Imagery Tasks Research Articles

Transfer Learning Based on Optimal Transport for Motor Imagery Brain-Computer Interfaces

This paper tackles the cross-sessions variability of electroencephalography-based brain-computer interfaces (BCIs) in order to avoid the lengthy recalibration step of the decoding method before every use. We develop a new approach of domain adaptation based on optimal transport to tackle brain signal variability between sessions of motor imagery BCIs. We propose a backward method where, unlike the original formulation, the data from a new session are transported to a calibration session, and thereby avoiding model retraining. Several domain adaptation approaches are evaluated and compared. We simulated two possible online scenarios: i) block-wise adaptation and ii) sample-wise adaptation. In this study, we collect a dataset of 10 subjects performing a hand motor imagery task in 2 sessions. A publicly available dataset is also used. For the first scenario, results indicate that classifier retraining can be avoided by means of our backward formulation yielding to equivalent classification performance as compared to retraining solutions. In the second scenario, classification performance rises up to 90.23% overall accuracy when the label of the indicated mental task is used to learn the transport. Adaptive time is between 10 and 80 times faster than the other methods. The proposed method is able to mitigate the cross-session variability in motor imagery BCIs. The backward formulation is an efficient retraining-free approach built to avoid lengthy calibration times. Thus, the BCI can be actively used after just a few minutes of setup. This is important for practical applications such as BCI-based motor rehabilitation.

Identification of Visual Imagery by Electroencephalography Based on Empirical Mode Decomposition and an Autoregressive Model.

The traditional imagery task for brain–computer interfaces (BCIs) consists of motor imagery (MI) in which subjects are instructed to imagine moving certain parts of their body. This kind of imagery task is difficult for subjects. In this study, we used a less studied yet more easily performed type of mental imagery—visual imagery (VI)—in which subjects are instructed to visualize a picture in their brain to implement a BCI. In this study, 18 subjects were recruited and instructed to observe one of two visual-cued pictures (one was static, while the other was moving) and then imagine the cued picture in each trial. Simultaneously, electroencephalography (EEG) signals were collected. Hilbert–Huang Transform (HHT), autoregressive (AR) models, and a combination of empirical mode decomposition (EMD) and AR were used to extract features, respectively. A support vector machine (SVM) was used to classify the two kinds of VI tasks. The average, highest, and lowest classification accuracies of HHT were 68.14 ± 3.06%, 78.33%, and 53.3%, respectively. The values of the AR model were 56.29 ± 2.73%, 71.67%, and 30%, respectively. The values obtained by the combination of the EMD and the AR model were 78.40 ± 2.07%, 87%, and 48.33%, respectively. The results indicate that multiple VI tasks were separable based on EEG and that the combination of EMD and an AR model used in VI feature extraction was better than an HHT or AR model alone. Our work may provide ideas for the construction of a new online VI-BCI.

Effects of Motor Imagery Tasks on Brain Functional Networks Based on EEG Mu/Beta Rhythm

Motor imagery (MI) refers to the mental rehearsal of movement in the absence of overt motor action, which can activate or inhibit cortical excitability. EEG mu/beta oscillations recorded over the human motor cortex have been shown to be consistently suppressed during both the imagination and performance of movements, although the specific effect on brain function remains to be confirmed. In this study, Granger causality (GC) was used to construct the brain functional network of subjects during motor imagery and resting state based on EEG in order to explore the effects of motor imagery on brain function. Parameters of the brain functional network were compared and analyzed, including degree, clustering coefficient, characteristic path length and global efficiency of EEG mu/beta rhythm in different states. The results showed that the clustering coefficient and efficiency of EEG mu/beta rhythm decreased significantly during motor imagery (p < 0.05), while degree distribution and characteristic path length increased significantly (p < 0.05), mainly concentrated in the frontal lobe and sensorimotor area. For the resting state after motor imagery, the changes of brain functional characteristics were roughly similar to those of the task state. Therefore, it is concluded that motor imagery plays an important role in activation of cortical excitability.

