Motor Imagery Research Articles

Does context matter for memory? Testing the effectiveness of learning by imagining situated interactions with objects

ABSTRACT Mounting evidence supports the efficacy of mental imagery for verbal information retention. Motor imagery, imagining oneself interacting physically with the object to be learned, emerges as an optimal form compared to less physically engaging imagery. Yet, when engaging in mental imagery, it occurs within a specific context that may affect imagined actions and consequently impact the mnemonic benefits of mental imagery. In a first study, participants were given instructions for incidental learning: mental rehearsal, visual imagery, motor imagery or situated motor imagery. The latter, which involved imagining physical interaction with an item within a coherent situation, produced the highest proportion of correct recalls. This highlights memory’s role in supporting situated actions and offers the possibility for further developing the mnemonic potential of embodied mental imagery. Furthermore, item-level analysis showed that individuals who engaged in situated motor imagery remembered words primarily due to the sensorimotor characteristics of the words’ referent. A second study investigating the role of inter-item distinctiveness in this effect failed to determine the extent to which the situational and motor elements need to be distinctive in order to be considered useful retrieval cues and produce an optimal memory performance.

Multi-scale spatiotemporal attention network for neuron based motor imagery EEG classification

BackgroundIn recent times, the expeditious expansion of Brain-Computer Interface (BCI) technology in neuroscience, which relies on electroencephalogram (EEG) signals associated with motor imagery, has yielded outcomes that rival conventional approaches, notably due to the triumph of deep learning. Nevertheless, the task of developing and training a comprehensive network to extract the underlying characteristics of motor imagining EEG data continues to pose challenges. New methodThis paper presents a multi-scale spatiotemporal self-attention (SA) network model that relies on an attention mechanism. This model aims to classify motor imagination EEG signals into four classes (left hand, right hand, foot, tongue/rest) by considering the temporal and spatial properties of EEG. It is employed to autonomously allocate greater weights to channels linked to motor activity and lesser weights to channels not related to movement, thus choosing the most suitable channels. Neuron utilises parallel multi-scale Temporal Convolutional Network (TCN) layers to extract feature information in the temporal domain at various scales, effectively eliminating temporal domain noise. ResultsThe suggested model achieves accuracies of 79.26%, 85.90%, and 96.96% on the BCI competition datasets IV-2a, IV-2b, and HGD, respectively. Comparison with existing methodsIn terms of single-subject classification accuracy, this strategy demonstrates superior performance compared to existing methods. ConclusionThe results indicate that the proposed strategy exhibits favourable performance, resilience, and transfer learning capabilities.

Graph neural network based on brain inspired forward-forward mechanism for motor imagery classification in brain-computer interfaces.

Within the development of brain-computer interface (BCI) systems, it is crucial to consider the impact of brain network dynamics and neural signal transmission mechanisms on electroencephalogram-based motor imagery (MI-EEG) tasks. However, conventional deep learning (DL) methods cannot reflect the topological relationship among electrodes, thereby hindering the effective decoding of brain activity. Inspired by the concept of brain neuronal forward-forward (F-F) mechanism, a novel DL framework based on Graph Neural Network combined forward-forward mechanism (F-FGCN) is presented. F-FGCN framework aims to enhance EEG signal decoding performance by applying functional topological relationships and signal propagation mechanism. The fusion process involves converting the multi-channel EEG into a sequence of signals and constructing a network grounded on the Pearson correlation coeffcient, effectively representing the associations between channels. Our model initially pre-trains the Graph Convolutional Network (GCN), and fine-tunes the output layer to obtain the feature vector. Moreover, the F-F model is used for advanced feature extraction and classification. Achievement of F-FGCN is assessed on the PhysioNet dataset for a four-class categorization, compared with various classical and state-of-the-art models. The learned features of the F-FGCN substantially amplify the performance of downstream classifiers, achieving the highest accuracy of 96.11% and 82.37% at the subject and group levels, respectively. Experimental results affirm the potency of FFGCN in enhancing EEG decoding performance, thus paving the way for BCI applications.

