Meta-analysis results confirm that imagination like execution movements can be used for neural decoding of motion trajectory in neural motor control systems. Also, nonlinear compare with linear model statistically confirmed to be more beneficial for complex movements. Furthermore, a new approach of synergy-based motion decoding can be significantly effective to increase model performance and more research needs to evaluate this method for different levels of complexity of movements.IMPLICATIONS FOR REHABILITATIONNeural decoding methods base on EEG as a non-invasive brain activity, are more user friendly for neurorehabilitation than invasive methods that developing of it makes it more applicable for reconstructing activities of daily living.Neurotechnology for neural control of motion reconstruction, makes the rehabilitation tools to be more synchrony with human intentional movement that can be used to improve the brain neuroplastisity in stroke or other paralysed people.The feasibility and validity of imagined movements equal with executed movements show that amputee people also can benefit EEG-based motion decoding for controling rehabilitation tools just by imagination of their intentional movements.For neurorehabilitation tools, comparing the study outcomes illucidate that the approach of synergy-based motor control in brain activities concluded significantly high performance that highlighted the need it to more investigated in future research.

Decoding of voluntary and involuntary upper-limb motor imagery based on graph fourier transform and cross-frequency coupling coefficients

OBJECTIVE

Brain-computer interface (BCI) technology based on motor imagery (MI) control has become a research hotspot but continues to encounter numerous challenges. BCI can assist in the recovery of stroke patients and serve as a key technology in robot control. Current research on MI almost exclusively focuses on the hands, feet, and tongue. Therefore, the purpose of this paper is to establish a four-class MI BCI system, in which the four types are the four articulations within the right upper limbs, involving the shoulder, elbow, wrist, and hand.

APPROACH

Ten subjects were chosen to perform nine upper-limb analytic movements, after which the differences were compared in P300, movement-related potentials(MRPS), and event-related desynchronization/event-related synchronization under voluntary MI (V-MI) and involuntary MI (INV-MI). Next, the cross-frequency coupling (CFC) coefficient based on mutual information was extracted from the electrodes and frequency bands with interest. Combined with the image Fourier transform and twin bounded support vector machine classifier, four kinds of electroencephalography data were classified, and the classifier's parameters were optimized using a genetic algorithm.

MAIN RESULTS

The results were shown to be encouraging, with an average accuracy of 93.2% and 92.2% for V-MI and INV-MI, respectively, and over 95% for any three classes and any two classes. In most cases, the accuracy of feature extraction using the proximal articulations as the basis was found to be relatively high and had better performance.

SIGNIFICANCE

This paper discussed four types of MI according to three aspects under two modes and classed them by combining graph Fourier transform and CFC. Accordingly, the theoretical discussion and classification methods may provide a fundamental theoretical basis for BCI interface applications.

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.

Inter-subject correlations during natural viewing: A filter-bank approach

A central question in neuroscience is how the brain processes real-world sensory input. For decades most classical studies focus on carefully controlled artificial stimuli. More recently researchers started to investigate brain activity under more realistic conditions. The main challenge in this setting is the analysis of the complex signals obtained with modern neuroimaging methods in response to natural stimuli. Inter-subject correlations (ISCs) have become a popular paradigm to study brain activation under natural stimulation. The underlying assumption of this analysis is that features of natural stimuli that are perceived and processed by all subjects exposed to the same stimulus result in similar activation patterns across subjects. Higher degrees of realism in stimulation, for instance audiovisual stimulation is more realistic than auditory stimulation, is usually associated with higher ISC values. We can confirm these findings in experiments in which we present a movie stimulus with varying degrees of realism. Extending previous findings we highlight the importance of artifact removal when evaluating ISCs and show that the impact of realism in natural stimulation on ISCs is frequency-dependent. A major challenge associated with this type of analysis is that it can be difficult to attribute the correlation strength to the physiological process of interest. In this study, we demonstrate that ISCs of neural activation as measured by electroencephalogram (EEG) recordings are influenced significantly by non-neural artifacts such as occulograms. Our findings highlight the potential of inter-subject correlations as a biomarker for immersion: If more realistic stimuli consistently lead to higher inter-subject correlations, then inter-subject correlations can serve as a quantitative marker for how engaging audiovisual stimuli are perceived.Clinical relevance- Future research will evaluate if correlation levels among subjects, who are exposed to natural stimuli are affected by neurological diseases such as Alzheimers, Parkinsons, and Schizophrenia among others.