Influence of imagery-based suggestions on performance during the training of professional firefighters

AbstractObjectivesFor several decades, a growing number of studies have highlighted that imagery-based suggestions, can efficiently influence motor control and perception. In the present study, we tested whether imagery-based suggestions without hypnotic induction might influence physical resistance performance and effort perception in the context of French firefighters’ usual training.MethodsA group of 18 male firefighters had to keep the wall-sit posture as long as they could while listening to different scripts. In the first condition, imagery was related to Lightness. In the second one, it was related to Heaviness. In the Control condition, they just had to listen and pay attention to series of two-digit numbers.ResultsResults showed that the participants kept the posture longer in the Lightness condition than in the Heaviness one. Furthermore the effort was perceived as less difficult in the Lightness condition in comparison to the Heaviness and the Control ones. Moreover in the Lightness condition, the higher the participants scored in visual and kinesthetic imagery tasks (MIQ-R), the less they rated the exercise as difficult.ConclusionsImagery-based suggestions significantly influenced both physical resistance performance and effort perception without any prior hypnotic induction. Further studies are necessary to better understand the factors that modulate this influence.

Brain functional connectivity during and after imagery of gaming and alternative leisure activities in patients with internet gaming disorder

BackgroundThe effect of gaming cue exposure on brain activity in patients with internet gaming disorder (IGD) has been investigated a lot, but the effect on brain connectivity has not. This study aimed to investigate the effects of imageries of gaming and alternative leisure activities on functional connectivity during the during-task and post-task states in patients with IGD. MethodsTwenty-nine patients and 20 healthy controls were scanned in the 6-min states before, during, and after the imagery tasks for gaming and alternative leisure behaviors using fMRI. Seed-based functional connectivity during and after the tasks were analyzed. The seeds were the nucleus accumbens (NAcc), ventral tegmental area (VTA), caudate, putamen, anterior cingulate cortex (ACC), and posterior cingulate cortex. ResultsThe group-by-state interaction effects for the during-tasks were found in caudate-, putamen-, and ACC-based connectivity, whereas those for the post-tasks were shown only in NAcc-based connectivity. In particular, patients showed that caudate-right parahippocampal gyrus connectivity and putamen-right orbitofrontal cortex connectivity increased during gaming and decreased during alternative, whereas NAcc-right precuneus connectivity decreased at baseline, increased in post-gaming, and were not different in post-alternative. ConclusionDifferences in during-task connectivity of the habit/motor and salience networks and post-task resting-state connectivity of the reward and limbic networks between the two imagery tasks may differ between the groups. In the treatment of IGD, when these network connections are reactive to alternative leisure activity, just as to gaming activity, they seem to be freed from gaming addiction.

Self-perception in anorexia nervosa: When the body becomes an object

ObjectiveWomen with anorexia nervosa (AN) act as if they have a larger body, as evidenced in obstacle avoidance tasks, where an allocentric perspective is adopted. This alteration emerges not only when they perform, but also when they imagine movements. However, no previous study has investigated own body centered tasks. As such, in this study we aim at documenting if women with AN show an altered behaviour also when the task requires a first-person perspective. MethodWe explored the performance of eleven woman affected by AN compared to eighteen matched controls, in two motor imagery tasks based on a self-frame of reference, the Hand Laterality Task and the Mental Motor Chronometry Task. Moreover, two control tasks relative to visual imagery were administered. ResultsIn the Hand Laterality Task, affected participants did not adopt a motor strategy to judge hands laterality (i.e. no biomechanical constraints effect). Crucially, they also showed an altered behavior in the control task. Similarly, they did not show the expected isochrony in the Mental Motor Chronometry Task, when actions pertained the left (but not the right) hand, in absence of any difference in the control task. ConclusionsOur findings reveal altered imagery processes in AN. Specifically, affected participants adopt a third-person, rather than a first-person perspective, even when the task requires to imagine their own body in an internal frame of reference. In other words, participants with AN objectify body stimuli. Different mechanisms (i.e., checking behaviour; mirror self-reflection; altered multisensory integration) can explain such an altered imagery in AN.

Handedness impacts the neural correlates of kinesthetic motor imagery and execution: A FMRI study.