MAE-EEG-Transformer: A transformer-based approach combining masked autoencoder and cross-individual data augmentation pre-training for EEG classification

Convolutional neural networks (CNN) may not be ideal for extracting global temporal features from non-stationary Electroencephalogram (EEG) signals. The application of the masking-based method in EEG classification is not well studied, and there is a shortage of commonly accepted models for verifying inter-individual results in motor imagery classification tasks. The MAE-EEG-Transformer, a transformer with masking mechanism, is proposed in this article. It pre-trains by randomly masking signals and forces the model to learn semantic features. The pre-trained encoder module is fine-tuned and moved to the classification task to obtain the category of EEG signals. The effectiveness of features with and without pre-training is compared using t-SNE visualization to demonstrate pre-training’s inter-subject efficacy. The MAE EEG Transformer was extensively evaluated across three prevalent datasets in EEG-based motor imagery, demonstrating performance comparable to state-of-the-art models while requiring only approximately 20% of the computational cost (results in Table 1, 2, 3 and 4).

Brain state and dynamic transition patterns of motor imagery revealed by the bayes hidden markov model

Brain state and dynamic transition patterns of motor imagery revealed by the bayes hidden markov model

Theoretical explanations and the availability of information for learning via combined action observation and motor imagery: a commentary on Eaves et al. (2022).

The recent review by Eaves et al. (Psychological Research/Psychologische Forschung, 2022) outlines the research conducted to-date on combined action-observation and motor imagery (AOMI), and more specifically, its added benefit to learning. Of interest, these findings have been primarily attributed to the dual action simulation hypothesis, whereby AO and MI activate separable representations for action that may be later merged when they are congruent with one another. The present commentary more closely evaluates this explanation. What's more, we offer an alternative information-based argument where the benefit to learning may be served instead by the availability of key information. Along these lines, we speculate on possible future directions including the need for a transfer design.

Merged CNNs for the classification of EEG motor imagery signals

Merged CNNs for the classification of EEG motor imagery signals

A Local-Ascending-Global Learning Strategy for Brain-Computer Interface

Neuroscience research indicates that the interaction among different functional regions of the brain plays a crucial role in driving various cognitive tasks. Existing studies have primarily focused on constructing either local or global functional connectivity maps within the brain, often lacking an adaptive approach to fuse functional brain regions and explore latent relationships between localization during different cognitive tasks. This paper introduces a novel approach called the Local-Ascending-Global Learning Strategy (LAG) to uncover higher-level latent topological patterns among functional brain regions. The strategy initiates from the local connectivity of individual brain functional regions and develops a K-Level Self-Adaptive Ascending Network (SALK) to dynamically capture strong connectivity patterns among brain regions during different cognitive tasks. Through the step-by-step fusion of brain regions, this approach captures higher-level latent patterns, shedding light on the progressively adaptive fusion of various brain functional regions under different cognitive tasks. Notably, this study represents the first exploration of higher-level latent patterns through progressively adaptive fusion of diverse brain functional regions under different cognitive tasks. The proposed LAG strategy is validated using datasets related to fatigue (SEED-VIG), emotion (SEED-IV), and motor imagery (BCI_C_IV_2a). The results demonstrate the generalizability of LAG, achieving satisfactory outcomes in independent-subject experiments across all three datasets. This suggests that LAG effectively characterizes higher-level latent patterns associated with different cognitive tasks, presenting a novel approach to understanding brain patterns in varying cognitive contexts.

