Motor Imagery Research Articles

Towards formal models of inhibitory mechanisms involved in motor imagery: a commentary on Bach et al. (2022).

A vast body of research suggests that the primary motor cortex is involved in motor imagery. This raises the issue of inhibition: how is it possible for motor imagery not to lead to motor execution? Bach et al. (Psychol Res Psychol Forschung. 10.1007/s00426-022-01773-w, 2022, this issue) suggest that the motor execution threshold may be "upregulated" during motor imagery to prevent execution. Alternatively, it has been proposed that, in parallel to excitatory mechanisms, inhibitory mechanisms may be actively suppressing motor output during motor imagery. These theories are verbal in nature, with well-known limitations. Here, we describe a toy-model of the inhibitory mechanisms thought to be at play during motor imagery to start disentangling predictions from competing hypotheses.

Pseudo-online framework for BCI evaluation: a MOABB perspective using various MI and SSVEP datasets

Objective. BCI (Brain–Computer Interfaces) operate in three modes: online, offline, and pseudo-online. In online mode, real-time EEG data is constantly analyzed. In offline mode, the signal is acquired and processed afterwards. The pseudo-online mode processes collected data as if they were received in real-time. The main difference is that the offline mode often analyzes the whole data, while the online and pseudo-online modes only analyze data in short time windows. Offline processing tends to be more accurate, while online analysis is better for therapeutic applications. Pseudo-online implementation approximates online processing without real-time constraints. Many BCI studies being offline introduce biases compared to real-life scenarios, impacting classification algorithm performance. Approach. The objective of this research paper is therefore to extend the current MOABB framework, operating in offline mode, so as to allow a comparison of different algorithms in a pseudo-online setting with the use of a technology based on overlapping sliding windows. To do this will require the introduction of a idle state event in the dataset that takes into account all different possibilities that are not task thinking. To validate the performance of the algorithms we will use the normalized Matthews correlation coefficient and the information transfer rate. Main results. We analyzed the state-of-the-art algorithms of the last 15 years over several motor imagery and steady state visually evoked potential multi-subjects datasets, showing the differences between the two approaches from a statistical point of view. Significance. The ability to analyze the performance of different algorithms in offline and pseudo-online modes will allow the BCI community to obtain more accurate and comprehensive reports regarding the performance of classification algorithms.

The effects of internal representations on performance and fluidity in a motor task.

Individuals can differ in the mode in which they experience conscious thought. These differences in visualisation and verbalisation can also be evident during motor control. The Internal Representation Questionnaire (IRQ) was developed to measure propensity to engage certain types of representations, but its ability to predict motor control and links to reinvestment and motor imagery have not been tested. 159 included participants completed the IRQ, movement specific reinvestment scale (MSRS), and a novel online motor task before and after a period of practice. Results showed that the IRQ Verbal and Orthographic factors were significant predictors of scores on the MSRS. The IRQ factor of Manipulational Representations predicted motor performance both before and after practice. The fluidity of executed movements were predicted by the IRQ verbalisation factor where higher propensity to verbalise was associated with higher levels of jitter, but only after a period of practice. Results suggest there may be some informative conceptual overlap between internal verbalisations and reinvestment and that the propensity to manipulate internal representations may be predictive of motor performance in new tasks. The IRQ has potential to be a valuable tool for predicting motor performance.

When does imagery require motor resources? A commentary on Bach et al., 2022.

Bach, Frank, and Kunde introduce a hypothesis that encompasses two main claims: (1) motor imagery relies primarily on representations of the perceptual effects of actions, and (2) the engagement of motor resources provides access to the specific timing, kinematic or internal bodily state that characterize an action. In this commentary, I argue that the first claim is compelling and suggest some alternatives to the second one.