The human brain functional lateralization has been widely studied over the past decades, and neuroimaging studies have shown how activation of motor areas during hand movement execution (ME) is different according to hand dominance. Nevertheless, there is no research directly investigating the effects of the participant's handedness in a motor imagery (MI) and ME task in both right and left‐handed individuals at the cortical and subcortical level. Twenty‐six right‐handed and 25 left‐handed participants were studied using functional magnetic resonance imaging during the imagination and execution of repetitive self‐paced movements of squeezing a ball with their dominant, non‐dominant, and both hands. Results revealed significant statistical difference (p < 0.05) between groups during both the execution and the imagery task with the dominant, non‐dominant, and both hands both at cortical and subcortical level. During ME, left‐handers recruited a spread bilateral network, while in right‐handers, activity was more lateralized. At the critical level, MI between‐group analysis revealed a similar pattern in right and left‐handers showing a bilateral activation for the dominant hand. Differentially at the subcortical level, during MI, only right‐handers showed the involvement of the posterior cerebellum. No significant activity was found for left‐handers. Overall, we showed a partial spatial overlap of neural correlates of MI and ME in motor, premotor, sensory cortices, and cerebellum. Our results highlight differences in the functional organization of motor areas in right and left‐handed people, supporting the hypothesis that MI is influenced by the way people habitually perform motor actions.

A Study on the Effect of Features Obtained From Signal Segments on Classification Success

Successful classification depends on the selection of the distinctive features and the effective channel subset used in the classification. In this study, novel and practical methods are proposed for determining the distinctive features and detecting effective channel subsets in the multi channel classification systems such as EEG. Two different feature extraction methods are compared in the study. The first one is based on classical Wavelet transform and the second is our proposed approach which used the slope of signal segments. Feature vectors are generated from some signal properties such as the mean, standard deviation, numerical integral of the Wavelet coefficients for classical Wavelet transform based feature extraction method. For our proposed method, only the slopes of signal segments are used for the feature vectors. In the proposed Signal Path Slope (SPS) feature extraction method, differently from the classical Wavelet based method, a Savitzky Golay (S-G) filter with an optimal frame length is applied to the signal before segmentation to make the path of the signal more prominent in time domain. In this way, the distinctive classification features are extracted by using S-G filter. For channel selection, an iterative channel selection method based on the classification results which divide the dataset labelled dataset into two groups as % 90 pre-training and %10 pre-test data is proposed. The dataset provided as dataset-3 in BCI competition IV is used in this study. The feature vectors extracted by using the proposed methods are classified for each method with the Support Vector Machine classifier. The results are given comparatively and it is observed that our proposed method has less computational complexity and more successful classification than Wavelet based classical feature extraction methods. The highest classification accuracies of % 67.74 and % 49.27 for subject-1 and subject-2 respectively are obtained with a low dimensional feature vector by proposed SPS feature extraction method. The classification accuracies achieved in the study are increased by % 8.24 for subject-1 and % 14.97 for subject-2 when compared average of the competition results. The significant increase in the success for both subjects shows the consistency of the proposed methods. By this study, it is observed that there is a subject-specific signal pattern related to motor imagery tasks in the brain. This pattern distinctive features is successfully determined by using the proposed methods.

Subject-Independent Classification of Motor Imagery Tasks in EEG Using Multisubject Ensemble CNN

Subject-independent (SI) classification is a major area of investigation in Brain-Computer Interface (BCI) that aims to construct classifiers of users&#x2019; mental states based on collected electroencephalogram (EEG) of independent subjects. Significant inter-subject variabilities in the EEG are among the most challenging issues in designing SI BCI systems. In this work, we propose and examine the utility of Multi-Subject Ensemble Convolutional Neural Network (MS-En-CNN) for SI classification of motor imagery (MI) tasks. The base classifiers used in MS-En-CNN have a fixed CNN architecture (referred to as DeepConvNet) that are trained using data collected from multiple subjects during the training process. In this regard, training subjects are divided into <i>K</i>-folds using which <i>K</i> base DeepConvNets are trained based on data from <i>K</i>-1 folds, whereas the hyperparameter optimization is performed using the held-out fold. We evaluate the performance of the MS-En-CNN on the large open-access MI dataset from the literature, which includes 54 participants and a total number of 21,600 trials. The result shows that the MS-En-CNN achieves the highest single-trial SI classification performance reported on this dataset. In particular, we obtained SI classification performances with average and median accuracies of 85.42% and 86.50% (&#x00B1; 10.16%), respectively. This result exhibits a statistically significant improvement (<i>p</i> &#x003C; 0.001) over the best previously reported result with an average and a median accuracy of 84.19% and 84.50% (&#x00B1;10.08%), respectively.

