Motor Imagery-Based Brain-Computer Interface Coupled to a Robotic Hand Orthosis Aimed for Neurorehabilitation of Stroke Patients

STaRNet: A spatio-temporal and Riemannian network for high-performance motor imagery decoding

Brain-computer interfaces (BCIs), representing a transformative form of human-computer interaction, empower users to interact directly with external environments through brain signals. In response to the demands for high accuracy, robustness, and end-to-end capabilities within BCIs based on motor imagery (MI), this paper introduces STaRNet, a novel model that integrates multi-scale spatio-temporal convolutional neural networks (CNNs) with Riemannian geometry. Initially, STaRNet integrates a multi-scale spatio-temporal feature extraction module that captures both global and local features, facilitating the construction of Riemannian manifolds from these comprehensive spatio-temporal features. Subsequently, a matrix logarithm operation transforms the manifold-based features into the tangent space, followed by a dense layer for classification. Without preprocessing, STaRNet surpasses state-of-the-art (SOTA) models by achieving an average decoding accuracy of 83.29% and a kappa value of 0.777 on the BCI Competition IV 2a dataset, and 95.45% accuracy with a kappa value of 0.939 on the High Gamma Dataset. Additionally, a comparative analysis between STaRNet and several SOTA models, focusing on the most challenging subjects from both datasets, highlights exceptional robustness of STaRNet. Finally, the visualizations of learned frequency bands demonstrate that temporal convolutions have learned MI-related frequency bands, and the t-SNE analyses of features across multiple layers of STaRNet exhibit strong feature extraction capabilities. We believe that the accurate, robust, and end-to-end capabilities of the STaRNet will facilitate the advancement of BCIs.

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

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

Decoding Multi-Brain Motor Imagery From EEG Using Coupling Feature Extraction and Few-Shot Learning

Electroencephalography (EEG)-based motor imagery (MI) is one of brain computer interface (BCI) paradigms, which aims to build a direct communication pathway between human brain and external devices by decoding the brain activities. In a traditional way, MI BCI replies on a single brain, which suffers from the limitations, such as low accuracy and weak stability. To alleviate these limitations, multi-brain BCI has emerged based on the integration of multiple individuals' intelligence. Nevertheless, the existing decoding methods mainly use linear averaging or feature integration learning from multi-brain EEG data, and do not effectively utilize coupling relationship features, resulting in undesired decoding accuracy. To overcome these challenges, we proposed an EEG-based multi-brain MI decoding method, which utilizes coupling feature extraction and few-shot learning to capture coupling relationship features among multi-brains with only limited EEG data. We performed an experiment to collect EEG data from multiple persons who engaged in the same task simultaneously and compared the methods on the collected data. The comparison results showed that our proposed method improved the performance by 14.23% compared to the single-brain mode in the 10-shot three-class decoding task. It demonstrated the effectiveness of the proposed method and usability of the method in the context of only small amount of EEG data available.

Explainable cross-task adaptive transfer learning for motor imagery EEG classification

Objective. In the field of motor imagery (MI) electroencephalography (EEG)-based brain-computer interfaces, deep transfer learning (TL) has proven to be an effective tool for solving the problem of limited availability in subject-specific data for the training of robust deep learning (DL) models. Although considerable progress has been made in the cross-subject/session and cross-device scenarios, the more challenging problem of cross-task deep TL remains largely unexplored.Approach. We propose a novel explainable cross-task adaptive TL method for MI EEG decoding. Firstly, similarity analysis and data alignment are performed for EEG data of motor execution (ME) and MI tasks. Afterwards, the MI EEG decoding model is obtained via pre-training with extensive ME EEG data and fine-tuning with partial MI EEG data. Finally, expected gradient-based post-hoc explainability analysis is conducted for the visualization of important temporal-spatial features.Main results. Extensive experiments are conducted on one large ME EEG High-Gamma dataset and two large MI EEG datasets (openBMI and GIST). The best average classification accuracy of our method reaches 80.00% and 72.73% for OpenBMI and GIST respectively, which outperforms several state-of-the-art algorithms. In addition, the results of the explainability analysis further validate the correlation between ME and MI EEG data and the effectiveness of ME/MI cross-task adaptation.Significance. This paper confirms that the decoding of MI EEG can be well facilitated by pre-existing ME EEG data, which largely relaxes the constraint of training samples for MI EEG decoding and is important in a practical sense.

Brain-computer interface treatment for gait rehabilitation in stroke patients

The use of Brain-Computer Interfaces (BCI) as rehabilitation tools for chronically ill neurological patients has become more widespread. BCIs combined with other techniques allow the user to restore neurological function by inducing neuroplasticity through real-time detection of motor-imagery (MI) as patients perform therapy tasks. Twenty-five stroke patients with gait disability were recruited for this study. Participants performed 25 sessions with the MI-BCI and assessment visits to track functional changes during the therapy. The results of this study demonstrated a clinically significant increase in walking speed of 0.19 m/s, 95%CI [0.13-0.25], p < 0.001. Patients also reduced spasticity and improved their range of motion and muscle contraction. The BCI treatment was effective in promoting long-lasting functional improvements in the gait speed of chronic stroke survivors. Patients have more movements in the lower limb; therefore, they can walk better and safer. This functional improvement can be explained by improved neuroplasticity in the central nervous system.

Study of the Correlation between the Motor Ability of the Individual Upper Limbs and Motor Imagery Induced Neural Activities

Motor imagery based brain-computer interfaces (MI-BCIs) have excellent application prospects in motor enhancement and rehabilitation. However, MI-induced electroencephalogram features applied to MI-BCI usually vary from person to person. This study aimed to investigate whether the motor ability of the individual upper limbs was associated with these features, which helps understand the causes of inter-subject variability. We focused on the behavioral and psychological factors reflecting motor abilities. We first obtained the behavioral scale scores from Edinburgh Handedness Questionnaire, Maximum Grip Strength Test, and Purdue Pegboard Test assessments to evaluate the motor execution ability. We also required the subjects to complete the psychological Movement Imagery Questionnaire-3 estimate, representing MI ability. Then we recorded EEG signals from all twenty-two subjects during MI tasks. Pearson correlation coefficient and stepwise regression were used to analyze the relationships between MI-induced relative event-related desynchronization (rERD) patterns and motor abilities. Both Purdue Pegboard Test and Movement Imagery Questionnaire-3 scores had significant correlations with MI-induced neural oscillation patterns. Notably, the Purdue Pegboard Test of the left hand had the most significant correlation with the alpha rERD. The results of stepwise multiple regression analysis showed that the Purdue Pegboard Test and Movement Imagery Questionnaire-3 could best predict the MI-induced rERD. The results demonstrate that hand dexterity and fine motor coordination are significantly related to MI-induced neural activities. In addition, the method of imagining is also relevant to MI features. Therefore, this study is meaningful for understanding individual differences and the design of user-centered MI-BCI.