Subject-Independent Brain-Computer Interfaces Based on Deep Convolutional Neural Networks

For a brain-computer interface (BCI) system, a calibration procedure is required for each individual user before he/she can use the BCI. This procedure requires approximately 20-30 min to collect enough data to build a reliable decoder. It is, therefore, an interesting topic to build a calibration-free, or subject-independent, BCI. In this article, we construct a large motor imagery (MI)-based electroencephalography (EEG) database and propose a subject-independent framework based on deep convolutional neural networks (CNNs). The database is composed of 54 subjects performing the left- and right-hand MI on two different days, resulting in 21 600 trials for the MI task. In our framework, we formulated the discriminative feature representation as a combination of the spectral-spatial input embedding the diversity of the EEG signals, as well as a feature representation learned from the CNN through a fusion technique that integrates a variety of discriminative brain signal patterns. To generate spectral-spatial inputs, we first consider the discriminative frequency bands in an information-theoretic observation model that measures the power of the features in two classes. From discriminative frequency bands, spectral-spatial inputs that include the unique characteristics of brain signal patterns are generated and then transformed into a covariance matrix as the input to the CNN. In the process of feature representations, spectral-spatial inputs are individually trained through the CNN and then combined by a concatenation fusion technique. In this article, we demonstrate that the classification accuracy of our subject-independent (or calibration-free) model outperforms that of subject-dependent models using various methods [common spatial pattern (CSP), common spatiospectral pattern (CSSP), filter bank CSP (FBCSP), and Bayesian spatio-spectral filter optimization (BSSFO)].

Decoding kinetic features of hand motor preparation from single-trial EEG using convolutional neural networks

Building accurate movement decoding models from brain signals is crucial for many biomedical applications. Predicting specific movement features, such as speed and force, before movement execution may provide additional useful information at the expense of increasing the complexity of the decoding problem. Recent attempts to predict movement speed and force from the electroencephalogram (EEG) achieved classification accuracies at or slightly above chance levels, highlighting the need for more accurate prediction strategies. Thus, the aims of this study were to accurately predict hand movement speed and force from single-trial EEG signals and to decode neurophysiological information of motor preparation from the prediction strategies. To these ends, a decoding model based on convolutional neural networks (ConvNets) was implemented and compared against other state-of-the-art prediction strategies, such as support vector machines and decision trees. ConvNets outperformed the other prediction strategies, achieving an overall accuracy of 84% in the classification of two different levels of speed and force (four-class classification) from pre-movement single-trial EEG (100 ms and up to 1,600 ms prior to movement execution). Furthermore, an analysis of the ConvNet architectures suggests that the network performs a complex spatiotemporal integration of EEG data to optimize classification accuracy. These results show that movement speed and force can be accurately predicted from single-trial EEG, and that the prediction strategies may provide useful neurophysiological information about motor preparation.

A Usability Study of Low-cost Wireless Brain-Computer Interface for Cursor Control Using Online Linear Model

Computer cursor control using electroencephalogram (EEG) signals is a common and well-studied brain-computer interface (BCI). The emphasis of the literature has been primarily on evaluation of the objective measures of assistive BCIs such as accuracy of the neural decoder whereas the subjective measures such as user's satisfaction play an essential role for the overall success of a BCI. As far as we know, the BCI literature lacks a comprehensive evaluation of the usability of the mind-controlled computer cursor in terms of decoder efficiency (accuracy), user experience, and relevant confounding variables concerning the platform for the public use. To fill this gap, we conducted a two-dimensional EEG-based cursor control experiment among 28 healthy participants. The computer cursor velocity was controlled by the imagery of hand movement using a paradigm presented in the literature named imagined body kinematics (IBK) with a low-cost wireless EEG headset. We evaluated the usability of the platform for different objective and subjective measures while we investigated the extent to which the training phase may influence the ultimate BCI outcome. We conducted pre- and post- BCI experiment interview questionnaires to evaluate the usability. Analyzing the questionnaires and the testing phase outcome shows a positive correlation between the individuals' ability of visualization and their level of mental controllability of the cursor. Despite individual differences, analyzing training data shows the significance of electrooculogram (EOG) on the predictability of the linear model. The results of this work may provide useful insights towards designing a personalized user-centered assistive BCI.