Using crutches during walking possibly reduces gait imagery accuracy among healthy young and older adults.

[Purpose] Although crutches are widely used in the field of rehabilitation to improve gait performance, patients usually have difficulties using them, and this may increase their risks for falls. This study aimed to define the accuracy of gait imagery during walking with and without crutches, in healthy young and older adults, using the mental chronometry method. [Participants and Methods] Overall, 99 healthy young (mean age, 20.2 ± 1.0 years) and 39 healthy older adults (mean age, 71.3 ± 2.9 years) performed the imagery and execution tasks, which involved walking through a distance of 10 meters both with and without crutches. Using the mental chronometry method, the accuracy of the motor imagery was defined as the difference between the imagery time and the actual execution time. Two-way analysis of variance and one-sample t-tests were performed to evaluate the accuracy of the gait imagery. [Results] Both the young and older adults significantly overestimated their gait speeds when using crutches; the overestimation was larger among the older adults. [Conclusion] The overestimations indicate that participants estimated their gait speeds with crutches to be faster than their actual speeds. Therefore, using crutches decreased the accuracy of gait imagery and might therefore increase an individual’s risk of falling during walking.

Eye Closure Interacts with Music to Influence Vividness and Content of Directed Imagery

Goal-directed, intentional mental imagery generation supports a range of daily self-regulatory activities, such as planning, decision-making, and recreational escapism. Many clinical interventions for mood and anxiety disorders also use imagery and their effectiveness can be affected by an individual's ability to manipulate vividness and content of mental imagery. Prior literature points towards music as a promising candidate to influence imagination in such settings, but basic questions remain regarding how music affects mental imagery and how it interacts with basic, well-established parameters, such as facilitatory effects of eye closure. One hundred participants listened to music and a silent control whilst performing a guided mental imagery task. Specifically, participants saw a short video of a figure journeying towards a landmark and imagined a continuation of the journey with either closed or open eyes. After each trial, participants reported vividness and content of their imagined journeys. Bayesian Mixed Effects Models obtained strong evidence of greater vividness, duration, as well as distance travelled in music conditions compared to silent conditions. Additionally, interactive effects of music and eye closure were found for both vividness and the emotional valence of imagined content, where music effects were disproportionately amplified by eye closure. Findings further support music's potential to manipulate the perceptual, spatial-temporal, as well as emotional sentiment of deliberately generated mental imagery.

Brain Connectivity Changes During Bimanual and Rotated Motor Imagery.

Motor imagery-based brain-computer interface (MI-BCI) currently represents a new trend in rehabilitation. However, individual differences in the responsive frequency bands and a poor understanding of the communication between the ipsilesional motor areas and other regions limit the use of MI-BCI therapy. Objective: Bimanual training has recently attracted attention as it achieves better outcomes as compared to repetitive one-handed training. This study compared the effects of three MI tasks with different visual feedback. Methods: Fourteen healthy subjects performed single hand motor imagery tasks while watching single static hand (traditional MI), single hand with rotation movement (rmMI), and bimanual coordination with a hand pedal exerciser (bcMI). Functional connectivity is estimated by Transfer Entropy (TE) analysis for brain information flow. Results: Brain connectivity of conducting three MI tasks showed that the bcMI demonstrated increased communications from the parietal to the bilateral prefrontal areas and increased contralateral connections between motor-related zones and spatial processing regions. Discussion/Conclusion: The results revealed bimanual coordination operation events increased spatial information and motor planning under the motor imagery task. And the proposed bimanual coordination MI-BCI (bcMI-BCI) can also achieve the effect of traditional motor imagery tasks and promotes more effective connections with different brain regions to better integrate motor-cortex functions for aiding the development of more effective MI-BCI therapy. Clinical and Translational Impact Statement The proposed bcMI-BCI provides more effective connections with different brain areas and integrates motor-cortex functions to promote motor imagery rehabilitation for patients’ impairment.

