Enhancement of left-right sensorimotor EEG differences during feedback-regulated motor imagery

Iteratively Calibratable Network for Reliable EEG-Based Robotic Arm Control

Robotic arms are increasingly being utilized in shared workspaces, which necessitates the accurate interpretation of human intentions for both efficiency and safety. Electroencephalogram (EEG) signals, commonly employed to measure brain activity, offer a direct communication channel between humans and robotic arms. However, the ambiguous and unstable characteristics of EEG signals, coupled with their widespread distribution, make it challenging to collect sufficient data and hinder the calibration performance for new signals, thereby reducing the reliability of EEG-based applications. To address these issues, this study proposes an iteratively calibratable network aimed at enhancing the reliability and efficiency of EEG-based robotic arm control systems. The proposed method integrates feature inputs with network expansion techniques. This integration allows a network trained on an extensive initial dataset to adapt effectively to new users during calibration. Additionally, our approach combines motor imagery and speech imagery datasets to increase not only its intuitiveness but also the number of command classes. The evaluation is conducted in a pseudo-online manner, with a robotic arm operating in real-time to collect data, which is then analyzed offline. The evaluation results demonstrated that the proposed method outperformed the comparison group in 10 sessions and demonstrated competitive results when the two paradigms were combined. Therefore, it was confirmed that the network can be calibrated and personalized using only the new data from new users.

Effects of visual-electrotactile stimulation feedback on brain functional connectivity during motor imagery practice

The use of neurofeedback is an important aspect of effective motor rehabilitation as it offers real-time sensory information to promote neuroplasticity. However, there is still limited knowledge about how the brain's functional networks reorganize in response to such feedback. To address this gap, this study investigates the reorganization of the brain network during motor imagery tasks when subject to visual stimulation or visual-electrotactile stimulation feedback. This study can provide healthcare professionals with a deeper understanding of the changes in the brain network and help develop successful treatment approaches for brain-computer interface-based motor rehabilitation applications. We examine individual edges, nodes, and the entire network, and use the minimum spanning tree algorithm to construct a brain network representation using a functional connectivity matrix. Furthermore, graph analysis is used to detect significant features in the brain network that might arise in response to the feedback. Additionally, we investigate the power distribution of brain activation patterns using power spectral analysis and evaluate the motor imagery performance based on the classification accuracy. The results showed that the visual and visual-electrotactile stimulation feedback induced subject-specific changes in brain activation patterns and network reorganization in the [Formula: see text] band. Thus, the visual-electrotactile stimulation feedback significantly improved the integration of information flow between brain regions associated with motor-related commands and higher-level cognitive functions, while reducing cognitive workload in the sensory areas of the brain and promoting positive emotions. Despite these promising results, neither neurofeedback modality resulted in a significant improvement in classification accuracy, compared with the absence of feedback. These findings indicate that multimodal neurofeedback can modulate imagery-mediated rehabilitation by enhancing motor-cognitive communication and reducing cognitive effort. In future interventions, incorporating this technique to ease cognitive demands for participants could be crucial for maintaining their motivation to engage in rehabilitation.

Predicting Motor Imagery BCI Performance Based on EEG Microstate Analysis

Motor imagery (MI) electroencephalography (EEG) is natural and comfortable for controllers, and has become a research hotspot in the field of the brain-computer interface (BCI). Exploring the inter-subject MI-BCI performance variation is one of the fundamental problems in MI-BCI application. EEG microstates with high spatiotemporal resolution and multichannel information can represent brain cognitive function. In this paper, four EEG microstates (MS1, MS2, MS3, MS4) were used in the analysis of the differences in the subjects' MI-BCI performance, and the four microstate feature parameters (the mean duration, the occurrences per second, the time coverage ratio, and the transition probability) were calculated. The correlation between the resting-state EEG microstate feature parameters and the subjects' MI-BCI performance was measured. Based on the negative correlation of the occurrence of MS1 and the positive correlation of the mean duration of MS3, a resting-state microstate predictor was proposed. Twenty-eight subjects were recruited to participate in our MI experiments to assess the performance of our resting-state microstate predictor. The experimental results show that the average area under curve (AUC) value of our resting-state microstate predictor was 0.83, and increased by 17.9% compared with the spectral entropy predictor, representing that the microstate feature parameters can better fit the subjects' MI-BCI performance than spectral entropy predictor. Moreover, the AUC of microstate predictor is higher than that of spectral entropy predictor at both the single-session level and average level. Overall, our resting-state microstate predictor can help MI-BCI researchers better select subjects, save time, and promote MI-BCI development.