MI-CAT: A transformer-based domain adaptation network for motor imagery classification

Due to its convenience and safety, electroencephalography (EEG) data is one of the most widely used signals in motor imagery (MI) brain-computer interfaces (BCIs). In recent years, methods based on deep learning have been widely applied to the field of BCIs, and some studies have gradually tried to apply Transformer to EEG signal decoding due to its superior global information focusing ability. However, EEG signals vary from subject to subject. Based on Transformer, how to effectively use data from other subjects (source domain) to improve the classification performance of a single subject (target domain) remains a challenge. To fill this gap, we propose a novel architecture called MI-CAT. The architecture innovatively utilizes Transformer's self-attention and cross-attention mechanisms to interact features to resolve differential distribution between different domains. Specifically, we adopt a patch embedding layer for the extracted source and target features to divide the features into multiple patches. Then, we comprehensively focus on the intra-domain and inter-domain features by stacked multiple Cross-Transformer Blocks (CTBs), which can adaptively conduct bidirectional knowledge transfer and information exchange between domains. Furthermore, we also utilize two non-shared domain-based attention blocks to efficiently capture domain-dependent information, optimizing the features extracted from the source and target domains to assist in feature alignment. To evaluate our method, we conduct extensive experiments on two real public EEG datasets, Dataset IIb and Dataset IIa, achieving competitive performance with an average classification accuracy of 85.26% and 76.81%, respectively. Experimental results demonstrate that our method is a powerful model for decoding EEG signals and facilitates the development of the Transformer for brain-computer interfaces (BCIs).

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.

Motor imagery brain–computer interface rehabilitation system enhances upper limb performance and improves brain activity in stroke patients: A clinical study

This study compared the efficacy of Motor Imagery brain-computer interface (MI-BCI) combined with physiotherapy and physiotherapy alone in ischemic stroke before and after rehabilitation training. We wanted to explore whether the rehabilitation effect of MI-BCI is affected by the severity of the patient’s condition and whether MI-BCI was effective for all patients. Forty hospitalized patients with ischemic stroke with motor deficits participated in this study. The patients were divided into MI and control groups. Functional assessments were performed before and after rehabilitation training. The Fugl-Meyer Assessment (FMA) was used as the primary outcome measure, and its shoulder and elbow scores and wrist scores served as secondary outcome measures. The motor assessment scale (MAS) was used to assess motor function recovery. We used non-contrast CT (NCCT) to investigate the influence of different types of middle cerebral artery high-density signs on the prognosis of ischemic stroke. Brain topographic maps can directly reflect the neural activity of the brain, so we used them to detect changes in brain function and brain topological power response after stroke. Compared the MI group and control group after rehabilitation training, better functional outcome was observed after MI-BCI rehabilitation, including a significantly higher probability of achieving a relevant increase in the Total FMA scores (MI = 16.70 ± 12.79, control = 5.34 ± 10.48), FMA shoulder and elbow scores (MI = 12.56 ± 6.37, control = 2.45 ± 7.91), FMA wrist scores (MI = 11.01 ± 3.48, control = 3.36 ± 5.79), the MAS scores (MI = 3.62 ± 2.48, control = 1.85 ± 2.89), the NCCT (MI = 21.94 ± 2.37, control = 17.86 ± 3.55). The findings demonstrate that MI-BCI rehabilitation training could more effectively improve motor function after upper limb motor dysfunction after stroke compared with routine rehabilitation training, which verifies the feasibility of active induction of neural rehabilitation. The severity of the patient’s condition may affect the rehabilitation effect of the MI-BCI system.

Tailoring brain-machine interface rehabilitation training based on neural reorganization: towards personalized treatment for stroke patients

Electroencephalogram (EEG)-based brain-machine interface (BMI) has the potential to enhance rehabilitation training efficiency, but it still remains elusive regarding how to design BMI training for heterogeneous stroke patients with varied neural reorganization. Here, we hypothesize that tailoring BMI training according to different patterns of neural reorganization can contribute to a personalized rehabilitation trajectory. Thirteen stroke patients were recruited in a 2-week personalized BMI training experiment. Clinical and behavioral measurements, as well as cortical and muscular activities, were assessed before and after training. Following treatment, significant improvements were found in motor function assessment. Three types of brain activation patterns were identified during BMI tasks, namely, bilateral widespread activation, ipsilesional focusing activation, and contralesional recruitment activation. Patients with either ipsilesional dominance or contralesional dominance can achieve recovery through personalized BMI training. Results indicate that personalized BMI training tends to connect the potentially reorganized brain areas with event-contingent proprioceptive feedback. It can also be inferred that personalization plays an important role in establishing the sensorimotor loop in BMI training. With further understanding of neural rehabilitation mechanisms, personalized treatment strategy is a promising way to improve the rehabilitation efficacy and promote the clinical use of rehabilitation robots and other neurotechnologies.

Literature review of stroke assessment for upper-extremity physical function via EEG, EMG, kinematic, and kinetic measurements and their reliability

BACKGROUND

Significant clinician training is required to mitigate the subjective nature and achieve useful reliability between measurement occasions and therapists. Previous research supports that robotic instruments can improve quantitative biomechanical assessments of the upper limb, offering reliable and more sensitive measures. Furthermore, combining kinematic and kinetic measurements with electrophysiological measurements offers new insights to unlock targeted impairment-specific therapy. This review presents common methods for analyzing biomechanical and neuromuscular data by describing their validity and reporting their reliability measures.