Motor imagery in amyotrophic lateral Sclerosis: An fMRI study of postural control

BackgroundThe functional reorganization of brain networks sustaining gait is poorly characterized in amyotrophic lateral sclerosis (ALS) despite ample evidence of progressive disconnection between brain regions. The main objective of this fMRI study is to assess gait imagery-specific networks in ALS patients using dynamic causal modeling (DCM) complemented by parametric empirical Bayes (PEB) framework. MethodSeventeen lower motor neuron predominant (LMNp) ALS patients, fourteen upper motor neuron predominant (UMNp) ALS patients and fourteen healthy controls participated in this study. Each subject performed a dual motor imagery task: normal and precision gait. The Movement Imagery Questionnaire (MIQ-rs) and imagery time (IT) were used to evaluate gait imagery in each participant. In a neurobiological computational model, the circuits involved in imagined gait and postural control were investigated by modelling the relationship between normal/precision gait and connection strengths. ResultsBehavioral results showed significant increase in IT in UMNp patients compared to healthy controls (Pcorrected < 0.05) and LMNp (Pcorrected < 0.05). During precision gait, healthy controls activate the model's circuits involved in the imagined gait and postural control. In UMNp, decreased connectivity (inhibition) from basal ganglia (BG) to supplementary motor area (SMA) and from SMA to posterior parietal cortex (PPC) is observed. Contrary to healthy controls, DCM detects no cerebellar-PPC connectivity in neither UMNp nor LMNp ALS. During precision gait, bilateral connectivity (excitability) between SMA and BG is observed in the LMNp group contrary to UMNp and healthy controls. ConclusionsOur findings demonstrate the utility of implementing both DCM and PEB to characterize connectivity patterns in specific patient phenotypes. Our approach enables the identification of specific circuits involved in postural deficits, and our findings suggest a putative excitatory–inhibitory imbalance. More broadly, our data demonstrate how clinical manifestations are underpinned by network-specific disconnection phenomena in ALS.

FGANet: fNIRS-Guided Attention Network for Hybrid EEG-fNIRS Brain-Computer Interfaces.

Non-invasive brain-computer interfaces (BCIs) have been widely used for neural decoding, linking neural signals to control devices. Hybrid BCI systems using electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) have received significant attention for overcoming the limitations of EEG- and fNIRS-standalone BCI systems. However, most hybrid EEG-fNIRS BCI studies have focused on late fusion because of discrepancies in their temporal resolutions and recording locations. Despite the enhanced performance of hybrid BCIs, late fusion methods have difficulty in extracting correlated features in both EEG and fNIRS signals. Therefore, in this study, we proposed a deep learning-based early fusion structure, which combines two signals before the fully-connected layer, called the fNIRS-guided attention network (FGANet). First, 1D EEG and fNIRS signals were converted into 3D EEG and fNIRS tensors to spatially align EEG and fNIRS signals at the same time point. The proposed fNIRS-guided attention layer extracted a joint representation of EEG and fNIRS tensors based on neurovascular coupling, in which the spatially important regions were identified from fNIRS signals, and detailed neural patterns were extracted from EEG signals. Finally, the final prediction was obtained by weighting the sum of the prediction scores of the EEG and fNIRS-guided attention features to alleviate performance degradation owing to delayed fNIRS response. In the experimental results, the FGANet significantly outperformed the EEG-standalone network. Furthermore, the FGANet has 4.0% and 2.7% higher accuracy than the state-of-the-art algorithms in mental arithmetic and motor imagery tasks, respectively.

A Semi-Supervised Progressive Learning Algorithm for Brain-Computer Interface.

Brain-computer interface (BCI) usually suffers from the problem of low recognition accuracy and large calibration time, especially when identifying motor imagery tasks for subjects with indistinct features and classifying fine grained motion control tasks by electroencephalogram (EEG)-electromyogram (EMG) fusion analysis. To fill the research gap, this paper presents an end-to-end semi-supervised learning framework for EEG classification and EEG-EMG fusion analysis. Benefiting from the proposed metric learning based label estimation strategy, sampling criterion and progressive learning scheme, the proposed framework efficiently extracts distinctive feature embedding from the unlabeled EEG samples and achieves a 5.40% improvement on BCI Competition IV Dataset IIa with 80% unlabeled samples and an average 3.35% improvement on two public BCI datasets. By employing synchronous EMG features as pseudo labels for the unlabeled EEG samples, the proposed framework further extracts deep level features of the synergistic complementarity between the EEG signals and EMG features based on the deep encoders, which improves the performance of hybrid BCI (with a 5.53% improvement for the Upper Limb Motion Dataset and an average 4.34% improvement on two hybrid datasets). Moreover, the ablation experiments show that the proposed framework can substantially improve the performance of the deep encoders (with an average 5.53% improvement). The proposed framework not only largely improves the performance of deep networks in the BCI system, but also significantly reduces the calibration time for EEG-EMG fusion analysis, which shows great potential for building an efficient and high-performance hybrid BCI for the motor rehabilitation process.