Archery under the (electroencephalography-)hood: Theta-lateralization as a marker for motor learning

An intrinsic characteristic of the motor system is the preference of one side of the body. Lateralization is found in motor behavior and in the structural and functional correlates of cortical motor networks. While genetic factors have been elucidated as mechanisms leading to such asymmetries, findings in motor learning and experience from clinical experience demonstrate considerable additional plasticity during the lifespan. If and how functional lateralization develops in short timeframes during training of motor skills involving both sides of the body is still largely unclear. In the present exploratory study, we investigate lateralization of theta-, alpha- and beta-band oscillations during training of an ecologically valid skill - archery. We relate lateralization shift to performance improvement and elucidate the underlying cortical areas. To this end, healthy participants without any previous experience in archery underwent intensive training with 100 shots on each of three days. 64-channel electroencephalography was recorded simultaneously during the individual shots. We found that a central-parietal theta lateralization shift to the left immediately before the shot was associated with performance improvement. Lateralization of alpha or beta did not yield a significant association. Importantly, areas of maximum activation were not identical with areas showing the strongest associations with performance improvement. These data suggest that learning a complex bimanual motor skill is associated with a shift of theta-band oscillations to the left in central-parietal areas. The relationship with performance improvement may reflect increased cortical efficiency of task-relevant processing.

Event-Related Potentials Analysis of the Effects of Discontinuous Short-Term Fine Motor Imagery on Motor Execution

In this study, event-related potentials and neurobehavioral measurements were used to investigate the effects of discontinuous short-term fine motor imagery (MI), a paradigm of finger sequential MI training interspersed with no-MI that occurs within 1 hr, on fine finger motor execution. The event-related potentials revealed that there were significant differences in the P300 between the fine MI training and the no-MI training. There were also significant changes in the P200 between fine motor execution of familiar tasks after MI training and fine motor execution of unfamiliar tasks without MI training. Neurobehavioral data revealed that the fine MI enhanced fine motor execution. These findings may suggest that discontinuous short-term fine MI could be useful in improving fine motor skills.

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.

BCI-Based Control for Ankle Exoskeleton T-FLEX: Comparison of Visual and Haptic Stimuli with Stroke Survivors

Brain–computer interface (BCI) remains an emerging tool that seeks to improve the patient interaction with the therapeutic mechanisms and to generate neuroplasticity progressively through neuromotor abilities. Motor imagery (MI) analysis is the most used paradigm based on the motor cortex’s electrical activity to detect movement intention. It has been shown that motor imagery mental practice with movement-associated stimuli may offer an effective strategy to facilitate motor recovery in brain injury patients. In this sense, this study aims to present the BCI associated with visual and haptic stimuli to facilitate MI generation and control the T-FLEX ankle exoskeleton. To achieve this, five post-stroke patients (55–63 years) were subjected to three different strategies using T-FLEX: stationary therapy (ST) without motor imagination, motor imagination with visual stimulation (MIV), and motor imagination with visual-haptic inducement (MIVH). The quantitative characterization of both BCI stimuli strategies was made through the motor imagery accuracy rate, the electroencephalographic (EEG) analysis during the MI active periods, the statistical analysis, and a subjective patient’s perception. The preliminary results demonstrated the viability of the BCI-controlled ankle exoskeleton system with the beta rebound, in terms of patient’s performance during MI active periods and satisfaction outcomes. Accuracy differences employing haptic stimulus were detected with an average of 68% compared with the 50.7% over only visual stimulus. However, the power spectral density (PSD) did not present changes in prominent activation of the MI band but presented significant variations in terms of laterality. In this way, visual and haptic stimuli improved the subject’s MI accuracy but did not generate differential brain activity over the affected hemisphere. Hence, long-term sessions with a more extensive sample and a more robust algorithm should be carried out to evaluate the impact of the proposed system on neuronal and motor evolution after stroke.

Does Real-Time Feedback Affect Sensorimotor EEG Patterns in Routine Motor Imagery Practice?