Individual-finger motor imagery classification: a data-driven approach with Shapley-informed augmentation

Objective. Classifying motor imagery (MI) tasks that involve fine motor control of the individual five fingers presents unique challenges when utilizing electroencephalography (EEG) data. In this paper, we systematically assess the classification of MI functions for the individual five fingers using single-trial time-domain EEG signals. This assessment encompasses both within-subject and cross-subject scenarios, supported by data-driven analysis that provides statistical validation of the neural correlate that could potentially discriminate between the five fingers. Approach. We present Shapley-informed augmentation, an informed approach to enhance within-subject classification accuracy. This method is rooted in insights gained from our data-driven analysis, which revealed inconsistent temporal features encoding the five fingers MI across sessions of the same subject. To evaluate its impact, we compare within-subject classification performance both before and after implementing this augmentation technique. Main results. Both the data-driven approach and the model explainability analysis revealed that the parietal cortex contains neural information that helps discriminate the individual five fingers’ MI apart. Shapley-informed augmentation successfully improved classification accuracy in sessions severely affected by inconsistent temporal features. The accuracy for sessions impacted by inconsistency in their temporal features increased by an average of 26.3%±6.70 , thereby enabling a broader range of subjects to benefit from brain–computer interaction (BCI) applications involving five-fingers MI classification. Conversely, non-impacted sessions experienced only a negligible average accuracy decrease of 2.01±5.44% . The average classification accuracy achieved is around 60.0% (within-session), 50.0% (within-subject) and 40.0% (leave-one-subject-out). Significance. This research offers data-driven evidence of neural correlates that could discriminate between the individual five fingers MI and introduces a novel Shapley-informed augmentation method to address temporal variability of features, ultimately contributing to the development of personalized systems.

Optimizing motion imagery classification with limited channels using the common spatial pattern-based integrated algorithm.

The extraction of effective classification features from electroencephalogram (EEG) signals in motor imagery is a popular research topic. The Common Spatial Pattern (CSP) algorithm is widely employed in this field. However, the performance of the traditional CSP method depends significantly on the choice of a specific frequency band and channel number of EEG data. Furthermore, inter-class variance among these frequency bands and the limited number of available EEG channels can adversely affect the CSP algorithm's ability to extract meaningful features from the relevant signal frequency bands. We hypothesize that multiple Intrinsic Mode Functions (IMFS), into which the raw EEG signal is decomposed, can better capture the non-Gaussian characteristics of the signal, thus compensating for the limitations of the CSP algorithm when dealing with nonlinear and non-Gaussian distributed data with few channels. Therefore, this paper proposes a novel method that integrates Variational Mode Decomposition (VMD), Phase Space Reconstruction (PSR), and the CSP algorithm to address these issues. VMD is used to filter and enhance the quality of the collected data, PSR is employed to increase the effective data channels (data augmentation), and the subsequent CSP filtering can obtain signals with spatial features, which are decoded by Convolutional Neural Networks (CNN) for action decoding. This study utilizes self-collected EEG data to demonstrate that the new method can achieve a good classification accuracy of 82.30% on average, confirming the improved algorithm's effectiveness and feasibility. Furthermore, this study conducted validation on the publicly available BCI Competition IV dataset 2b, demonstrating an average classification accuracy of 87.49%.

A brain functional network feature extraction method based on directed transfer function and graph theory for MI-BCI decoding tasks.