Bilateral vs unilateral motor imagery training: effects on motor execution performance and ERD

Bilateral movement has been reported to enhance actual motor performance more than unilateral movement and increase motor cortex activation more than unilateral movement. We hypothesized that bilateral motor imagery would result in greater improvements in event-related desynchronization (ERD) amplitude and ball rotation performance than unilateral motor imagery. Forty healthy young adults participated in this study. The mental practice session was performed in the unilateral hand condition (right and left hands) and bilateral hand condition for four blocks. ERD in mental practice was calculated using electroencephalography (EEG). The ball rotations were compared between the pre-and post-tests of mental practice. The results showed a greater improvement in actual motor performance with unilateral motor imagery than with bilateral motor imagery. ERD analysis showed no significant differences in multiple comparisons. These results did not support this hypothesis. Nonetheless, the present study showed that unilateral movements resulted in greater performance gains than bilateral movements, suggesting that bilateral motor imagery may have additional control processes similar to actual movements.

Being in Virtual Reality and Its Influence on Brain Health-An Overview of Benefits, Limitations and Prospects.

Dynamic technological development and its enormous impact on modern societies are posing new challenges for 21st-century neuroscience. A special place is occupied by technologies based on virtual reality (VR). VR tools have already played a significant role in both basic and clinical neuroscience due to their high accuracy, sensitivity and specificity and, above all, high ecological value. Being in a digital world affects the functioning of the body as a whole and its individual systems. The data obtained so far, both from experimental and modeling studies, as well as (clinical) observations, indicate their great and promising potential, but apart from the benefits, there are also losses and negative consequences for users. This review was conducted according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework across electronic databases (such as Web of Science Core Collection; PubMed; and Scopus, Taylor & Francis Online and Wiley Online Library) to identify beneficial effects and applications, as well as adverse impacts, especially on brain health in human neuroscience. More than half of these articles were published within the last five years and represent state-of-the-art approaches and results (e.g., 54.7% in Web of Sciences and 63.4% in PubMed), with review papers accounting for approximately 16%. The results show that in addition to proposed novel devices and systems, various methods or procedures for testing, validation and standardization are presented (about 1% of articles). Also included are virtual developers and experts, (bio)(neuro)informatics specialists, neuroscientists and medical professionals. VR environments allow for expanding the field of research on perception and cognitive and motor imagery, both in healthy and patient populations. In this context, research on neuroplasticity phenomena, including mirror neuron networks and the effects of applied virtual (mirror) tasks and training, is of interest in virtual prevention and neurogeriatrics, especially in neurotherapy and neurorehabilitation in basic/clinical and digital neuroscience.

Empowering EEG motor imagery classification with deep transfer learning approach

AbstractThe brain‐computer interface (BCI) enables individuals with impairments to interact with the real world without relying on the neuromuscular pathway. BCI leverages artificial intelligence (AI) models for control. It can capture brain activity patterns associated with mental processes and convert them into commands for actuators. One promising application of BCI is in rehabilitation centres. When compared to traditional methods integrated with machine learning (ML) approaches that were initially explored in the past decade, there is a relatively limited number of studies utilizing deep learning (DL) approaches in BCI applications. A novel approach has been developed for the automatic recognition of motor imagery (MI) tasks. This article introduces the improved sparrow search algorithm with deep transfer learning‐based EEG motor imagery classification (ISSADTL‐EEGMIC) algorithm for BCIs. The presented ISSADTL‐EEGMIC algorithm primarily focuses on the automated classification of motor imagery tasks. To achieve this, the ISSADTL‐EEGMIC method first preprocesses EEG signals using the wavelet packet decomposition (WPD) technique. Additionally, it employs the neural architecture search network (NASNet) technique for feature extraction. Moreover, the ISSADTL‐EEGMIC model performs the classification process using the stacked sparse autoencoder (SSAE) model. Furthermore, hyperparameter optimization of the SSAE model is performed using the ISSA technique, which helps achieve maximum classification performance. The results from the simulation of the ISSADTL‐EEGMIC algorithm have been examined using two benchmark datasets. The experimental findings suggest that it outperforms recent approaches in terms of performance.