Background. Motor imagery engages much of the same neural circuits as an overt movement. Therefore, the mental rehearsal of movements is often used to supplement physical training and might aid motor neurorehabilitation after stroke. One attempt to capture the brain’s involvement in imagery involves the use, as a marker, of the depression or event-related desynchronization (ERD) of thalamocortical sensorimotor rhythms found in a human electroencephalogram (EEG). Using fast real-time processing, it is possible to make the subject aware of their own brain reactions or—even better—to turn them into actions through a technology called the brain–computer interface (BCI). However, it remains unclear whether BCI-enabled imagery facilitates a stronger or qualitatively different brain response compared to the open-loop training. Methods. Seven healthy volunteers who were experienced in both closed and open-loop motor imagery took part in six experimental sessions over a period of 4.5 months, in which they performed kinesthetic imagery of a previously known set of finger and arm movements with simultaneous 30-channel EEG acquisition. The first and the last session mostly consisted of feedback trials in which the subjects were presented with the classification results of the EEG patterns in real time; during the other sessions, no feedback was provided. Spatiotemporal and amplitude features of the ERD patterns concomitant with imagery were compared across experimental days and between feedback conditions using linear mixed-effects modeling. Results. The main spatial sources of ERD appeared to be highly stable across the six experimental days, remaining nearly identical in five of seven subjects (Pearson’s ρ > 0.94). Only in one subject did the spatial pattern of activation statistically significantly differ (p = 0.009) between the feedback and no-feedback conditions. Real-time visual feedback delivered through the BCI did not significantly increase the ERD strength. Conclusion. The results imply that the potential benefits of MI could be yielded by well-habituated subjects with a simplified open-loop setup, e.g., through at-home self-practice.

Midfrontal theta oscillation encodes haptic delay

Haptic technologies aim to simulate tactile or kinesthetic interactions with a physical or virtual environment in order to enhance user experience and/or performance. However, due to stringent communication and computational needs, the user experience is influenced by delayed haptic feedback. While delayed feedback is well understood in the visual and auditory modalities, little research has systematically examined the neural correlates associated with delayed haptic feedback. In this paper, we used electroencephalography (EEG) to study sensory and cognitive neural correlates caused by haptic delay during passive and active tasks performed using a haptic device and a computer screen. Results revealed that theta power oscillation was significantly higher at the midfrontal cortex under the presence of haptic delay. Sensory correlates represented by beta rebound were found to be similar in the passive task and different in the active task under the delayed and synchronous conditions. Additionally, the event related potential (ERP) P200 component is modulated under the haptic delay condition during the passive task. The P200 amplitude significantly reduced in the last 20% of trials during the passive task and in the absence of haptic delay. Results suggest that haptic delay could be associated with increased cognitive control processes including multi-sensory divided attention followed by conflict detection and resolution with an earlier detection during the active task. Additionally, haptic delay tends to generate greater perceptual attention that does not significantly decay across trials during the passive task.

Distinct modulation of mu and beta rhythm desynchronization during observation of embodied fake hand rotation

The rubber hand illusion (RHI) is a phenomenon whereby participants recognize a fake hand as their own. Studies have examined the effects of observing fake hand movements after the RHI on brain sensorimotor activity, although results remain controversial. To address these discrepancies, we investigated the effects of observation of fake hand rotation after the RHI on sensorimotor mu (μ: 8-13 Hz) and beta (β: 15-25 Hz) rhythm event-related desynchronization (ERD) using electroencephalography (EEG). Questionnaire results and proprioceptive drift revealed that the RHI occurred in participants when their invisible hand and fake visible hand were stroked synchronously but not during asynchronous stroking. Independent component (IC) clustering from EEG data during movement observation identified three IC clusters, including the right sensorimotor, left sensorimotor, and left occipital cluster. In the right sensorimotor cluster, we observed distinct modulation of μ and β ERD during fake hand rotation. Illusory ownership over the fake hand enhanced μ ERD but inversely attenuated β ERD. Further, the extent of μ ERD correlated with proprioceptive drift, but not with questionnaire ratings, whereas the converse results were obtained for β ERD. No ownership-dependent ERD modulation was detected in the left sensorimotor cluster. Alpha (α: 8-13 Hz) rhythm ERD of the left occipital cluster was smaller in the synchronous condition than in the asynchronous condition, but α ERD was not correlated with questionnaire rating or drift. These findings suggest that observing embodied fake hand rotation induces distinct cortical processing in sensorimotor brain areas.

