Joint hybrid recursive feature elimination based channel selection and ResGCN for cross session MI recognition.

In the field of brain-computer interface (BCI) based on motor imagery (MI), multi-channel electroencephalography (EEG) data is commonly utilized for MI task recognition to achieve sensory compensation or precise human-computer interaction. However, individual physiological differences, environmental variations, or redundant information and noise in certain channels can pose challenges and impact the performance of BCI systems. In this study, we introduce a channel selection method utilizing Hybrid-Recursive Feature Elimination (H-RFE) combined with residual graph neural networks for MI recognition. This channel selection method employs a recursive feature elimination strategy and integrates three classification methods, namely random forest, gradient boosting, and logistic regression, as evaluators for adaptive channel selection tailored to specific subjects. To fully exploit the spatiotemporal information of multi-channel EEG, this study employed a graph neural network embedded with residual blocks to achieve precise recognition of motor imagery. We conducted algorithm testing using the SHU dataset and the PhysioNet dataset. Experimental results show that on the SHU dataset, utilizing 73.44% of the total channels, the cross-session MI recognition accuracy is 90.03%. Similarly, in the PhysioNet dataset, using 72.5% of the channel data, the classification result also reaches 93.99%. Compared to traditional strategies such as selecting three specific channels, correlation-based channel selection, mutual information-based channel selection, and adaptive channel selection based on Pearson coefficients and spatial positions, the proposed method improved classification accuracy by 34.64%, 10.8%, 3.25% and 2.88% on the SHU dataset, and by 46.96%, 5.04%, 5.81% and 2.32% on the PhysioNet dataset, respectively.

Differential Hemodynamic Responses to Motor and Tactile Imagery: Insights from Multichannel fNIRS Mapping.

Tactile and motor imagery are crucial components of sensorimotor functioning and cognitive neuroscience research, yet the neural mechanisms of tactile imagery remain underexplored compared to motor imagery. This study employs multichannel functional near-infrared spectroscopy (fNIRS) combined with image reconstruction techniques to investigate the neural hemodynamics associated with tactile (TI) and motor imagery (MI). In a study of 15 healthy participants, we found that MI elicited significantly greater hemodynamic responses (HRs) in the precentral area compared to TI, suggesting the involvement of different cortical areas involved in two different types of sensorimotor mental imagery. Concurrently, the HRs in S1 and parietal areas exhibited comparable patterns in both TI and MI. During MI, both motor and somatosensory areas demonstrated comparable HRs. However, in TI, somatosensory activation was observed to be more pronounced. Our results highlight the distinctive neural profiles of motor versus tactile imagery and indicate fNIRS technique to be sensitive for this. This distinction is significant for fundamental understanding of sensorimotor integration and for developing advanced neurotechnologies, including imagery-based brain-computer interfaces (BCIs) that can differentiate between different types of mental imagery.

An SCA-based classifier for motor imagery EEG classification.

Efficient and accurate multi-class classification of electroencephalogram (EEG) signals poses a significant challenge in the development of motor imagery-based brain-computer interface (MI-BCI). Drawing inspiration from the sine cosine algorithm (SCA), a widely employed swarm intelligence algorithm for optimization problems, we proposed a novel population-based classification algorithm for EEG signals in this article. To fully leverage the characteristics contained in EEG signals, multi-scale sub-signals were constructed in terms of temporal windows and spectral bands simultaneously, and the common spatial pattern (CSP) features were extracted from each sub-signal. Subsequently, we integrated the multi-center optimal vectors mechanism into the classical SCA, resulting in the development of a multi-center SCA (MCSCA) classifier. During the classification stage, the label was assigned to the test trials by evaluating the Euclidean distance between their feature vectors and each optimal vector in MCSCA. Additionally, the weights of feature vectors were exploited to select the sub-signal of specific temporal windows and spectral bands for feature reduction, thereby declining computational effort and eliminating data redundancy. To validate the performance of the MCSCA classifier, we conducted four-class classification experiments using the BCI Competition IV dataset 2a, achieving an average classification accuracy of 71.89%. The experimental results show that the proposed algorithm offers a novel and effective approach for EEG classification.

Analysis of brain network differences in the active, motor imagery, and passive stoke rehabilitation paradigms based on the task-state EEG.