Perceiving and Mentally Rotating Real and Artificial Hands

ABSTRACT Introduction In a hand laterality judgment task, participants determine whether rotated images depict a left or a right hand. It is believed that people use motor imagery (imagining their own body moving) to complete this task. This is evidenced by a biomechanical constraints effect (BCE), whereby people take longer to respond to hands shown at biologically awkward angles. It is unknown whether this extends to artificial hands. This study investigated whether prosthetic hands are processed differently when mentally manipulated, potentially due to their perceived eeriness. Materials and Methods In two online studies, participants completed a hand laterality judgment task containing real and artificial hands (realistic and mechanical prosthetics). Results All three hand types produced a BCE, evidencing motor imagery, although this was weaker in mechanical hands. Reaction time and slope (effect of angular rotation on reaction time) also varied between the hand types. Conclusions Our findings indicate that people use motor imagery to process artificial hands, although possible differences in processing between the hands should be followed up. Clinical Relevance Hand laterality judgment tasks could be used to further explore differences in how people process real and artificial hands. Future research might incorporate these tasks with users of prosthetic hands.

Aggregating intrinsic information to enhance BCI performance through federated learning

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

Revealing brain connectivity: graph embeddings for EEG representation learning and comparative analysis of structural and functional connectivity.

This study employs deep learning techniques to present a compelling approach for modeling brain connectivity in EEG motor imagery classification through graph embedding. The compelling aspect of this study lies in its combination of graph embedding, deep learning, and different brain connectivity types, which not only enhances classification accuracy but also enriches the understanding of brain function. The approach yields high accuracy, providing valuable insights into brain connections and has potential applications in understanding neurological conditions. The proposed models consist of two distinct graph-based convolutional neural networks, each leveraging different types of brain connectivities to enhance classification performance and gain a deeper understanding of brain connections. The first model, Adjacency-based Convolutional Neural Network Model (Adj-CNNM), utilizes a graph representation based on structural brain connectivity to embed spatial information, distinguishing it from prior spatial filtering approaches dependent on subjects and tasks. Extensive tests on a benchmark dataset-IV-2a demonstrate that an accuracy of 72.77% is achieved by the Adj-CNNM, surpassing baseline and state-of-the-art methods. The second model, Phase Locking Value Convolutional Neural Network Model (PLV-CNNM), incorporates functional connectivity to overcome structural connectivity limitations and identifies connections between distinct brain regions. The PLV-CNNM achieves an overall accuracy of 75.10% across the 1-51 Hz frequency range. In the preferred 8-30 Hz frequency band, known for motor imagery data classification (including α, μ, and β waves), individual accuracies of 91.9%, 90.2%, and 85.8% are attained for α, μ, and β, respectively. Moreover, the model performs admirably with 84.3% accuracy when considering the entire 8-30 Hz band. Notably, the PLV-CNNM reveals robust connections between different brain regions during motor imagery tasks, including the frontal and central cortex and the central and parietal cortex. These findings provide valuable insights into brain connectivity patterns, enriching the comprehension of brain function. Additionally, the study offers a comprehensive comparative analysis of diverse brain connectivity modeling methods.

Avatar embodiment prior to motor imagery training in VR does not affect the induced event-related desynchronization: a pilot study