METHODS

This paper reviews literature (2000-2021) on sensor-based measures and metrics for upper-limb biomechanical and electrophysiological (neurological) assessment, which have been shown to correlate with clinical test outcomes for motor assessment. The search terms targeted robotic and passive devices developed for movement therapy. Journal and conference papers on stroke assessment metrics were selected using PRISMA guidelines. Intra-class correlation values of some of the metrics are recorded, along with model, type of agreement, and confidence intervals, when reported.

RESULTS

A total of 60 articles are identified. The sensor-based metrics assess various aspects of movement performance, such as smoothness, spasticity, efficiency, planning, efficacy, accuracy, coordination, range of motion, and strength. Additional metrics assess abnormal activation patterns of cortical activity and interconnections between brain regions and muscle groups; aiming to characterize differences between the population who had a stroke and the healthy population.

CONCLUSION

Range of motion, mean speed, mean distance, normal path length, spectral arc length, number of peaks, and task time metrics have all demonstrated good to excellent reliability, as well as provide a finer resolution compared to discrete clinical assessment tests. EEG power features for multiple frequency bands of interest, specifically the bands relating to slow and fast frequencies comparing affected and non-affected hemispheres, demonstrate good to excellent reliability for populations at various stages of stroke recovery. Further investigation is needed to evaluate the metrics missing reliability information. In the few studies combining biomechanical measures with neuroelectric signals, the multi-domain approaches demonstrated agreement with clinical assessments and provide further information during the relearning phase. Combining the reliable sensor-based metrics in the clinical assessment process will provide a more objective approach, relying less on therapist expertise. This paper suggests future work on analyzing the reliability of metrics to prevent biasedness and selecting the appropriate analysis.

Continuous versus discrete robotic feedback for brain-computer interfaces aimed for neurorehabilitation

Introduction

Brain-Computer Interfaces (BCI) can allow control of external devices using motor imagery (MI) decoded from electroencephalography (EEG). Although BCI have a wide range of applications including neurorehabilitation, the low spatial resolution of EEG, coupled to the variability of cortical activations during MI, make control of BCI based on EEG a challenging task.

Methods

An assessment of BCI control with different feedback timing strategies was performed. Two different feedback timing strategies were compared, comprised by passive hand movement provided by a robotic hand orthosis. One of the timing strategies, the continuous, involved the partial movement of the robot immediately after the recognition of each time segment in which hand MI was performed. The other feedback, the discrete, was comprised by the entire movement of the robot after the processing of the complete MI period. Eighteen healthy participants performed two sessions of BCI training and testing, one with each feedback.

Results

Significantly higher BCI performance (65.4 ± 17.9% with the continuous and 62.1 ± 18.6% with the discrete feedback) and pronounced bilateral alpha and ipsilateral beta cortical activations were observed with the continuous feedback.

Discussion

It was hypothesized that these effects, although heterogenous across participants, were caused by the enhancement of attentional and closed-loop somatosensory processes. This is important, since a continuous feedback timing could increase the number of BCI users that can control a MI-based system or enhance cortical activations associated with neuroplasticity, important for neurorehabilitation applications.

MI-DABAN: A dual-attention-based adversarial network for motor imagery classification

The brain-computer interface (BCI) based on motor imagery electroencephalography (EEG) is widely used because of its convenience and safety. However, due to the distributional disparity between EEG signals, data from other subjects cannot be used directly to train a subject-specific classifier. For efficient use of the labeled data, domain transfer learning and adversarial learning are gradually applied to BCI classification tasks. While these methods improve classification performance, they only align globally and ignore task-specific class boundaries, which may lead to the blurring of features near the classification boundaries. Simultaneously, they employ fully shared generators to extract features, resulting in the loss of domain-specific information and the destruction of performance. To address these issues, we propose a novel dual-attention-based adversarial network for motor imagery classification (MI-DABAN). Our framework leverages multiple subjects' knowledge to improve a single subject's motor imagery classification performance by cleverly using a novel adversarial learning method and two unshared attention blocks. Specifically, without introducing additional domain discriminators, we iteratively maximize and minimize the output difference between the two classifiers to implement adversarial learning to ensure accurate domain alignment. Among them, maximization is used to identify easily confused samples near the decision boundary, and minimization is used to align the source and target domain distributions. Moreover, for the shallow features from source and target domains, we use two non-shared attention blocks to preserve domain-specific information, which can prevent the negative transfer of domain information and further improve the classification performance on test data. We conduct extensive experiments on two publicly available EEG datasets, namely BCI Competition IV Datasets 2a and 2b. The experiment results demonstrate our method's effectiveness and superiority.

Online adaptive group-wise sparse Penalized Recursive Exponentially Weighted N-way Partial Least Square for epidural intracranial BCI

Introduction

Motor Brain-Computer Interfaces (BCIs) create new communication pathways between the brain and external effectors for patients with severe motor impairments. Control of complex effectors such as robotic arms or exoskeletons is generally based on the real-time decoding of high-resolution neural signals. However, high-dimensional and noisy brain signals pose challenges, such as limitations in the generalization ability of the decoding model and increased computational demands.

Methods

The use of sparse decoders may offer a way to address these challenges. A sparsity-promoting penalization is a common approach to obtaining a sparse solution. BCI features are naturally structured and grouped according to spatial (electrodes), frequency, and temporal dimensions. Applying group-wise sparsity, where the coefficients of a group are set to zero simultaneously, has the potential to decrease computational time and memory usage, as well as simplify data transfer. Additionally, online closed-loop decoder adaptation (CLDA) is known to be an efficient procedure for BCI decoder training, taking into account neuronal feedback. In this study, we propose a new algorithm for online closed-loop training of group-wise sparse multilinear decoders using L _p -Penalized Recursive Exponentially Weighted N-way Partial Least Square (PREW-NPLS). Three types of sparsity-promoting penalization were explored using L _p with p = 0., 0.5, and 1.

Results

The algorithms were tested offline in a pseudo-online manner for features grouped by spatial dimension. A comparison study was conducted using an epidural ECoG dataset recorded from a tetraplegic individual during long-term BCI experiments for controlling a virtual avatar (left/right-hand 3D translation). Novel algorithms showed comparable or better decoding performance than conventional REW-NPLS, which was achieved with sparse models. The proposed algorithms are compatible with real-time CLDA.