Different movement paradigms have varying effects on stroke rehabilitation, and their mechanisms of action on the brain are not fully understood. This study aims to investigate disparities in brain network and functional connectivity of three movement paradigms (active, motor imagery, passive) on stroke recovery. EEG signals were recorded from 11 S patients (SP) and 13 healthy controls (HC) during fist clenching and opening tasks under the three paradigms. Brain networks were constructed to analyze alterations in brain network connectivity, node strength (NS), clustering coefficients (CC), characteristic path length (CPL), and small-world index(S). Our findings revealed increased activity in the contralateral motor area in SP and higher activity in the ipsilateral motor area in HC. In the beta band, SP exhibited significantly higher CC in motor imagery (MI) than in active and passive tasks. Furthermore, the small world index of SP during MI tasks in the beta band was significantly smaller than in the active and passive tasks. NS in the gamma band for SP during the MI paradigm was significantly higher than in the active and passive paradigms. These findings suggest reorganization within both ipsilateral and contralateral motor areas of stroke patients during MI tasks, providing evidence for neural restructuring. Collectively, these findings contribute to a deeper understanding of task-state brain network changes and the rehabilitative mechanism of MI on motor function.

Transforming Motor Imagery Analysis: A Novel EEG Classification Framework Using AtSiftNet Method.

This paper presents an innovative approach for the Feature Extraction method using Self-Attention, incorporating various Feature Selection techniques known as the AtSiftNet method to enhance the classification performance of motor imaginary activities using electrophotography (EEG) signals. Initially, the EEG signals were sorted and then denoised using multiscale principal component analysis to obtain clean EEG signals. However, we also conducted a non-denoised experiment. Subsequently, the clean EEG signals underwent the Self-Attention feature extraction method to compute the features of each trial (i.e., 350×18). The best 1 or 15 features were then extracted through eight different feature selection techniques. Finally, five different machine learning and neural network classification models were employed to calculate the accuracy, sensitivity, and specificity of this approach. The BCI competition III dataset IV-a was utilized for all experiments, encompassing the datasets of five volunteers who participated in the competition. The experiment findings reveal that the average accuracy of classification is highest among ReliefF (i.e., 99.946%), Mutual Information (i.e., 98.902%), Independent Component Analysis (i.e., 99.62%), and Principal Component Analysis (i.e., 98.884%) for both 1 and 15 best-selected features from each trial. These accuracies were obtained for motor imagery using a Support Vector Machine (SVM) as a classifier. In addition, five-fold validation was performed in this paper to assess the fair performance estimation and robustness of the model. The average accuracy obtained through five-fold validation is 99.89%. The experiments' findings indicate that the suggested framework provides a resilient biomarker with minimal computational complexity, making it a suitable choice for advancing Motor Imagery Brain-Computer Interfaces (BCI).

Assessment of Motor Imagery and Its Relationship to Functional Impairment in Post-Stroke Patients: A Descriptive Cross-Sectional Study.

Background: Motor and cognitive sequelae are common in patients who have experienced a stroke. Recent advances in neuroscience have enabled the development of novel therapeutic approaches, such as motor imagery, which facilitate motor learning. The objective of this study is to examine the relationship between implicit and explicit motor imagery abilities and their correlation with functional impairment in post-stroke patients. Methods: A descriptive cross-sectional study was conducted with 36 patients who had experienced a stroke between March 2008 and March 2023. The capacity to generate both implicit and explicit motor imagery and to perform physical functions was evaluated. The relationship between implicit and explicit motor imagery measures was investigated using Pearson's correlation coefficient. The factorial structure, which encompasses the capacity to generate motor imagery, whether implicit or explicit, and physical function, was subjected to analysis. Results: A correlation was identified between the time taken to identify images and the accuracy of this process, with the right hand (R = 0.474), the left hand (R = 0.568), and the left foot (R = 0.344) all demonstrating significant associations. Additionally, a notable correlation was observed between the two subscales of the KVIQ-10 scale (R = 0.749). No association was identified between the capacity to generate implicit and explicit motor imagery. Two- and three-factor solutions were obtained for the right and left hemibodies, respectively. On both sides, accuracy in identifying images and physical function constituted a single factor, while time to generate images for both hands and feet constituted a second factor. Conclusions: In conclusion, no significant data were reported regarding the association between the capacity to generate implicit and explicit motor imagery in the studied sample. However, the ability to generate implicit motor imagery was related to physical function, suggesting that it may serve as a screening criterion for implementing specific therapeutic approaches in post-stroke patients.