Motor-imagery brain-computer interfaces (MI-BCIs) have the potential to improve motor function in individuals with neurological disorders. Their effectiveness relies on patients’ ability to generate reliable MI-related electroencephalography (EEG) patterns, which can be influenced by the quality of neurofeedback. Virtual Reality (VR) has emerged as a promising tool for enhancing proprioceptive feedback due to its ability to induce a sense of embodiment (SoE), where individuals perceive a virtual body as their own. Although prior research has highlighted the importance of SoE in enhancing MI skills and BCI performance, to date, no study has successfully isolated nor manipulated the SoE in VR before MI training, creating a gap in our understanding of the precise role of the priming effect of embodiment in MI-BCIs. In this study, we aimed to examine whether the virtual SoE when induced, as priming of avatar embodiment, and assessed before MI training, could enhance MI-induced EEG patterns. To achieve this, we divided 26 healthy participants into two groups: the embodied group, which experienced SoE with an avatar before undergoing VR-based MI training, and the non-embodied group, which underwent the same MI training without a prior embodiment phase, serving as a control. We analyzed subjective measures of embodiment, the event-related desynchronization (ERD) power of the sensorimotor rhythms, lateralization of ERD, and offline classification BCI accuracy. Although the embodiment phase effectively induced SoE in the embodied group, both groups exhibited similar MI-induced ERD patterns and BCI classification accuracy. This suggests that the induction of SoE prior to MI training may not significantly influence the training outcomes. Instead, it appears that the integration of embodied VR feedback during MI training itself is sufficient to induce appropriate ERD, as evidenced by previous research.

Subject-independent meta-learning framework towards optimal training of EEG-based classifiers

Advances in deep learning have shown great promise towards the application of performing high-accuracy Electroencephalography (EEG) signal classification in a variety of tasks. However, many EEG-based datasets are often plagued by the issue of high inter-subject signal variability. Robust deep learning models are notoriously difficult to train under such scenarios, often leading to subpar or widely varying performance across subjects under the leave-one-subject-out paradigm. Recently, the model agnostic meta-learning framework was introduced as a way to increase the model’s ability to generalize towards new tasks. While the original framework focused on task-based meta-learning, this research aims to show that the meta-learning methodology can be modified towards subject-based signal classification while maintaining the same task objectives and achieve state-of-the-art performance. Namely, we propose the novel implementation of a few/zero-shot subject-independent meta-learning framework towards multi-class inner speech and binary class motor imagery classification. Compared to current subject-adaptive methods which utilize large number of labels from the target, the proposed framework shows its effectiveness in training zero-calibration and few-shot models for subject-independent EEG classification. The proposed few/zero-shot subject-independent meta-learning mechanism performs well on both small and large datasets and achieves robust, generalized performance across subjects. The results obtained shows a significant improvement over the current state-of-the-art, with the binary class motor imagery achieving 88.70% and the accuracy of multi-class inner speech achieving an average of 31.15%. Codes will be made available to public upon publication.

Multiclass classification of motor imagery tasks based on multi-branch convolutional neural network and temporal convolutional network model.

Motor imagery (MI) is a cognitive process wherein an individual mentally rehearses a specific movement without physically executing it. Recently, MI-based brain-computer interface (BCI) has attracted widespread attention. However, accurate decoding of MI and understanding of neural mechanisms still face huge challenges. These seriously hinder the clinical application and development of BCI systems based on MI. Thus, it is very necessary to develop new methods to decode MI tasks. In this work, we propose a multi-branch convolutional neural network (MBCNN) with a temporal convolutional network (TCN), an end-to-end deep learning framework to decode multi-class MI tasks. We first used MBCNN to capture the MI electroencephalography signals information on temporal and spectral domains through different convolutional kernels. Then, we introduce TCN to extract more discriminative features. The within-subject cross-session strategy is used to validate the classification performance on the dataset of BCI Competition IV-2a. The results showed that we achieved 75.08% average accuracy for 4-class MI task classification, outperforming several state-of-the-art approaches. The proposed MBCNN-TCN-Net framework successfully captures discriminative features and decodes MI tasks effectively, improving the performance of MI-BCIs. Our findings could provide significant potential for improving the clinical application and development of MI-based BCI systems.