Discussion

The proposed algorithm demonstrated good performance while drastically reducing the computational load and the memory consumption. However, the current study is limited to offline computation on data recorded with a single patient, with penalization restricted to the spatial domain only.

A case report: Upper limb recovery from stroke related to SARS-CoV-2 infection during an intervention with a brain-computer interface

COVID-19 may increase the risk of acute ischemic stroke that can cause a loss of upper limb function, even in patients with low risk factors. However, only individual cases have been reported assessing different degrees of hospitalization outcomes. Therefore, outpatient recovery profiles during rehabilitation interventions are needed to better understand neuroplasticity mechanisms required for upper limb motor recovery. Here, we report the progression of physiological and clinical outcomes during upper limb rehabilitation of a 41-year-old patient, without any stroke risk factors, which presented a stroke on the same day as being diagnosed with COVID-19. The patient, who presented hemiparesis with incomplete motor recovery after conventional treatment, participated in a clinical trial consisting of an experimental brain-computer interface (BCI) therapy focused on upper limb rehabilitation during the chronic stage of stroke. Clinical and physiological features were measured throughout the intervention, including the Fugl-Meyer Assessment for the Upper Extremity (FMA-UE), Action Research Arm Test (ARAT), the Modified Ashworth Scale (MAS), corticospinal excitability using transcranial magnetic stimulation, cortical activity with electroencephalography, and upper limb strength. After the intervention, the patient gained 8 points and 24 points of FMA-UE and ARAT, respectively, along with a reduction of one point of MAS. In addition, grip and pinch strength doubled. Corticospinal excitability of the affected hemisphere increased while it decreased in the unaffected hemisphere. Moreover, cortical activity became more pronounced in the affected hemisphere during movement intention of the paralyzed hand. Recovery was higher compared to that reported in other BCI interventions in stroke and was due to a reengagement of the primary motor cortex of the affected hemisphere during hand motor control. This suggests that patients with stroke related to COVID-19 may benefit from a BCI intervention and highlights the possibility of a significant recovery in these patients, even in the chronic stage of stroke.

A Comprehensive Review of Endogenous EEG-Based BCIs for Dynamic Device Control

Electroencephalogram (EEG)-based brain–computer interfaces (BCIs) provide a novel approach for controlling external devices. BCI technologies can be important enabling technologies for people with severe mobility impairment. Endogenous paradigms, which depend on user-generated commands and do not need external stimuli, can provide intuitive control of external devices. This paper discusses BCIs to control various physical devices such as exoskeletons, wheelchairs, mobile robots, and robotic arms. These technologies must be able to navigate complex environments or execute fine motor movements. Brain control of these devices presents an intricate research problem that merges signal processing and classification techniques with control theory. In particular, obtaining strong classification performance for endogenous BCIs is challenging, and EEG decoder output signals can be unstable. These issues present myriad research questions that are discussed in this review paper. This review covers papers published until the end of 2021 that presented BCI-controlled dynamic devices. It discusses the devices controlled, EEG paradigms, shared control, stabilization of the EEG signal, traditional machine learning and deep learning techniques, and user experience. The paper concludes with a discussion of open questions and avenues for future work.

SSVEP-Based Brain Computer Interface Controlled Soft Robotic Glove for Post-Stroke Hand Function Rehabilitation

Soft robotic glove with brain computer interfaces (BCI) control has been used for post-stroke hand function rehabilitation. Motor imagery (MI) based BCI with robotic aided devices has been demonstrated as an effective neural rehabilitation tool to improve post-stroke hand function. It is necessary for a user of MI-BCI to receive a long time training, while the user usually suffers unsuccessful and unsatisfying results in the beginning. To propose another non-invasive BCI paradigm rather than MI-BCI, steady-state visually evoked potentials (SSVEP) based BCI was proposed as user intension detection to trigger the soft robotic glove for post-stroke hand function rehabilitation. Thirty post-stroke patients with impaired hand function were randomly and equally divided into three groups to receive conventional, robotic, and BCI-robotic therapy in this randomized control trial (RCT). Clinical assessment of Fugl-Meyer Motor Assessment of Upper Limb (FMA-UL), Wolf Motor Function Test (WMFT) and Modified Ashworth Scale (MAS) were performed at pre-training, post-training and three months follow-up. In comparing to other groups, The BCI-robotic group showed significant improvement after training in FMA full score (10.05±8.03, p=0.001), FMA shoulder/elbow (6.2±5.94, p=0.0004) and FMA wrist/hand (4.3±2.83, p=0.007), and WMFT (5.1±5.53, p=0.037). The improvement of FMA was significantly correlated with BCI accuracy (r=0.714, p=0.032). Recovery of hand function after rehabilitation of SSVEP-BCI controlled soft robotic glove showed better result than solely robotic glove rehabilitation, equivalent efficacy as results from previous reported MI-BCI robotic hand rehabilitation. It proved the feasibility of SSVEP-BCI controlled soft robotic glove in post-stroke hand function rehabilitation.

Arithmetic Optimization with RetinaNet Model for Motor Imagery Classification on Brain Computer Interface

Brain Computer Interface (BCI) technology commonly used to enable communication for the person with movement disability. It allows the person to communicate and control assistive robots by the use of electroencephalogram (EEG) or other brain signals. Though several approaches have been available in the literature for learning EEG signal feature, the deep learning (DL) models need to further explore for generating novel representation of EEG features and accomplish enhanced outcomes for MI classification. With this motivation, this study designs an arithmetic optimization with RetinaNet based deep learning model for MI classification (AORNDL-MIC) technique on BCIs. The proposed AORNDL-MIC technique initially exploits Multiscale Principal Component Analysis (MSPCA) approach for the EEG signal denoising and Continuous Wavelet Transform (CWT) is exploited for the transformation of 1D-EEG signal into 2D time-frequency amplitude representation, which enables to utilize the DL model via transfer learning approach. In addition, the DL based RetinaNet is applied for extracting of feature vectors from the EEG signal which are then classified with the help of ID3 classifier. In order to optimize the classification efficiency of the AORNDL-MIC technique, arithmetical optimization algorithm (AOA) is employed for hyperparameter tuning of the RetinaNet. The experimental analysis of the AORNDL-MIC algorithm on the benchmark data sets reported its promising performance over the recent state of art methodologies.