Large scale investigation of the effect of gender on mu rhythm suppression in motor imagery brain-computer interfaces.

The utmost issue in Motor Imagery Brain-Computer Interfaces (MI-BCI) is the BCI poor performance known as 'BCI inefficiency'. Although past research has attempted to find a solution by investigating factors influencing users' MI-BCI performance, the issue persists. One of the factors that has been studied in relation to MI-BCI performance is gender. Research regarding the influence of gender on a user's ability to control MI-BCIs remains inconclusive, mainly due to the small sample size and unbalanced gender distribution in past studies. To address these issues and obtain reliable results, this study combined four MI-BCI datasets into one large dataset with 248 subjects and equal gender distribution. The datasets included EEG signals from healthy subjects from both gender groups who had executed a right- vs. left-hand motor imagery task following the Graz protocol. The analysis consisted of extracting the Mu Suppression Index from C3 and C4 electrodes and comparing the values between female and male participants. Unlike some of the previous findings which reported an advantage for female BCI users in modulating mu rhythm activity, our results did not show any significant difference between the Mu Suppression Index of both groups, indicating that gender may not be a predictive factor for BCI performance.

E-SAT: An extreme learning machine based self attention approach for decoding motor imagery EEG in subject-specific tasks.

The advancements in Brain-Computer Interface (BCI) have substantially evolved people's lives by enabling direct communication between the human brain and external peripheral devices. In recent years, the integration of machine larning (ML) and deep learning (DL) models have considerably imrpoved the performances of BCIs for decoding the motor imagery (MI) tasks. However, there still exist several limitations, e.g., extensive training time and high sensitivity to noises or outliers with those existing models, which largely hinder the rapid developments of BCIs. To address such issues, this paper proposes a novel extreme learning machine (ELM) based self-attention (E-SAT) mechanism to enhance subject-specific classification performances. Specifically, for E-SAT, ELM is employed both to imrpove self-attention module generalization ability for feature extraction and to optimize the model's parameter initialization process. Meanwhile, the extracted features are also classified using ELM, and the end-to-end ELM based setup is used to evaluate E-SAT performances on different MI EEG signals. Extensive experiments with different datasets, such as BCI Competition III Dataset IV-a, IV-b and BCI Competition IV Datasets 1,2a,2b,3, are conducted to verify the effectiveness of proposed E-SAT strategy. Results show that E-SAT outperforms several state-of-the-art (SOTA) existing methods in subject-specific classification on all the datasets, with an average classification accuracy of 99.8%,99.1%,98.9%,75.8%, 90.8%, and 95.4%, being achieved for each datasets, respectively. The experimental results not only show outstanding performance of E-SAT in feature extractions, but also demonstrate that it helps achieves the best results among nine other robust ones. In addition, results in this study also demonstrate that E-SAT achieves exceptional performance in both binary and multi-class classification tasks, as well as for noisy and non-noisy datatsets. .

Efficient Multi-View Graph Convolutional Network with Self-Attention for Multi-Class Motor Imagery Decoding.

Research on electroencephalogram-based motor imagery (MI-EEG) can identify the limbs of subjects that generate motor imagination by decoding EEG signals, which is an important issue in the field of brain-computer interface (BCI). Existing deep-learning-based classification methods have not been able to entirely employ the topological information among brain regions, and thus, the classification performance needs further improving. In this paper, we propose a multi-view graph convolutional attention network (MGCANet) with residual learning structure for multi-class MI decoding. Specifically, we design a multi-view graph convolution spatial feature extraction method based on the topological relationship of brain regions to achieve more comprehensive information aggregation. During the modeling, we build an adaptive weight fusion (Awf) module to adaptively merge feature from different brain views to improve classification accuracy. In addition, the self-attention mechanism is introduced for feature selection to expand the receptive field of EEG signals to global dependence and enhance the expression of important features. The proposed model is experimentally evaluated on two public MI datasets and achieved a mean accuracy of 78.26% (BCIC IV 2a dataset) and 73.68% (OpenBMI dataset), which significantly outperforms representative comparative methods in classification accuracy. Comprehensive experiment results verify the effectiveness of our proposed method, which can provide novel perspectives for MI decoding.