Coordinated Reset Vibrotactile Stimulation Induces Sustained Cumulative Benefits in Parkinson's Disease

BACKGROUND

Abnormal synchronization of neuronal activity in dopaminergic circuits is related to motor impairment in Parkinson's disease (PD). Vibrotactile coordinated reset (vCR) fingertip stimulation aims to counteract excessive synchronization and induce sustained unlearning of pathologic synaptic connectivity and neuronal synchrony. Here, we report two clinical feasibility studies that examine the effect of regular and noisy vCR stimulation on PD motor symptoms. Additionally, in one clinical study (study 1), we examine cortical beta band power changes in the sensorimotor cortex. Lastly, we compare these clinical results in relation to our computational findings.

METHODS

Study 1 examines six PD patients receiving noisy vCR stimulation and their cortical beta power changes after 3 months of daily therapy. Motor evaluations and at-rest electroencephalographic (EEG) recordings were assessed off medication pre- and post-noisy vCR. Study 2 follows three patients for 6+ months, two of whom received daily regular vCR and one patient from study 1 who received daily noisy vCR. Motor evaluations were taken at baseline, and follow-up visits were done approximately every 3 months. Computationally, in a network of leaky integrate-and-fire (LIF) neurons with spike timing-dependent plasticity, we study the differences between regular and noisy vCR by using a stimulus model that reproduces experimentally observed central neuronal phase locking.

RESULTS

Clinically, in both studies, we observed significantly improved motor ability. EEG recordings observed from study 1 indicated a significant decrease in off-medication cortical sensorimotor high beta power (21-30 Hz) at rest after 3 months of daily noisy vCR therapy. Computationally, vCR and noisy vCR cause comparable parameter-robust long-lasting synaptic decoupling and neuronal desynchronization.

CONCLUSION

In these feasibility studies of eight PD patients, regular vCR and noisy vCR were well tolerated, produced no side effects, and delivered sustained cumulative improvement of motor performance, which is congruent with our computational findings. In study 1, reduction of high beta band power over the sensorimotor cortex may suggest noisy vCR is effectively modulating the beta band at the cortical level, which may play a role in improved motor ability. These encouraging therapeutic results enable us to properly plan a proof-of-concept study.

Visual-Electrotactile Stimulation Feedback to Improve Immersive Brain-Computer Interface Based on Hand Motor Imagery

In the aging society, the number of people suffering from vascular disorders is rapidly increasing and has become a social problem. The death rate due to stroke, which is the second leading cause of global mortality, has increased by 40% in the last two decades. Stroke can also cause paralysis. Of late, brain-computer interfaces (BCIs) have been garnering attention in the rehabilitation field as assistive technology. A BCI for the motor rehabilitation of patients with paralysis promotes neural plasticity, when subjects perform motor imagery (MI). Feedback, such as visual and proprioceptive, influences brain rhythm modulation to contribute to MI learning and motor function restoration. Also, virtual reality (VR) can provide powerful graphical options to enhance feedback visualization. This work aimed to improve immersive VR-BCI based on hand MI, using visual-electrotactile stimulation feedback instead of visual feedback. The MI tasks include grasping, flexion/extension, and their random combination. Moreover, the subjects answered a system perception questionnaire after the experiments. The proposed system was evaluated with twenty able-bodied subjects. Visual-electrotactile feedback improved the mean classification accuracy for the grasping (93.00%  $\pm$  3.50%) and flexion/extension (95.00%  $\pm$  5.27%) MI tasks. Additionally, the subjects achieved an acceptable mean classification accuracy (maximum of 86.5%  $\pm$  5.80%) for the random MI task, which required more concentration. The proprioceptive feedback maintained lower mean power spectral density in all channels and higher attention levels than those of visual feedback during the test trials for the grasping and flexion/extension MI tasks. Also, this feedback generated greater relative power in the $\mu$ -band for the premotor cortex, which indicated better MI preparation. Thus, electrotactile stimulation along with visual feedback enhanced the immersive VR-BCI classification accuracy by 5.5% and 4.5% for the grasping and flexion/extension MI tasks, respectively, retained the subject’s attention, and eased MI better than visual feedback alone.