Intention Detection Strategies for Robotic Upper-Limb Orthoses: A Scoping Review Considering Usability, Daily Life Application, and User Evaluation

Wearable robotic upper limb orthoses (ULO) are promising tools to assist or enhance the upper-limb function of their users. While the functionality of these devices has continuously increased, the robust and reliable detection of the user's intention to control the available degrees of freedom remains a major challenge and a barrier for acceptance. As the information interface between device and user, the intention detection strategy (IDS) has a crucial impact on the usability of the overall device. Yet, this aspect and the impact it has on the device usability is only rarely evaluated with respect to the context of use of ULO. A scoping literature review was conducted to identify non-invasive IDS applied to ULO that have been evaluated with human participants, with a specific focus on evaluation methods and findings related to functionality and usability and their appropriateness for specific contexts of use in daily life. A total of 93 studies were identified, describing 29 different IDS that are summarized and classified according to a four-level classification scheme. The predominant user input signal associated with the described IDS was electromyography (35.6%), followed by manual triggers such as buttons, touchscreens or joysticks (16.7%), as well as isometric force generated by residual movement in upper-limb segments (15.1%). We identify and discuss the strengths and weaknesses of IDS with respect to specific contexts of use and highlight a trade-off between performance and complexity in selecting an optimal IDS. Investigating evaluation practices to study the usability of IDS, the included studies revealed that, primarily, objective and quantitative usability attributes related to effectiveness or efficiency were assessed. Further, it underlined the lack of a systematic way to determine whether the usability of an IDS is sufficiently high to be appropriate for use in daily life applications. This work highlights the importance of a user- and application-specific selection and evaluation of non-invasive IDS for ULO. For technology developers in the field, it further provides recommendations on the selection process of IDS as well as to the design of corresponding evaluation protocols.

Improving Motor Imagery-Based Brain-Computer Interface Performance Based on Sensory Stimulation Training: An Approach Focused on Poorly Performing Users

The motor imagery (MI)-based brain-computer interface (BCI) is an intuitive interface that provides control over computer applications directly from brain activity. However, it has shown poor performance compared to other BCI systems such as P300 and SSVEP BCI. Thus, this study aimed to improve MI-BCI performance by training participants in MI with the help of sensory inputs from tangible objects (i.e., hard and rough balls), with a focus on poorly performing users. The proposed method is a hybrid of training and imagery, combining motor execution and somatosensory sensation from a ball-type stimulus. Fourteen healthy participants participated in the somatosensory-motor imagery (SMI) experiments (within-subject design) involving EEG data classification with a three-class system (signaling with left hand, right hand, or right foot). In the scenario of controlling a remote robot to move it to the target point, the participants performed MI when faced with a three-way intersection. The SMI condition had a better classification performance than did the MI condition, achieving a 68.88% classification performance averaged over all participants, which was 6.59% larger than that in the MI condition (p < 0.05). In poor performers, the classification performance in SMI was 10.73% larger than in the MI condition (62.18% vs. 51.45%). However, good performers showed a slight performance decrement (0.86%) in the SMI condition compared to the MI condition (80.93% vs. 81.79%). Combining the brain signals from the motor and somatosensory cortex, the proposed hybrid MI-BCI system demonstrated improved classification performance, this phenomenon was predominant in poor performers (eight out of nine subjects). Hybrid MI-BCI systems may significantly contribute to reducing the proportion of BCI-inefficiency users and closing the performance gap with other BCI systems.

Emergence of flexible technology in developing advanced systems for post-stroke rehabilitation: a comprehensive review

OBJECTIVE

Stroke is one of the most common neural disorders, which causes physical disabilities and motor impairments among its survivors. Several technologies have been developed for providing stroke rehabilitation and to assist the survivors in performing their daily life activities. Currently, the use of flexible technology (FT) for stroke rehabilitation systems is on a rise that allows the development of more compact and lightweight wearable systems, which stroke survivors can easily use for long-term activities.

APPROACH

For stroke applications, FT mainly includes the "flexible/stretchable electronics", "e-textile (electronic textile)" and "soft robotics". Thus, a thorough literature review has been performed to report the practical implementation of FT for post-stroke application.

MAIN RESULTS

In this review, the highlights of the advancement of FT in stroke rehabilitation systems are dealt with. Such systems mainly involve the "biosignal acquisition unit", "rehabilitation devices" and "assistive systems". In terms of biosignals acquisition, electroencephalography (EEG) and electromyography (EMG) are comprehensively described. For rehabilitation/assistive systems, the application of functional electrical stimulation (FES) and robotics units (exoskeleton, orthosis, etc.) have been explained.

SIGNIFICANCE

This is the first review article that compiles the different studies regarding flexible technology based post-stroke systems. Furthermore, the technological advantages, limitations, and possible future implications are also discussed to help improve and advance the flexible systems for the betterment of the stroke community.

Physiologic signaling and viability of the muscle cuff regenerative peripheral nerve interface (MC-RPNI) for intact peripheral nerves