Pain neuroscience education and motor imagery-based exercise protocol for patients with fibromyalgia: A randomized controlled trial.

BACKGROUND: This study is a randomized controlled, biopsychosocial study investigating the effectiveness of pain neuroscience education (PNE) and motor imagery-based exercise protocol (MIEP) on fibromyalgia pain. METHODS: Our study has four groups (MIEP n = 12, PNE n = 12, MIEP + PNE n = 14, Control n = 12) and all participants (n = 50) consist of patients diagnosed with fibromyalgia with chronic back pain. The primary outcome measure was pain intensity, and secondary outcome measures were beliefs, kinesiophobia, anxiety-depression, cognitive-mood, self-esteem, and body awareness. RESULTS: A statistically significant decrease in pain intensity was observed in all experimental groups, without any group being superior (Visual Analog Scale [VAS]: MIEP + PNE p = .003, 95% confidence interval [CI], -4.7078 to -0.9922; MIEP p = .003, 95% CI, -5.4806 to -1.0194; PNE p = .002, 95% CI, -3.6139 to -1.5461). There was a significant improvement in organic beliefs in both groups where PNE was applied (MIEP + PNE: p = .017, 95% CI, -7.8211 to -0.3189; PNE: p = .003, 95% CI, -9.7999 to -0.0401). A significant superiority in organic pain beliefs was detected in the MIEP + PNE group compared to the control group (p = .008, 95% CI, 1.7241-9.4959). CONCLUSIONS: According to this study, in which MIEP and PNE were combined, there was a decrease in pain intensity when both applications were applied together and when they were applied one by one. MIEP has improved her motor imagery ability, improved pain and increased body awareness. PNE has improved people's organic pain beliefs; removed people from fears, catastrophizing, and negative thoughts about pain; improved easier management of psychological processes and cognitive-emotion regulation ability.

Breaking the Cycle of Pain: The Role of Graded Motor Imagery and Mirror Therapy in Complex Regional Pain Syndrome.

Background: Complex Regional Pain Syndrome (CRPS) is a chronic condition characterized by severe pain and functional impairment. Graded Motor Imagery (GMI) and Mirror Therapy (MT) have emerged as potential non-invasive treatments; this review evaluates the effectiveness of these therapies in reducing pain, improving function, and managing swelling in CRPS patients. Methods: A systematic review was conducted including randomized controlled trials (RCTs) that investigated GMI and MT in CRPS patients. This review was registered in PROSPERO (CRD42024535972) to ensure transparency and adherence to protocols. This review included searches of PubMed, Cochrane, SCOPUS, and Web of Science databases. Out of 81 studies initially screened, 6 were included in the final review. Studies were assessed for quality using the PEDro and RoB-2 scales. The primary outcomes were pain reduction, functional improvement, and swelling reduction. Results: Graded Motor Imagery (GMI) and Mirror Therapy (MT) reduced pain by an average of 20 points on the Neuropathic Pain Scale (NPS) and resulted in functional improvements as measured by the Task-Specific Numeric Rating Scale (NRS). GMI also contributed to some reduction in swelling. MT, particularly in post-stroke CRPS patients, showed significant pain reduction and functional improvements, with additional benefits in reducing swelling in certain studies. However, the included studies had small sample sizes and mixed designs, which limit the generalizability of the findings. The studies varied in sample size and design, with some risk of bias noted. Conclusions: Graded Motor Imagery (GMI) and Mirror Therapy (MT) have proven to be effective interventions for managing Complex Regional Pain Syndrome (CRPS), with significant improvements in pain reduction and functional recovery. These non-invasive treatments hold potential for integration into standard rehabilitation protocols. However, the small sample sizes and variability in study designs limit the generalizability of these findings. Future research should focus on larger, more homogeneous trials to validate the long-term effectiveness of GMI and MT, ensuring more robust clinical application.