The development of Brain-Computer Interface (BCI) technology has brought tremendous potential to various fields. In recent years, prominent research has focused on enhancing the accuracy of BCI decoding algorithms by effectively utilizing meaningful features extracted from electroencephalographic (EEG) signals. This paper proposes a method for extracting brain functional network features based on directed transfer function (DTF) and graph theory. The method incorporates the extracted brain network features with common spatial pattern (CSP) to enhance the performance of motor imagery (MI) classification task. The signals from each electrode of the EEG, utilizing a total of 32 channels, are used as input signals for the network nodes. In this study, 26 healthy participants were recruited to provide EEG data. The brain functional network is constructed in Alpha and Beta bands using the DTF method. The node degree (ND), clustering coefficient (CC), and global efficiency (GE) of the brain functional network are obtained using graph theory. The DTF network features and graph theory are combined with the traditional signal processing method, the CSP algorithm. The redundant network features are filtered out using the Lasso method, and finally, the fused features are classified using a support vector machine (SVM), culminating in a novel approach we have termed CDGL. For Beta frequency band, with 8 electrodes, the proposed CDGL method achieved an accuracy of 89.13%, a sensitivity of 90.15%, and a specificity of 88.10%, which are 14.10, 16.69, and 11.50% percentage higher than the traditional CSP method (75.03, 73.46, and 76.60%), respectively. Furthermore, the results obtained with 8 channels were superior to those with 4 channels (82.31, 83.35, and 81.74%), and the result for the Beta frequency band were better than those for the Alpha frequency band (87.42, 87.48, and 87.36%). Similar results were also obtained on two public datasets, where the CDGL algorithm's performance was found to be optimal. The feature fusion of DTF network and graph theory features enhanced CSP algorithm's performance in MI task classification. Increasing the number of channels allows for more EEG signal feature information, enhancing the model's sensitivity and discriminative ability toward specific activities in brain regions. It should be noted that the functional brain network features in the Beta band exhibit superior performance improvement for the algorithm compared to those in the Alpha band.

An eight-week single-blind randomised controlled trial on dual task balance training and motor imagery practice in ischaemic stroke survivors.

The purpose of this study was to find the effects of motor imagery on balance and mobility of stroke patients.This was a single-blind randomised controlled trial which included a total of 30 patients. These patients were assigned into two group: experimental (n=15) and control (n=15) by sealed envelope method. Functional Reach Test (FRT), Time Up and Go Test (TUGT), Berg Balance Scale (BBS), and Movement Imagery Questionnaire (MIQ) were used as assessment tools. The overall mean age of the participants was 52.63 ±8.78 years. Between groups analysis showed non-statistically significant difference (p>0.05) in FRT but significant difference in TUGT, BBS, and MIQ-3 (p<0.009) after eight weeks of training. Within group analysis showed statistically significant difference (p<0.05) for all outcome measures. This study concluded that motor imagery is an effective treatment strategy for improving balance and mobility in stroke patients and brings better results as compared to conventional treatments.

The Role of Sport Psychology in Injury Prevention and Rehabilitation in Junior Athletes.

Sports injuries have historically been addressed and treated from a purely physical perspective. Nevertheless, like in many other aspects of sports, it has become evident during the last decades that psychological considerations and consequent interventions are both vital and inevitable in the work with athletes, particularly in the work with junior athletes. Especially in the domains of sports injury prevention and rehabilitation, psychological measures can yield significant benefits for junior athletes. Stress management techniques, cognitive restructuring, mindfulness, motor imagery, or seeking social support have been demonstrated as being highly effective. These techniques, many of them originally intended by sport psychologists to optimize performance, now aid junior athletes in performing at their best while also preventing injury and facilitating a safe return to competition after injury. During injury rehabilitation, sport psychological measures play an important role as well. The purpose of this review is firstly to provide an overview of the psychological factors that significantly support both injury prevention and rehabilitation. We subsequently elaborate on the identification and optimization of these factors by presenting evidence-based psychological interventions and training programs. In addition, we provide science-informed fundamentals that may serve as a basis for the adaptation and/or development of novel psychological measures to support junior athletes during injury prevention and rehabilitation.

A two-stage transformer based network for motor imagery classification

Brain-computer interfaces (BCIs) are used to understand brain functioning and develop therapies for neurological and neurodegenerative disorders. Therefore, BCIs are crucial in rehabilitating motor dysfunction and advancing motor imagery applications. For motor imagery, electroencephalogram (EEG) signals are used to classify the subject's intention of moving a body part without actually moving it. This paper presents a two-stage transformer-based architecture that employs handcrafted features and deep learning techniques to enhance the classification performance on benchmarked EEG signals. Stage-1 is built on parallel convolution based EEGNet, multi-head attention, and separable temporal convolution networks for spatiotemporal feature extraction. Further, for enhanced classification, in stage-2, additional features and embeddings extracted from stage-1 are used to train TabNet. In addition, a novel channel cluster swapping data augmentation technique is also developed to handle the issue of limited samples for training deep learning architectures. The developed two-stage architecture offered an average classification accuracy of 88.5 % and 88.3 % on the BCI Competition IV-2a and IV-2b datasets, respectively, which is approximately 3.0 % superior over similar recent reported works.