Background. Robotic exoskeleton devices have become a promising modality for restoration of extremity function in individuals with limb loss or functional weakness. However, there exists no consistent or reliable way to record efferent motor action potentials from intact peripheral nerves to control device movement. Peripheral nerve motor action potentials are similar in amplitude to that of background noise, producing an unfavorable signal-to-noise ratio (SNR) that makes these signals difficult to detect and interpret. To address this issue, we have developed the muscle cuff regenerative peripheral nerve interface (MC-RPNI), a construct consisting of a free skeletal muscle graft wrapped circumferentially around an intact peripheral nerve. Over time, the muscle graft regenerates, and the intact nerve undergoes collateral axonal sprouting to reinnervate the muscle. The MC-RPNI amplifies efferent motor action potentials by several magnitudes, thereby increasing the SNR, allowing for higher fidelity signaling and detection of motor intention. The goal of this study was to characterize the signaling capabilities and viability of the MC-RPNI over time.Methods. Thirty-seven rats were randomly assigned to one of five experimental groups (Groups A-E). For MC-RPNI animals, their contralateral extensor digitorum longus (EDL) muscle was harvested and trimmed to either 8 mm (Group A) or 13 mm (Group B) in length, wrapped circumferentially around the intact ipsilateral common peroneal (CP) nerve, secured, and allowed to heal for 3 months. Additionally, one 8 mm (Group C) and one 13 mm (Group D) length group had an epineurial window created in the CP nerve immediately preceding MC-RPNI creation. Group E consisted of sham surgery animals. At 3 months, electrophysiologic analyses were conducted to determine the signaling capabilities of the MC-RPNI. Additionally, electromyography and isometric force analyses were performed on the CP-innervated EDL to determine the effects of the MC-RPNI on end organ function. Following evaluation, the CP nerve, MC-RPNI, and ipsilateral EDL muscle were harvested for histomorphometric analysis.Results. Study endpoint analysis was performed at 3 months post-surgery. All rats displayed visible muscle contractions in both the MC-RPNI and EDL following proximal CP nerve stimulation. Compound muscle action potentials were recorded from the MC-RPNI following proximal CP nerve stimulation and ranged from 3.67 ± 0.58 mV to 6.04 ± 1.01 mV, providing efferent motor action potential amplification of 10-20 times that of a normal physiologic nerve action potential. Maximum tetanic isometric force (F_o) testing of the distally-innervated EDL muscle in MC-RPNI groups producedF_o(2341 ± 114 mN-2832 ± 102 mN) similar to controls (2497 ± 122 mN), thus demonstrating that creation of MC-RPNIs did not adversely impact the function of the distally-innervated EDL muscle. Overall, comparison between all MC-RPNI sub-groups did not reveal any statistically significant differences in signaling capabilities or negative effects on distal-innervated muscle function as compared to the control group.Conclusions. MC-RPNIs have the capability to provide efferent motor action potential amplification from intact nerves without adversely impacting distal muscle function. Neither the size of the muscle graft nor the presence of an epineurial window in the nerve had any significant impact on the ability of the MC-RPNI to amplify efferent motor action potentials from intact nerves. These results support the potential for the MC-RPNI to serve as a biologic nerve interface to control advanced exoskeleton devices.

Decoding Finger Tapping With the Affected Hand in Chronic Stroke Patients During Motor Imagery and Execution

In stroke rehabilitation, motor imagery based on a brain-computer interface is an extremely useful method to control an external device and utilize neurofeedback. Many studies have reported on the classification performance of motor imagery to decode individual fingers in stroke patients compared with healthy controls. However, classification performance for a given limb is still low because the differences between patients owing to brain reorganization after stroke are not considered. We used electroencephalography signals from eleven healthy controls and eleven stroke patients in this study. The subjects performed a finger tapping task during motor execution, and motor imagery was performed with the dominant and affected hands in the healthy controls and stroke patients, respectively. All fingers except for the thumb were classified using the proposed framework based on a voting module. The averaged four-class accuracies during motor execution and motor imagery were 53.16 ± 8.42% and 46.94 ± 5.99% for the healthy controls and 53.17 ± 14.09% and 66.00 ± 14.96% for the stroke patients, respectively. Importantly, the classification accuracies in the stroke patients were statistically higher than those in healthy controls during motor imagery. However, there was no significant difference between the accuracies of motor execution and motor imagery. These findings show the potential for high classification performance for a given limb during motor imagery in stroke patients. These results can also provide insights into controlling an external device on the basis of a brain-computer interface.

Brain-Computer Interface Coupled to a Robotic Hand Orthosis for Stroke Patients' Neurorehabilitation: A Crossover Feasibility Study

Brain-Computer Interfaces (BCI) coupled to robotic assistive devices have shown promise for the rehabilitation of stroke patients. However, little has been reported that compares the clinical and physiological effects of a BCI intervention for upper limb stroke rehabilitation with those of conventional therapy. This study assesses the feasibility of an intervention with a BCI based on electroencephalography (EEG) coupled to a robotic hand orthosis for upper limb stroke rehabilitation and compares its outcomes to conventional therapy. Seven subacute and three chronic stroke patients (M = 59.9 ± 12.8) with severe upper limb impairment were recruited in a crossover feasibility study to receive 1 month of BCI therapy and 1 month of conventional therapy in random order. The outcome measures were comprised of: Fugl-Meyer Assessment of the Upper Extremity (FMA-UE), Action Research Arm Test (ARAT), motor evoked potentials elicited by transcranial magnetic stimulation (TMS), hand dynamometry, and EEG. Additionally, BCI performance and user experience were measured. All measurements were acquired before and after each intervention. FMA-UE and ARAT after BCI (23.1 ± 16; 8.4 ± 10) and after conventional therapy (21.9 ± 15; 8.7 ± 11) were significantly higher (p < 0.017) compared to baseline (17.5 ± 15; 4.3 ± 6) but were similar between therapies (p > 0.017). Via TMS, corticospinal tract integrity could be assessed in the affected hemisphere of three patients at baseline, in five after BCI, and four after conventional therapy. While no significant difference (p > 0.05) was found in patients’ affected hand strength, it was higher after the BCI therapy. EEG cortical activations were significantly higher over motor and non-motor regions after both therapies (p < 0.017). System performance increased across BCI sessions, from 54 (50, 70%) to 72% (56, 83%). Patients reported moderate mental workloads and excellent usability with the BCI. Outcome measurements implied that a BCI intervention using a robotic hand orthosis as feedback has the potential to elicit neuroplasticity-related mechanisms, similar to those observed during conventional therapy, even in a group of severely impaired stroke patients. Therefore, the proposed BCI system could be a suitable therapy option and will be further assessed in clinical trials.

Brain-Computer Interfaces in Neurorecovery and Neurorehabilitation

Recent advances in brain-computer interface technology to restore and rehabilitate neurologic function aim to enable persons with disabling neurologic conditions to communicate, interact with the environment, and achieve other key activities of daily living and personal goals. Here we evaluate the principles, benefits, challenges, and future directions of brain-computer interfaces in the context of neurorehabilitation. We then explore the clinical translation of these technologies and propose an approach to facilitate implementation of brain-computer interfaces for persons with neurologic disease.