Strategies to Improve Bladder Control: A Preliminary Case Study.

Background: Lower urinary tract symptoms (LUTSs) are a common complaint in adult and elderly men with bladder outlet obstruction, and have a considerable impact on their quality of life. Symptoms affect storage, voiding and post micturition stages. Among the latter, a feeling of incomplete emptying is one of the most bothersome for the patients; a condition that in turn contributes to affect urinary urgency, nocturia and frequency. Common recommendations include self-management practices (e.g., control of fluid intake, double-voiding and distraction techniques) to relieve patients' symptoms, whose effectiveness, however, is under debate. Methods: In this report we describe two pioneering procedures to favor bladder residual content voiding in people complaining of LUTS disorders. The first is based on motor imagery and the second on the use of odors. The beneficial effects of Mental imagery techniques on various tasks (e.g., in the treatment of several pathological conditions or as valid mnemonics aids have a long tradition and have received consistently experimental support. Thus, a patient (a 68-year-old Caucasian man) complaining of LUTS was trained to use a motor imagery technique (building up a visual image comprising the bladder, the detrusor muscle and the urethra, and to imagine the detrusor muscle contracting and the flow of urine expelled) for 90 days and two odors (coffee and a lavender scented cleanser) for 10 days, as a trigger for micturition. He was asked to record-immediately after the first morning micturition-the time interval between the first (free) and the second (cued) micturition. Results: Reported data suggest the efficacy of motor imagery in favoring the bladder residual urine voiding in a few minutes (M = 4.75 min.) compared to the control condition, i.e., the baseline of the patient (M = 79.5 min.), while no differences between the odor-based procedures (M 1st odorant = 70.6 min.; M 2nd odorant = 71.1 min) and the latter were observed. Conclusions: A procedure based on an imagery technique may, therefore, be of general value-as a suggested protocol-and accordingly can be applicable to clinical settings. An olfactory bladder control hypothesis cannot, however, be ruled out and is discussed as a promising future line of research.

Enhancing EEG-Based MI-BCIs with Class-Specific and Subject-Specific Features Detected by Neural Manifold Analysis.

This paper presents an innovative approach leveraging Neuronal Manifold Analysis of EEG data to identify specific time intervals for feature extraction, effectively capturing both class-specific and subject-specific characteristics. Different pipelines were constructed and employed to extract distinctive features within these intervals, specifically for motor imagery (MI) tasks. The methodology was validated using the Graz Competition IV datasets 2A (four-class) and 2B (two-class) motor imagery classification, demonstrating an improvement in classification accuracy that surpasses state-of-the-art algorithms designed for MI tasks. A multi-dimensional feature space, constructed using NMA, was built to detect intervals that capture these critical characteristics, which led to significantly enhanced classification accuracy, especially for individuals with initially poor classification performance. These findings highlight the robustness of this method and its potential to improve classification performance in EEG-based MI-BCI systems.

Optimizing Real-Time MI-BCI Performance in Post-Stroke Patients: Impact of Time Window Duration on Classification Accuracy and Responsiveness.

Brain-computer interfaces (BCIs) are promising tools for motor neurorehabilitation. Achieving a balance between classification accuracy and system responsiveness is crucial for real-time applications. This study aimed to assess how the duration of time windows affects performance, specifically classification accuracy and the false positive rate, to optimize the temporal parameters of MI-BCI systems. We investigated the impact of time window duration on classification accuracy and false positive rate, employing Linear Discriminant Analysis (LDA), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) on data acquired from six post-stroke patients and on the external BCI IVa dataset. EEG signals were recorded and processed using the Common Spatial Patterns (CSP) algorithm for feature extraction. Our results indicate that longer time windows generally enhance classification accuracy and reduce false positives across all classifiers, with LDA performing the best. However, to maintain the real-time responsiveness, crucial for practical applications, a balance must be struck. The results suggest an optimal time window of 1-2 s, offering a trade-off between classification performance and excessive delay to guarantee the system responsiveness. These findings underscore the importance of temporal optimization in MI-BCI systems to improve usability in real rehabilitation scenarios.

Sensorimotor brain-computer interface performance depends on signal-to-noise ratio but not connectivity of the mu rhythm in a multiverse analysis of longitudinal data.