A review of user training methods in brain computer interfaces based on mental tasks

Mental-Tasks based Brain-Computer Interfaces (MT-BCIs) allow their users to interact with an external device solely by using brain signals produced through mental tasks. While MT-BCIs are promising for many applications, they are still barely used outside laboratories due to their lack of reliability. MT-BCIs require their users to develop the ability to self-regulate specific brain signals. However, the human learning process to control a BCI is still relatively poorly understood and how to optimally train this ability is currently under investigation. Despite their promises and achievements, traditional training programs have been shown to be sub-optimal and could be further improved. In order to optimize user training and improve BCI performance, human factors should be taken into account. An interdisciplinary approach should be adopted to provide learners with appropriate and/or adaptive training. In this article, we provide an overview of existing methods for MT-BCI user training - notably in terms of environment, instructions, feedback and exercises. We present a categorization and taxonomy of these training approaches, provide guidelines on how to choose the best methods and identify open challenges and perspectives to further improve MT-BCI user training.

Novel hybrid brain-computer interface system based on motor imagery and P300

Motor imagery (MI) is a mental representation of motor behavior and has been widely used in electroencephalogram based brain-computer interfaces (BCIs). Several studies have demonstrated the efficacy of MI-based BCI-feedback training in post-stroke rehabilitation. However, in the earliest stage of the training, calibration data typically contain insufficient discriminability, resulting in unreliable feedback, which may decrease subjects' motivation and even hinder their training. To improve the performance in the early stages of MI training, a novel hybrid BCI paradigm based on MI and P300 is proposed in this study. In this paradigm, subjects are instructed to imagine writing the Chinese character following the flash order of the desired Chinese character displayed on the screen. The event-related desynchronization/synchronization (ERD/ERS) phenomenon is produced with writing based on one's imagination. Simultaneously, the P300 potential is evoked by the flash of each stroke. Moreover, a fusion method of P300 and MI classification is proposed, in which unreliable P300 classifications are corrected by reliable MI classifications. Twelve healthy naïve MI subjects participated in this study. Results demonstrated that the proposed hybrid BCI paradigm yielded significantly better performance than the single-modality BCI paradigm. The recognition accuracy of the fusion method is significantly higher than that of P300 (p < 0.05) and MI (p < 0.01). Moreover, the training data size can be reduced through fusion of these two modalities.

Walking Imagery Evaluation in Brain Computer Interfaces via a Multi-View Multi-Level Deep Polynomial Network

Brain-computer interfaces based on motor imagery (MI) have been widely used to support the rehabilitation of motor functions of the upper limbs rather than lower limbs. This is probably because it is more difficult to detect the brain activities of lower limb MI. In order to reliably detect the brain activities of lower limbs to restore or improve the walking ability of the disabled, we propose a new paradigm of walking imagery (WI) in a virtual environment (VE), in order to elicit the reliable brain activities and achieve a significant training effect. First, we extract and fuse both the spatial and time-frequency features as a multi-view feature to represent the patterns in the brain activity. Second, we design a multi-view multi-level deep polynomial network (MMDPN) to explore the complementarity among the features so as to improve the detection of walking from an idle state. Our extensive experimental results show that the VE-based paradigm significantly performs better than the traditional text-based paradigm. In addition, the VE-based paradigm can effectively help users to modulate the brain activities and improve the quality of electroencephalography signals. We also observe that the MMDPN outperforms other deep learning methods in terms of classification performance.

Feasibility and safety of shared EEG/EOG and vision-guided autonomous whole-arm exoskeleton control to perform activities of daily living

Arm and finger paralysis, e.g. due to brain stem stroke, often results in the inability to perform activities of daily living (ADLs) such as eating and drinking. Recently, it was shown that a hybrid electroencephalography/electrooculography (EEG/EOG) brain/neural hand exoskeleton can restore hand function to quadriplegics, but it was unknown whether such control paradigm can be also used for fluent, reliable and safe operation of a semi-autonomous whole-arm exoskeleton restoring ADLs. To test this, seven abled-bodied participants (seven right-handed males, mean age 30 ± 8 years) were instructed to use an EEG/EOG-controlled whole-arm exoskeleton attached to their right arm to perform a drinking task comprising multiple sub-tasks (reaching, grasping, drinking, moving back and releasing a cup). Fluent and reliable control was defined as average 'time to initialize' (TTI) execution of each sub-task below 3 s with successful initializations of at least 75% of sub-tasks within 5 s. During use of the system, no undesired side effects were reported. All participants were able to fluently and reliably control the vision-guided autonomous whole-arm exoskeleton (average TTI 2.12 ± 0.78 s across modalities with 75% successful initializations reached at 1.9 s for EOG and 4.1 s for EEG control) paving the way for restoring ADLs in severe arm and hand paralysis.