Motor imagery for paediatric neurorehabilitation: how much do we know? Perspectives from a systematic review.

Motor Imagery (MI) is a cognitive process consisting in mental simulation of body movements without executing physical actions: its clinical use has been investigated prevalently in adults with neurological disorders. Review of the best-available evidence on the use and efficacy of MI interventions for neurorehabilitation purposes in common and rare childhood neurological disorders. systematic literature search conducted according to PRISMA by using the Scopus, PsycArticles, Cinahl, PUBMED, Web of Science (Clarivate), EMBASE, PsychINFO, and COCHRANE databases, with levels of evidence scored by OCEBM and PEDro Scales. Twenty-two original studies were retrieved and included for the analysis; MI was the unique or complementary rehabilitative treatment in 476 individuals (aged 5 to 18 years) with 10 different neurological conditions including, cerebral palsies, stroke, coordination disorders, intellectual disabilities, brain and/or spinal cord injuries, autism, pain syndromes, and hyperactivity. The sample size ranged from single case reports to cohorts and control groups. Treatment lasted 2 days to 6 months with 1 to 24 sessions. MI tasks were conventional, graded or ad-hoc. MI measurement tools included movement assessment batteries, mental chronometry tests, scales, and questionnaires, EEG, and EMG. Overall, the use of MI was stated as effective in 19/22, and uncertain in the remnant studies. MI could be a reliable supportive/add-on (home-based) rehabilitative tool for pediatric neurorehabilitation; its clinical use, in children, is highly dependent on the complexity of MI mechanisms, which are related to the underlying neurodevelopmental disorder.

Artifact removal and motor imagery classification in EEG using advanced algorithms and modified DNN

This paper presents an advanced approach for EEG artifact removal and motor imagery classification using a combination of Four Class Iterative Filtering and Filter Bank Common Spatial Pattern Algorithm with a Modified Deep Neural Network (DNN) classifier. The research aims to enhance the accuracy and reliability of BCI systems by addressing the challenges posed by EEG artifacts and complex motor imagery tasks.The methodology begins by introducing FCIF, a novel technique for ocular artifact removal, utilizing iterative filtering and filter banks. FCIF's mathematical formulation allows for effective artifact mitigation, thereby improving the quality of EEG data. In tandem, the FC-FBCSP algorithm is introduced, extending the Filter Bank Common Spatial Pattern approach to handle four-class motor imagery classification. The Modified DNN classifier enhances the discriminatory power of the FC-FBCSP features, optimizing the classification process.The paper showcases a comprehensive experimental setup, featuring the utilization of BCI Competition IV Dataset 2a & 2b. Detailed preprocessing steps, including filtering and feature extraction, are presented with mathematical rigor. Results demonstrate the remarkable artifact removal capabilities of FCIF and the classification prowess of FC-FBCSP combined with the Modified DNN classifier. Comparative analysis highlights the superiority of the proposed approach over baseline methods and the method achieves the mean accuracy of 98.575%.

Picture this! Suggested instructions for guiding the Neuroscience of action imagery: A commentary on Krüger et al. (2022).

Our commentary expands the multisensory and modulating factors proposed by Kruger et al.'s (2023) internal models of action imagery and sensory crossovers. We will discuss the essence of imagery experiences as conceptual intersections among sensory, movement and affective properties that require further neuro-anatomical-contextual mapping to better understand the practical application of imagery. Accordingly, we will propose alternative ideas of daisy-chaining and motor imagery systems. The role of imagery speed, and other properties of movement for refining movement and self-regulation will be considered along with sex as a modulating factor in intra-individual abilities to image movement.