Brain–Computer Interface Using Functional Near-Infrared Spectroscopy for Post-Stroke Motor Rehabilitation: Case Series

Introduction. Non-invasive brain–computer interfaces (BCIs) enable feedback motor imagery [MI] training in neurological patients to support their motor rehabilitation. Nowadays, the use of BCIs based on functional near-infrared spectroscopy (fNIRS) for motor rehabilitation is yet to be investigated.
 Objective: To evaluate the potential fNIRS BCI use in hand MI training for comprehensive post-stroke rehabilitation.
 Materials and methods. This pilot study included clinically stable patients with mild-to-moderate post-stroke hand paresis. In addition to the standard rehabilitation, the patients underwent 10 nine-minute MI fNIRS BCI training sessions. To evaluate the quality of fNIRS BCI control, we assessed the percentage of time during which the classifier accurately detected patient's mental state. We scored the hand function using the Action Research Arm Test (ARAT) and the Fugl-Meyer Assessment (FMA).
 Results. The study included 5 patients at 1 day to 12 months of stroke. All the participants completed the study. All study participants achieved BCI control rates higher than random (41–68%). While three patients demonstrated the clinically significant improvements in their ARAT scores, one of them also showed an improvement in the FMA score. All the participants reported experiencing drowsiness during training.
 Conclusions. Post-stroke patients can operate the fNIRS BCI system under investigation. We suggest adjusting the feedback system, extending the duration of training, and incorporating functional electromyostimulation to enhance training effectiveness.

A coarse-to-fine adaptive spatial–temporal graph convolution network with residuals for motor imagery decoding from the same limb

In the field of Brain Computer Interface (BCI) technology, Motor Imagery (MI) plays an important role as a paradigm. One of the primary focuses of this research area lies in exploring the MI of various upper limbs. Decoding MI signals from distinct joints within the same limb poses more intricate challenges in comparison to decoding MI signals originating from different upper limbs. In order to explore more efficient decoding methods, we propose a novel coarse-to-fine classification approach to investigate categorical decoding across three tasks, namely ‘rest’, ‘hand’, and ‘elbow’. This approach consists of two classification stages performed from coarse to fine. In the coarse classification stage, in order to capture the features of both resting state and the moving state in the temporal domain, the EEGNet network with temporal domain convolution is used to extract temporal domain features and classify the original samples into categories of ‘rest’ and ‘move’ (‘hand’, ‘elbow’). In the fine classification stage, the samples of ‘move’ category are segmented by time to form a graph sequence. Then, an adaptive spatial–temporal graph convolutional network with residuals is utilized to extract both temporal and spatial domains’ features from the graph sequence. The proposed algorithm has been validated experimentally on the MI-2 dataset and compared with contemporary methods. Its classification performance is quantified by the average accuracy which achieves a value of 72.21%. Extensive experimental results indicate that the novel coarse-to-fine classification approach is superior to the single classification approach.

Cross-cultural adaptation, reliability and validity of the Greek version of the Movement Imagery Questionnaire-3 (MIQ-3)

Abstract Objectives Motor imagery is widely used to enhance patients’ response to treatment via cognitive and neurophysiological processes. As a result, cross-cultural validation of the Movement Imagery Questionnaire-3 (MIQ-3) in the Greek population was deemed necessary. Methods The cross-cultural adaptation method in Greek was followed for the MIQ-3. It was then administered to 150 participants and its face, construct validity (exploratory factor analysis and known-groups validity), test-retest reliability, and internal consistency were assessed. Results The MIQ-3 demonstrated excellent internal consistency (Cronbach’s α=0.90). The intraclass correlation coefficients (ICC) for test-retest reliability of each factor were low: ICC=0.049−0.293. However, the standard error of the measurement (SEM) data was within acceptable limits (13.5–17.2 % of the grand mean) for all three sub-sections of the MIQ-3. Factor analysis confirmed the three-factor structure of the questionnaire. No differences between male and female participants or those with different levels of athletic involvement (intensity of physical activity and practice level) were identified. Conclusions The MIQ-3 appears to be a valid instrument that can be used to assess motor imagery in a Greek population. It can be uniformly applied to participants of different sexes and athletic involvement. Its reliability, though, requires further research.