Error Correction Regression Framework for Enhancing the Decoding Accuracies of Ear-EEG Brain-Computer Interfaces

Ear-electroencephalography (EEG) is a promising tool for practical brain-computer interface (BCI) applications because it is more unobtrusive, comfortable, and mobile than a typical scalp-EEG system. However, an ear-EEG has a natural constraint of electrode location (e.g., limited in or around the ear) for acquiring informative brain signals sufficiently. Achieving reliable performance of ear-EEG in specific BCI paradigms that do not utilize brain signals on the temporal lobe around the ear is difficult. For example, steady-state visual evoked potentials (SSVEPs), which are mainly generated in the occipital area, have a significantly attenuated and distorted amplitude in ear-EEG. Therefore, preserving the high level of decoding accuracy is challenging and essential for SSVEP BCI based on ear-EEG. In this paper, we first investigate linear and nonlinear regression methods to increase the decoding accuracy of ear-EEG regarding SSVEP paradigm by utilizing the estimated target EEG signals on the occipital area. Then, we investigate an ensemble method to consider the prediction variability of the regression methods. Finally, we propose an error correction regression (ECR) framework to reduce the prediction errors by adding an additional nonlinear regression process (i.e., kernel ridge regression). We evaluate the ECR framework in terms of single session, session-to-session transfer, and subject-transfer decoding. We also validate the online decoding ability of the proposed framework with a short-time window size. The average accuracies are observed to be 91.11±9.14%, 90.52±8.67%, 86.96±12.13%, and 78.79±12.59%. This paper demonstrates that SSVEP BCI based on ear-EEG can achieve reliable performance with the proposed ECR framework.

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.

Decoding hand movements from human EEG to control a robotic arm in a simulation environment

OBJECTIVE

Daily life tasks can become a significant challenge for motor impaired persons. Depending on the severity of their impairment, they require more complex solutions to retain an independent life. Brain-computer interfaces (BCIs) are targeted to provide an intuitive form of control for advanced assistive devices such as robotic arms or neuroprostheses. In our current study we aim to decode three different executed hand movements in an online BCI scenario from electroencephalographic (EEG) data.

APPROACH

Immersed in a desktop-based simulation environment, 15 non-disabled participants interacted with virtual objects from daily life by an avatar's robotic arm. In a short calibration phase, participants performed executed palmar and lateral grasps and wrist supinations. Using this data, we trained a classification model on features extracted from the low frequency time domain. In the subsequent evaluation phase, participants controlled the avatar's robotic arm and interacted with the virtual objects in case of a correct classification.

MAIN RESULTS

On average, participants scored online 48% of all movement trials correctly (3-condition scenario, adjusted chance level 40%, alpha = 0.05). The underlying movement-related cortical potentials (MRCPs) of the acquired calibration data show significant differences between conditions over contralateral central sensorimotor areas, which are retained in the data acquired from the online BCI use.

SIGNIFICANCE

We could show the successful online decoding of two grasps and one wrist supination movement using low frequency time domain features of the human EEG. These findings can potentially contribute to the development of a more natural and intuitive BCI-based control modality for upper limb motor neuroprostheses or robotic arms for people with motor impairments.

Stabilization of a brain-computer interface via the alignment of low-dimensional spaces of neural activity

The instability of neural recordings can render clinical brain-computer interfaces (BCIs) uncontrollable. Here, we show that the alignment of low-dimensional neural manifolds (low-dimensional spaces that describe specific correlation patterns between neurons) can be used to stabilize neural activity, thereby maintaining BCI performance in the presence of recording instabilities. We evaluated the stabilizer with non-human primates during online cursor control via intracortical BCIs in the presence of severe and abrupt recording instabilities. The stabilized BCIs recovered proficient control under different instability conditions and across multiple days. The stabilizer does not require knowledge of user intent and can outperform supervised recalibration. It stabilized BCIs even when neural activity contained little information about the direction of cursor movement. The stabilizer may be applicable to other neural interfaces and may improve the clinical viability of BCIs.