Objective.Serving as a channel for communication with locked-in patients or control of prostheses, sensorimotor brain-computer interfaces (BCIs) decode imaginary movements from the recorded activity of the user's brain. However, many individuals remain unable to control the BCI, and the underlying mechanisms are unclear. The user's BCI performance was previously shown to correlate with the resting-state signal-to-noise ratio (SNR) of the mu rhythm and the phase synchronization (PS) of the mu rhythm between sensorimotor areas. Yet, these predictors of performance were primarily evaluated in a single BCI session, while the longitudinal aspect remains rather uninvestigated. In addition, different analysis pipelines were used to estimate PS in source space, potentially hindering the reproducibility of the results.Approach.To systematically address these issues, we performed an extensive validation of the relationship between pre-stimulus SNR, PS, and session-wise BCI performance using a publicly available dataset of 62 human participants performing up to 11 sessions of BCI training. We performed the analysis in sensor space using the surface Laplacian and in source space by combining 24 processing pipelines in a multiverse analysis. This way, we could investigate how robust the observed effects were to the selection of the pipeline.Main results.Our results show that SNR had both between- and within-subject effects on BCI performance for the majority of the pipelines. In contrast, the effect of PS on BCI performance was less robust to the selection of the pipeline and became non-significant after controlling for SNR.Significance.Taken together, our results demonstrate that changes in neuronal connectivity within the sensorimotor system are not critical for learning to control a BCI, and interventions that increase the SNR of the mu rhythm might lead to improvements in the user's BCI performance.

Influence of feedback transparency on motor imagery neurofeedback performance: the contribution of agency.

Objective.Neurofeedback (NF) is a cognitive training procedure based on real-time feedback (FB) of a participant's brain activity that they must learn to self-regulate. A classical visual FB delivered in a NF task is a filling gauge reflecting a measure of brain activity. This abstract visual FB is not transparently linked-from the subject's perspective-to the task performed (e.g., motor imagery (MI)). This may decrease the sense of agency, that is, the participants' reported control over FB. Here, we assessed the influence of FB transparency on NF performance and the role of agency in this relationship.Approach.Participants performed a NF task using MI to regulate brain activity measured using electroencephalography. In separate blocks, participants experienced three different conditions designed to vary transparency: FB was presented as either (1) a swinging pendulum, (2) a clenching virtual hand, (3) a clenching virtual hand combined with a motor illusion induced by tendon vibration. We measured self-reported agency and user experience after each NF block.Main results. We found that FB transparency influences NF performance. Transparent visual FB provided by the virtual hand resulted in significantly better NF performance than the abstract FB of the pendulum. Surprisingly, adding a motor illusion to the virtual hand significantly decreased performance relative to the virtual hand alone. When introduced in incremental linear mixed effect models, self-reported agency was significantly associated with NF performance and it captured the variance related to the effect of FB transparency on NF performance.Significance. Our results highlight the relevance of transparent FB in relation to the sense of agency. This is likely an important consideration in designing FB to improve NF performance and learning outcomes.

Multisensory approach in Mental Imagery: ALE meta-analyses comparing Motor, Visual and Auditory Imagery.

Mental Imagery is a topic of longstanding and widespread scientific interest. Individual studies have typically focused on a single modality (e.g. Motor, Visual, Auditory) of Mental Imagery. Relatively little work has considered directly comparing and contrasting the brain networks associated with these different modalities of Imagery. The present study integrates data from 439 neuroimaging experiments to identify both modality-specific and shared neural networks involved in Mental Imagery. Comparing the networks involved in Motor, Visual, and Auditory Imagery identified a pattern whereby each form of Imagery preferentially recruited 'higher level' associative brain regions involved in the associated 'real' experience. Results also indicate significant overlap in a left-lateralized network including the pre-supplementary motor area, ventral premotor cortex and inferior parietal lobule. This pattern of results supports the existence of a 'core' network that supports the attentional, spatial, and decision-making demands of Mental Imagery. Together these results offer new insights into the brain networks underlying human imagination.

Improving classification performance of motor imagery BCI through EEG data augmentation with conditional generative adversarial networks.