A time-frequency map generation network embedded with spectral self-attention for motor imagery classification

End-to-end networks have achieved remarkable success in Motor Imagery (MI) classification by directly extracting features from raw Electroencephalogram (EEG) signals and performing classification. The self-attention mechanism has been successfully introduced to improve the performance of these networks further. However, the features extracted from existing end-to-end networks lack interpretable and comprehensive spectral information, making it difficult to develop spectral self-attention mechanisms. To overcome this challenge, we proposed a novel end-to-end network called Time-Frequency Map Generation Network (TFGNet), which utilizes the frequency domain information of raw EEG signals to generate interpretable time–frequency maps. TFGNet has shown comparable performance to State-of-the-Art (SotA) methods on MI classification tasks. Subsequently, the first spectral attention module for end-to-end networks for discriminative analysis of frequency components is presented. Extensive experiments have shown that using this module in the TFGNet increases classification accuracy by approximately 3% for classification tasks involving multiple objects. The visualization results have also illustrated the process of generating time–frequency maps and the mechanism of spectral self-attention.

Unilateral movement decoding of upper and lower limbs using magnetoencephalography

Problem: The effectiveness of distinguishing unilateral lower limb motor execution (ME) or imagery (MI) based on electroencephalogram (EEG) is limited by its low spatial resolution, since the somatotopies of bilateral lower limbs are close to each other. Aim: This research focused on differentiating unilateral lower limb tasks using magnetoencephalography (MEG) signals. Methods: MEG signals were recorded during unilateral upper and lower limb movements. Channel selection and extraction of band power features were performed at both the conventional sensor level and the proposed source level, reconstructed using beamforming. The classification performance at both levels was compared. Results: The theta band changes exhibited the most significant differences and lateralization across tasks. Task-related features were more prominent at the source than at the sensor level. The classification results indicate that all methods achieved an average accuracy of over 98.33% in classifying the upper limb task. For the classification of lower limb tasks, the average accuracies achieved at the source level (96.97% and 95.86%) were significantly higher than those obtained at the sensor level (90.00% and 92.57%). Conclusion and Significance: Our results demonstrated the feasibility of MEG in classifying unilateral lower limb movements, providing a potentially effective method for brain-computer interfaces (BCIs) to enhance control commands. Furthermore, signal processing at the source level can effectively enhance inter-task differences to achieve higher classification performance. Meanwhile, the theta band is highly effective in movement classification and may play an important role in motor function.

Changes in the excitability of anterior horn cells in a mental rotation task of body parts.

Mental rotation (MR), a tool of implicit motor imagery, is the ability to rotate mental representations of two- or three-dimensional objects. Although many reports have described changes in brain activity during MR tasks, it is not clear whether the excitability of anterior horn cells in the spinal cord can be changed. In this study, we examined whether MR tasks of hand images affect the excitability of anterior horn cells using F-wave analysis. Right-handed, healthy participants were recruited for this study. F-waves of the right abductor pollicis brevis were recorded after stimulation of the right median nerve at rest, during a non-MR task, and during an MR task. The F-wave persistence and the F/M amplitude ratio were calculated and analyzed. Twenty participants (11 men and 9 women; mean age, 29.2 ± 4.4 years) were initially recruited, and data from the 18 that met the inclusion criteria were analyzed. The F-wave persistence was significantly higher in the MR task than in the resting condition (p = .001) or the non-MR task (p = .012). The F/M amplitude ratio was significantly higher in the MR task than in the resting condition (p = .019). The MR task increases the excitability of anterior horn cells corresponding to the same body part. MR tasks may have the potential for improving motor function in patients with reduced excitability of the anterior horn cells, although this methodology must be further verified in a clinical setting.