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.

Research on Recognition of Motor Imagination Based on Connectivity Features of Brain Functional Network

Feature extraction is essential for classifying different motor imagery (MI) tasks in a brain-computer interface. To improve classification accuracy, we propose a novel feature extraction method in which the connectivity increment rate (CIR) of the brain function network (BFN) is extracted. First, the BFN is constructed on the basis of the threshold matrix of the Pearson correlation coefficient of the mu rhythm among the channels. In addition, a weighted BFN is constructed and expressed by the sum of the existing edge weights to characterize the cerebral cortex activation degree in different movement patterns. Then, on the basis of the topological structures of seven mental tasks, three regional networks centered on the C3, C4, and Cz channels are constructed, which are consistent with correspondence between limb movement patterns and cerebral cortex in neurophysiology. Furthermore, the CIR of each regional functional network is calculated to form three-dimensional vectors. Finally, we use the support vector machine to learn a classifier for multiclass MI tasks. Experimental results show a significant improvement and demonstrate the success of the extracted feature CIR in dealing with MI classification. Specifically, the average classification performance reaches 88.67% which is higher than other competing methods, indicating that the extracted CIR is effective for MI classification.

Review on motor imagery based BCI systems for upper limb post-stroke neurorehabilitation: From designing to application

Strokes are a growing cause of mortality and many stroke survivors suffer from motor impairment as well as other types of disabilities in their daily life activities. To treat these sequelae, motor imagery (MI) based brain-computer interface (BCI) systems have shown potential to serve as an effective neurorehabilitation tool for post-stroke rehabilitation therapy. In this review, different MI-BCI based strategies, including "Functional Electric Stimulation, Robotics Assistance and Hybrid Virtual Reality based Models," have been comprehensively reported for upper-limb neurorehabilitation. Each of these approaches have been presented to illustrate the in-depth advantages and challenges of the respective BCI systems. Additionally, the current state-of-the-art and main concerns regarding BCI based post-stroke neurorehabilitation devices have also been discussed. Finally, recommendations for future developments have been proposed while discussing the BCI neurorehabilitation systems.

Brain-computer interface performance analysis of monozygotic twins with discordant hand dominance: A case study

Brain-computer interfaces (BCI) decode user's intentions to control external devices. However, performance variations across individuals have limited their use to laboratory environments. Handedness could contribute to these variations, especially when motor imagery (MI) tasks are used for BCI control. To further understand how handedness affects BCI control, performance differences between two monozygotic twins were analysed during offline movement and MI tasks, and while twins controlled a BCI using right-hand MI. Quantitative electroencephalography (qEEG), brain structures' volumes, and neuropsychological tests were assessed to evaluate physiological, anatomical and psychological relationships with BCI performance. Results showed that both twins had good motor imagery and attention abilities, similar volumes on most subcortical brain structures, more pronounced event-related desynchronization elicited by the twin performing non-dominant MI, and that this twin also obtained significant higher performances with the BCI. Linear regression analysis implied a strong association between twins' BCI performance, and more pronounced cortical activations in the contralateral hemisphere relative to hand MI. Therefore, it is possible that BCI performance was related with the ability of each twin to elicit cortical activations during hand MI, and less associated with subcortical brain structures' volumes and neuropsychological tests.

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.

Direct comparison of supervised and semi-supervised retraining approaches for co-adaptive BCIs

For Brain-Computer interfaces (BCIs), system calibration is a lengthy but necessary process for successful operation. Co-adaptive BCIs aim to shorten training and imply positive motivation to users by presenting feedback already at early stages: After just 5 min of gathering calibration data, the systems are able to provide feedback and engage users in a mutual learning process. In this work, we investigate whether the retraining stage of co-adaptive BCIs can be adapted to a semi-supervised concept, where only a small amount of labeled data is available and all additional data needs to be labeled by the BCI itself. The aim of the current work was to evaluate whether a semi-supervised co-adaptive BCI could successfully compete with a supervised co-adaptive BCI model. In a supporting two-class (190 trials per condition) BCI study based on motor imagery tasks, we evaluated both approaches in two separate groups of 10 participants online, while we simulated the other approach in each group offline. Our results indicate that despite the lack of true labeled data, the semi-supervised driven BCI did not perform significantly worse (p > 0.05) than the supervised counterpart. We believe that these findings contribute to developing BCIs for long-term use, where continuous adaptation becomes imperative for maintaining meaningful BCI performance.

Graphical abstract

Design of smart EEG cap

BACKGROUND AND OBJECTIVE

Brain machine interface (BMI) is a system which communicates the brain with the external machines. In general, an electroencephalograph (EEG) machine has to be used to monitor multi-channel brain responses to improve the BMI performance. However, the bulky size of the EEG machine and applying conductive gels in EEG electrodes also cause the inconvenience of daily life applications. How to select the relevant EEG channel and remove irrelevant channels is important and useful for the development of BMIs.

METHODS

In this research, a smart EEG cap was proposed to improve the above issues. Different from the conventional EEG machine, the proposed smart EEG cap contain a spatial filtering circuit to enhance EEG features in local area, and it could also select the relevant EEG channel automatically. Moreover, the novel dry active electrodes were also designed to acquire EEG without conductive gels in the hairy skin of the head, to improve the convenience in use.

RESULTS

Finally, the proposed smart EEG cap was applied in motion imagery-based BMI and several experiments were tested to valid the system performance. The proposed smart EEG cap could effectively enhance EEG features and select relevant EEG channel, and the information transfer rate of BMI was about 6.06 bits/min.

CONCLUSIONS

The proposed smart EEG cap has advantages of measuring EEG without conductive gels and wireless transmission to effectively improve the convenience of use, and reduce the limitation of activity in daily life. In the future, it might be widely applied in other BMI applications.