A Novel Classification Framework Using the Graph Representations of Electroencephalogram for Motor Imagery Based Brain-Computer Interface

The motor imagery (MI) based brain-computer interfaces (BCIs) have been proposed as a potential physical rehabilitation technology. However, the low classification accuracy achievable with MI tasks is still a challenge when building effective BCI systems. We propose a novel MI classification model based on measurement of functional connectivity between brain regions and graph theory. Specifically, motifs describing local network structures in the brain are extracted from functional connectivity graphs. A graph embedding model called Ego-CNNs is then used to build a classifier, which can convert the graph from a structural representation to a fixed-dimensional vector for detecting critical structure in the graph. We validate our proposed method on four datasets, and the results show that our proposed method produces high classification accuracies in two-class classification tasks (92.8% for dataset 1, 93.4% for dataset 2, 96.5% for dataset 3, and 80.2% for dataset 4) and multiclass classification tasks (90.33% for dataset 1). Our proposed method achieves a mean Kappa value of 0.88 across nine participants, which is superior to other methods we compared it to. These results indicate that there is a local structural difference in functional connectivity graphs extracted under different motor imagery tasks. Our proposed method has great potential for motor imagery classification in future studies.

Use of recognition of laterality through implicit motor imagery for the improvement of postural control and balance in subacute stroke patients: a randomized controlled study.

Motor Imagery techniques may be used as a complement to the recovery of motor sequelae after a stroke, as during the evocation of a movement the activation of neuronal circuits involved in the actual execution of the movement occurs. A simple-blind randomized controlled trial was conducted. A total of 38 patients were randomly assigned to a study group. Both groups performed, for four weeks, five weekly sessions of neurorehabilitation and three weekly sessions of experimental or control intervention, respectively.The experimental group training the recognition of laterality, while the control group the recognition of body parts. Participants were evaluated pre and post intervention with posturography parameters -Sway area (AREA), Sway path length (LONG), difference in weigthload between lower limbs (DIFLOAD)-, the Berg Balance scale (BBS), the Barthel Index (BI), the Time Up and Go Test (TUG), the Functional Ambulation Categories (FAC), and the quality-of-life scale for stroke (ECVI-38). After performing the intragroup analysis, statistical significance was obtained for AREA (p < 0.001), LONG (p = 0.04), DIFLOAD (p = 0.02), BBS (p < 0.001), BI (p < 0.001), FAC (p < 0.001), and ECVI-38 (p < 0.001) in the experimental group; and for DIFLOAD (p = 0.01), BBS (p = 0.001), BI (p = 0.001), TUG (p = 0.04), FAC (p = 0.03), and ECVI-38 (p = 0.003) in the control group. In the intergroup analysis, statistical significance was obtained for AREA (p = 0.03), BBS (p = 0.03), FAC (p = 0.02) and ECVI-38 (p = 0.002) at postintervention time. Combined use of physical rehabilitation and recognition of laterality through implicit motor imagery tasks, improves balance and functions related to postural control in subacute stroke patients.