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.

Large-Scale Cortical Network Analysis and Classification of MI-BCI Tasks Based on Bayesian Nonnegative Matrix Factorization.

Motor imagery (MI) is a high-level cognitive process that has been widely applied to clinical rehabilitation and brain-computer interfaces (BCIs). However, the decoding of MI tasks still faces challenges, and the neural mechanisms underlying its application are unclear, which seriously hinders the development of MI-based clinical applications and BCIs. Here, we combined EEG source reconstruction and Bayesian nonnegative matrix factorization (NMF) methods to construct large-scale cortical networks of left-hand and right-hand MI tasks. Compared to right-hand MI, the results showed that the significantly increased functional network connectivities (FNCs) mainly located among the visual network (VN), sensorimotor network (SMN), right temporal network, right central executive network, and right parietal network in the left-hand MI at the β (13-30Hz) and all (8-30Hz) frequency bands. For the network properties analysis, we found that the clustering coefficient, global efficiency, and local efficiency were significantly increased and characteristic path length was significantly decreased in left-hand MI compared to right-hand MI at the β and all frequency bands. These network pattern differences indicated that the left-hand MI may need more modulation of multiple large-scale networks (i.e., VN and SMN) mainly located in the right hemisphere. Finally, based on the spatial pattern network of FNC and network properties, we propose a classification model. The proposed model achieves a top classification accuracy of 78.2% in cross-subject two-class MI-BCI tasks. Overall, our findings provide new insights into the neural mechanisms of MI and a potential network biomarker to identify MI-BCI tasks.

Neural correlates of motor imagery and execution in real-world dynamic behavior: evidence for similarities and differences.

A large body of evidence shows that motor imagery and action execution behaviors result from overlapping neural substrates, even in the absence of overt movement during motor imagery. To date it is unclear how neural activations in motor imagery and execution compare for naturalistic whole-body movements, such as walking. Neuroimaging studies have not directly compared imagery and execution during dynamic walking movements. Here we recorded brain activation with mobile EEG during walking compared to during imagery of walking, with mental counting as a control condition. We asked 24 healthy participants to either walk six steps on a path, imagine taking six steps, or mentally count from one to six. We found beta and alpha power modulation during motor imagery resembling action execution patterns; a correspondence not found performing the control task of mental counting. Neural overlap occurred early in the execution and imagery walking actions, suggesting activation of shared action representations. Remarkably, a distinctive walking-related beta rebound occurred both during action execution and imagery at the end of the action suggesting that, like actual walking, motor imagery involves resetting or inhibition of motor processes. However, we also found that motor imagery elicits a distinct pattern of more distributed beta activity, especially at the beginning of the task. These results indicate that motor imagery and execution of naturalistic walking involve shared motor-cognitive activations, but that motor imagery requires additional cortical resources.

Motor Imagery Classification for Asynchronous EEG-Based Brain-Computer Interfaces.

Motor imagery (MI) based brain-computer interfaces (BCIs) enable the direct control of external devices through the imagined movements of various body parts. Unlike previous systems that used fixed-length EEG trials for MI decoding, asynchronous BCIs aim to detect the user's MI without explicit triggers. They are challenging to implement, because the algorithm needs to first distinguish between resting-states and MI trials, and then classify the MI trials into the correct task, all without any triggers. This paper proposes a sliding window prescreening and classification (SWPC) approach for MI-based asynchronous BCIs, which consists of two modules: a prescreening module to screen MI trials out of the resting-state, and a classification module for MI classification. Both modules are trained with supervised learning followed by self-supervised learning, which refines the feature extractors. Within-subject and cross-subject asynchronous MI classifications on four different EEG datasets validated the effectiveness of SWPC, i.e., it always achieved the highest average classification accuracy, and outperformed the best state-of-the-art baseline on each dataset by about 2%.