Longitudinal Analysis of Stroke Patients' Brain Rhythms during an Intervention with a Brain-Computer Interface

Stroke is a leading cause of motor disability worldwide. Upper limb rehabilitation is particularly challenging since approximately 35% of patients recover significant hand function after 6 months of the stroke's onset. Therefore, new therapies, especially those based on brain-computer interfaces (BCI) and robotic assistive devices, are currently under research. Electroencephalography (EEG) acquired brain rhythms in alpha and beta bands, during motor tasks, such as motor imagery/intention (MI), could provide insight of motor-related neural plasticity occurring during a BCI intervention. Hence, a longitudinal analysis of subacute stroke patients' brain rhythms during a BCI coupled to robotic device intervention was performed in this study. Data of 9 stroke patients were acquired across 12 sessions of the BCI intervention. Alpha and beta event-related desynchronization/synchronization (ERD/ERS) trends across sessions and their association with time since stroke onset and clinical upper extremity recovery were analyzed, using correlation and linear stepwise regression, respectively. More EEG channels presented significant ERD/ERS trends across sessions related with time since stroke onset, in beta, compared to alpha. Linear models implied a moderate relationship between alpha rhythms in frontal, temporal, and parietal areas with upper limb motor recovery and suggested a strong association between beta activity in frontal, central, and parietal regions with upper limb motor recovery. Higher association of beta with both time since stroke onset and upper limb motor recovery could be explained by beta relation with closed-loop communication between the sensorimotor cortex and the paralyzed upper limb, and alpha being probably more associated with motor learning mechanisms. The association between upper limb motor recovery and beta activations reinforces the hypothesis that broader regions of the cortex activate during movement tasks as a compensatory mechanism in stroke patients with severe motor impairment. Therefore, EEG across BCI interventions could provide valuable information for prognosis and BCI cortical activity targets.

The Effects of Combined Low Frequency Repetitive Transcranial Magnetic Stimulation and Motor Imagery on Upper Extremity Motor Recovery Following Stroke

Objective: To investigate the effects of low frequency transcranial magnetic stimulation (LF-rTMS) combined with motor imagery (MI) on upper limb motor function during stroke rehabilitation.

Background: Hemiplegic upper extremity activity obstacle is a common movement disorder after stroke. Compared with a single intervention, sequential protocol or combination of several techniques has been proven to be better for alleviating motor function disorder. Non-invasive neuromodulation techniques such as repetitive transcranial magnetic stimulation (rTMS) and motor imagery (MI) have been verified to augment the efficacy of rehabilitation.

Methods:Participants were randomly assigned to 2 intervention cohorts: (1) experimental group (rTMS+MI group) was applied at 1 Hz rTMS over the primary motor cortex of the contralesional hemisphere combined with audio-based MI; (2) control group (rTMS group) received the same therapeutic parameters of rTMS combined with audiotape-led relaxation. LF-rTMS protocol was conducted in 10 sessions over 2 weeks for 30 min. Functional measurements include Wolf Motor Function Test (WMFT), the Fugl-Meyer Assessment Upper Extremity (UE-FMA) subscore, the Box and Block Test (BBT), and the Modified Barthel index (MBI) were conducted at baseline, the second week (week 2) and the fourth week (week 4).

Results: All assessments of upper limb function improved in both groups at weeks 2 and 4. In particular, significant differences were observed between two groups at end-intervention and after intervention (p < 0.05). In these findings, we saw greater changes of WMFT (p < 0.01), UE-FMA (p < 0.01), BBT (p < 0.01), and MBI (p < 0.001) scores in the experimental group.

Conclusions: LF-rTMS combined with MI had a positive effect on motor function of upper limb and can be used for the rehabilitation of upper extremity motor recovery in stroke patients.

Portable brain-computer interface based on novel convolutional neural network

Electroencephalography (EEG) is a powerful, noninvasive tool that provides a high temporal resolution to directly reflect brain activities. Conventional electrodes require skin preparation and the use of conductive gels, while subjects must wear uncomfortable EEG hats. These procedures usually create a challenge for subjects. In the present study, we propose a portable EEG signal acquisition system. This study consists of two main parts: 1) A novel, portable dry-electrode and wireless brain-computer interface is designed. The EEG signal acquisition board is based on 24 bit, analog-to-digital converters chip and wireless microprocessor unit. The wireless portable brain computer interface device acquires an EEG signal comfortably, and the EEG signals are transmitted to a personal computer via Bluetooth. 2) A convolutional neural network (CNN) classification algorithm is implemented to classify the motor imagery (MI) experiment using novel feature 3-dimension input. The time dimension was reshaped to represent the first and second dimension, and the frequency band was used as the third dimension. Specifically, frequency domain representations of EEG signals obtained via wavelet package decomposition (WPD) are obtained to train CNN. The classification performance in terms of the value of kappa is 0.564 for the proposed method. The t-test results show that the performance improvement of CNN over other selected state-of-the-art methods is statistically significant. Our results show that the proposed design is reliable in measuring EEG signals, and the 3D CNN provides better classification performance than other method for MI experiments.

Feature selection using regularized neighbourhood component analysis to enhance the classification performance of motor imagery signals

In motor imagery (MI) based brain-computer interface (BCI) signal analysis, mu and beta rhythms of electroencephalograms (EEGs) are widely investigated due to their high temporal resolution and capability to define the different movement-related mental tasks separately. However, due to the high dimensions and subject-specific behaviour of EEG features, there is a need for a suitable feature selection algorithm that can select the optimal features to give the best classification performance along with increased computational efficiency. The present study proposes a feature selection algorithm based on neighbourhood component analysis (NCA) with modification of the regularization parameter. In the experiment, time, frequency, and phase features of the EEG are extracted using a dual-tree complex wavelet transform (DTCWT). Afterwards, the proposed algorithm selects the most significant EEG features, and using these selected features, a support vector machine (SVM) classifier performs the classification of MI signals. The proposed algorithm has been validated experimentally on two public BCI datasets (BCI Competition II Dataset III and BCI Competition IV Dataset 2b). The classification performance of the algorithm is quantified by the average accuracy and kappa coefficient, whose values are 80.7% and 0.615 respectively. The performance of the proposed algorithm is compared with standard feature selection methods based on Genetic Algorithm (GA), Principal Component Analysis (PCA), and ReliefF and performs better than these methods. Further, the proposed algorithm selects the lowest number of features and results in increased computational efficiency, which makes it a promising feature selection tool for an MI-based BCI system.