In brain-computer interface (BCI), building accurate electroencephalogram (EEG) classifiers for specific mental tasks is critical for BCI performance. The classifiers are developed by machine learning (ML) and deep learning (DL) techniques, requiring a large dataset for training to build reliable and accurate models. However, collecting large enough EEG datasets is difficult due to intra-/inter-subject variabilities and experimental costs. This leads to the data scarcity problem, which causes overfitting issues to training samples, resulting in reducing generalization performance. To solve the EEG data scarcity problem and improve the performance of the EEG classifiers, we propose a novel EEG data augmentation (DA) framework using conditional generative adversarial networks (cGANs). An experimental study is implemented with two public EEG datasets, including motor imagery (MI) tasks (BCI competition IV IIa and III IVa), to validate the effectiveness of the proposed EEG DA method for the EEG classifiers. To evaluate the proposed cGAN-based DA method, we tested eight EEG classifiers for the experiment, including traditional MLs and state-of-the-art DLs with three existing EEG DA methods. Experimental results showed that most DA methods with proper DA proportion in the training dataset had higher classification performances than without DA. Moreover, applying the proposed DA method showed superior classification performance improvement than the other DA methods. This shows that the proposed method is a promising EEG DA method for enhancing the performances of the EEG classifiers in MI-based BCIs.

Unlike overt movement, motor imagery cannot update internal models.

In overt movement, internal models make predictions about the sensory consequences of a desired movement, generating the appropriate motor commands to achieve that movement. Using available sensory feedback, internal models are updated to allow for movement adaptation and in-turn better performance. Whether internal models are updated during motor imagery, the mental rehearsal of movement, is not well established. To investigate internal modelling during motor imagery, 66 participants were exposed to a leftwards prism shift while performing actual pointing movements (physical practice; PP), imagined pointing movements (motor imagery; MI), or no pointing movements (control). If motor imagery updates internal models, we hypothesized that aftereffects (pointing in the direction opposite the prism shift) would be observed in MI, like that of PP, and unlike that of control. After prism exposure, the magnitude of aftereffects was significant in PP (4.73° ± 1.56°), but not in MI (0.34° ± 0.96°) and control (0.34° ± 1.04°). Accordingly, PP differed significantly from MI and control. Our results show that motor imagery does not update internal models, suggesting that it is not a direct simulation of overt movement. Furthering our understanding of the mechanisms that underlie learning through motor imagery will lead to more effective applications of motor imagery.

Motor imagery with cues in virtual reality, audio and screen.

OBJECTIVE: Training plays a significant role in motor imagery (MI), particularly in applications such as Motor Imagery-based Brain-Computer Interface (MIBCI) systems and rehabilitation systems. Previous studies have investigated the intricate relationship between cues and MI signals. However, the medium of presentation still remains an emerging area to be explored, as possible factors to enhance Motor Imagery signals.. Approach: We hypothesise that the medium used for cue presentation can significantly influence both performance and training outcomes in MI tasks. To test this hypothesis, we designed and executed an experiment implementing no- feedback MI. Our investigation focused on three distinct cue presentation mediums -audio, screen, and virtual reality(VR) headsets-all of which have potential implications for BCI use in the Activities of Daily Lives. Main Results: The results of our study uncovered notable variations in MI signals depending on the medium of cue presentation, where the analysis is based on 3 EEG channels. To substantiate our findings, we employed a comprehensive approach, utilizing various evaluation metrics including Event- Related Synchronisation(ERS)/Desynchronisation(ERD), Feature Extraction (using Recursive Feature Elimination (RFE)), Machine Learning methodologies (using Ensemble Learning), and participant Questionnaires. All the approaches signify that Motor Imagery signals are enhanced when presented in VR, followed by audio, and lastly screen. Applying a Machine Learning approach across all subjects, the mean cross-validation accuracy (Mean ± Std. Error) was 69.24 ± 3.12, 68.69 ± 3.3 and 66.1±2.59 when for the VR, audio-based, and screen-based instructions respectively. Significance: This multi-faceted exploration provides evidence to inform MI- based BCI design and advocates the incorporation of different mediums into the design of MIBCI systems, experimental setups, and user studies. The influence of the medium used for cue presentation may be applied to develop more effective and inclusive MI applications in the realm of human-computer interaction and rehabilitation.