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.

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.

Decoding Movement-Related Cortical Potentials Based on Subject-Dependent and Section-Wise Spectral Filtering

An important challenge in developing a movement-related cortical potential (MRCP)-based brain-machine interface (BMI) is an accurate decoding of the user intention for real-world environments. However, the performance remains insufficient for real-time decoding owing to the endogenous signal characteristics compared to other BMI paradigms. This study aims to enhance the MRCP decoding performance from the perspective of preprocessing techniques (i.e., spectral filtering). To the best of our knowledge, existing MRCP studies have used spectral filters with a fixed frequency bandwidth for all subjects. Hence, we propose a subject-dependent and section-wise spectral filtering (SSSF) method that considers the subjects' individual MRCP characteristics for two different temporal sections. In this study, MRCP data were acquired under a powered exoskeleton environments in which the subjects conducted self-initiated walking. We evaluated our method using both our experimental data and a public dataset (BNCI Horizon 2020). The decoding performance using the SSSF was 0.86 (±0.09), and the performance on the public dataset was 0.73 (±0.06) across all subjects. The experimental results showed a statistically significant enhancement ( ) compared with the fixed frequency bands used in previous methods on both datasets. In addition, we presented successful decoding results from a pseudo-online analysis. Therefore, we demonstrated that the proposed SSSF method can involve more meaningful MRCP information than conventional methods.

Force decoding using local field potentials in primary motor cortex: PLS or Kalman filter regression?

The development of brain-computer interface (BCI) systems is an important approach in brain studies. Control of communication devices and prostheses in real-world scenarios requires complex movement parameters. Decoding a variety of neural signals captured by micro-wire arrays is a potential applicant for extracting movement-related information. The present work was conducted to compare the functionality of partial least square (PLS) regression and Kalman filter to predict the force parameter from local field potential (LFP) signals of the primary motor cortex (M1). The signals were recorded using a 16-channel micro-wire array from the forelimb-related area of the M1 of three rats performing a behavioral task in which the force signal of the rat's forelimb paw was generated. Our results show that PLS regression and Kalman filters with the mean performance of 0.75 and 0.72 in terms of the correlation coefficient (CC) and 0.37 and 0.48 in terms of normalized mean square error (NMSE), respectively, are effective methods for decoding the force parameter from LFPs. Kalman filter underperforms PLS both in performance and speed. Although adding nonlinearity to the Kalman filter results in equally accurate CC performance as PLS, it has even more computational cost. Therefore, it is inferred that nonlinear methods do not necessarily have better functionality than linear ones and PLS, as a simple fast linear method could be an effectively applicable regression technique for BCIs.

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.

A Subject-Transfer Framework Based on Single-Trial EMG Analysis Using Convolutional Neural Networks

In recent years, electromyography (EMG)-based practical myoelectric interfaces have been developed to improve the quality of daily life for people with physical disabilities. With these interfaces, it is very important to decode a user's movement intention, to properly control the external devices. However, improving the performance of these interfaces is difficult due to the high variations in the EMG signal patterns caused by intra-user variability. Therefore, this paper proposes a novel subject-transfer framework for decoding hand movements, which is robust in terms of intra-user variability. In the proposed framework, supportive convolutional neural network (CNN) classifiers, which are pre-trained using the EMG data of several subjects, are selected and fine-tuned for the target subject via single-trial analysis. Then, the target subject's hand movements are classified by voting the outputs of the supportive CNN classifiers. The feasibility of the proposed framework is validated with NinaPro databases 2 and 3, which comprise 49 hand movements of 40 healthy and 11 amputee subjects, respectively. The experimental results indicate that, when compared to the self-decoding framework, which uses only the target subject's data, the proposed framework can successfully decode hand movements with improved performance in both healthy and amputee subjects. From the experimental results, the proposed subject-transfer framework can be seen to represent a useful tool for EMG-based practical myoelectric interfaces controlling external devices.

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.

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%).