Neurofeedback-guided kinesthetic motor imagery training in Parkinson’s disease: Randomized trial

BackgroundParkinson’s disease (PD) causes difficulty with maintaining the speed, size, and vigor of movements, especially when they are internally generated. We previously proposed that the insula is important in motivating intentional movement via its connections with the dorsomedial frontal cortex (dmFC). We demonstrated that subjects with PD can increase the right insula-dmFC functional connectivity using fMRI-based neurofeedback (NF) combined with kinesthetic motor imagery (MI). The current study is a randomized clinical trial testing whether NF-guided kinesthetic MI training can improve motor performance and increase task-based and resting-state right insula-dmFC functional connectivity in subjects with PD. MethodsWe assigned nondemented subjects with mild PD (Hoehn & Yahr stage ≤ 3) to the experimental kinesthetic MI with NF (MI-NF, n = 22) and active control visual imagery (VI, n = 22) groups. Only the MI-NF group received NF-guided MI training (10–12 runs). The NF signal was based on the right insula-dmFC functional connectivity strength. All subjects also practiced their respective imagery tasks at home daily for 4 weeks. Post-training changes in 1) task-based and resting-state right insula-dmFC functional connectivity were the primary imaging outcomes, and 2) MDS-UPDRS motor exam and motor function scores were the primary and secondary clinical outcomes, respectively. ResultsThe MI-NF group was not significantly different from the VI group in any of the primary imaging or clinical outcome measures. The MI-NF group reported subjective improvement in kinesthetic body awareness. There was significant and comparable improvement only in motor function scores in both groups (secondary clinical outcome). This improvement correlated with NF regulation of the right insula-dmFC functional connectivity only in the MI-NF group. Both groups showed specific training effects in whole-brain functional connectivity with distinct neural circuits supporting kinesthetic motor and visual imagery (exploratory imaging outcome). ConclusionsThe functional connectivity-based NF regulation was unsuccessful, however, both kinesthetic MI and VI practice improved motor function in our cohort with mild PD.

Recursive Estimation of Multichannel Autoregressive Processes in Correlated Noise With Joint Instrumental Variable and Bias Compensation

This paper proposes a new recursive algorithm for estimating multichannel autoregressive (AR) processes in spatially correlated noise using joint extended instrumental variable (EIV) and bias compensation (BC). A weighted least squares solution (WLS) for solving the Yule-Walker (YW) equations from EIV and BC is proposed, while the noise covariance parameters is estimated via the least squares method. A splitting approach is proposed for solving this WLS problem based on matrix splitting, and it is further extended to a recursive algorithm, which can be solved via the variable forgetting factor (VFF)-EIV algorithm. A robust smoothing method for estimating the noise parameters and an adaptive model selection method for controlling the BC contribution are proposed for reducing the estimation variance. The validity of the proposed algorithm is evaluated using both synthetic and real data. Experimental results show that the proposed VFF-EBC algorithm gives higher accuracy than conventional recursive least squares (RLS) algorithm and the VFF-EIV method. It also provides faster tracking speed under sudden changes. The proposed method is applied to the BCI competition IV-2b EEG data set on motor imagery tasks for spectrum and effective connectivity estimation. The high-alpha and beta event-related desynchronization associated with the tasks can be clearly revealed. It was also applied to an auditory odd-ball data from the Open-fMRI database.

A Transformer-Based Approach Combining Deep Learning Network and Spatial-Temporal Information for Raw EEG Classification.

The attention mechanism of the Transformer has the advantage of extracting feature correlation in the long-sequence data and visualizing the model. As time-series data, the spatial and temporal dependencies of the EEG signals between the time points and the different channels contain important information for accurate classification. So far, Transformer-based approaches have not been widely explored in motor-imagery EEG classification and visualization, especially lacking general models based on cross-individual validation. Taking advantage of the Transformer model and the spatial-temporal characteristics of the EEG signals, we designed Transformer-based models for classifications of motor imagery EEG based on the PhysioNet dataset. With 3s EEG data, our models obtained the best classification accuracy of 83.31%, 74.44%, and 64.22% on two-, three-, and four-class motor-imagery tasks in cross-individual validation, which outperformed other state-of-the-art models by 0.88%, 2.11%, and 1.06%. The inclusion of the positional embedding modules in the Transformer could improve the EEG classification performance. Furthermore, the visualization results of attention weights provided insights into the working mechanism of the Transformer-based networks during motor imagery tasks. The topography of the attention weights revealed a pattern of event-related desynchronization (ERD) which was consistent with the results from the spectral analysis of Mu and beta rhythm over the sensorimotor areas. Together, our deep learning methods not only provide novel and powerful tools for classifying and understanding EEG data but also have broad applications for brain-computer interface (BCI) systems.