Sensory Stimulation Training for BCI System Based on Somatosensory Attentional Orientation

In this study, we propose a sensory stimulation training (SST) approach to improve the performance of a brain-computer interface (BCI) based on somatosensory attentional orientation (SAO). In this BCI, subjects imagine the tactile sensation and maintain the attention on the corresponding hand as if there was a tactile stimulus on the wrist skin. Twenty BCI naïve subjects were recruited and randomly divided into a Control-Group and an SST-Group. In the Control-Group, subjects performed left hand and right hand SAO tasks in six consecutive runs (with 40 trials in each run), divided into three blocks with each having two runs. For the SST-Group, two runs included real tactile stimulation to the left or right hand (SST training block), between the first two (Pre-SST block) and the last two SAO runs (Post-SST block). Results showed that the SST-Group had a significantly improved performance of 9.4% between the last block and the first block after SST training (F_(2,18) = 11.11, p = 0.0007); in contrast, no significant difference was found in the Control-Group between the first, second, and the last block (F_(2,18) = 2.07, p = 0.1546), indicating no learning effect. The tactile sensation-induced oscillatory dynamics were similar to those induced by SAO. In the SST-Group, R² discriminative information was enhanced around the somatosensory cortex due to the real sensory stimulation as compared with that in the Control-Group. Since the SAO mental task is inherently an internal process, the proposed SST method is meant as an adjuvant to SAO to facilitate subjects in achieving an initial SAO-based BCI control.

Mapping the Cortical Network Arising From Up-Regulated Amygdaloidal Activation Using -Louvain Algorithm

The amygdala plays an important role in emotion processing. Several studies have proved that its activation can be regulated by real-time functional magnetic resonance imaging (rtfMRI)-based neurofeedback training. However, although studies have found brain regions that are functionally closely connected to the amygdala in the cortex, it is not clear whether these brain regions and the amygdala are structurally closely connected, and if they show the same training effect as the amygdala in the process of emotional regulation. In this paper, we instructed subjects to up-regulate the activation of the left amygdala (LA) through rtfMRI-based neurofeedback training. In order to fuse multimodal imaging data, we introduced a network analysis method called the -Louvain clustering algorithm. This method was used to integrate multimodal data from the training experiment and construct an LA-cortical network. Correlation analysis and main-effect analysis were conducted to determine the signal covariance associated with the activation of the target area; ultimately, we identified the left temporal pole superior as the amygdaloidal-cortical network region. As a deep nucleus in the brain, the treatment and stimulation of the amygdala remains challenging. Our results provide new insights for the regulation of activation in a deep nucleus using more neurofeedback techniques.

Target-directed motor imagery of the lower limb enhances event-related desynchronization

Event-related desynchronization/synchronization (ERD/S) is an electroencephalogram (EEG) feature widely used as control signals for Brain-Computer Interfaces (BCIs). Nevertheless, the underlying neural mechanisms and functions of ERD/S are largely unknown, thus investigating them is crucial to improve the reliability of ERD/S-based BCIs. This study aimed to identify Motor Imagery (MI) conditions that enhance ERD/S. We investigated following three questions: 1) whether target-directed MI affects ERD/S, 2) whether MI with sound imagery affects ERD/S, and 3) whether ERD/S has a body part dependency of MI. Nine participants took part in the experiments of four MI conditions; they were asked to imagine right foot dorsiflexion (F), right foot dorsiflexion and the sound of a bass drum when the sole touched the floor (FS), right leg extension (L), and right leg extension directed toward a soccer ball (LT). Statistical comparison revealed that there were significant differences between conditions L and LT in beta-band ERD and conditions F and L in beta-band ERS. These results suggest that mental rehearsal of target-directed lower limb movement without real sensory stimuli can enhance beta-band ERD; furthermore, MI of foot dorsiflexion induces significantly larger beta-band ERS than that of leg extension. These findings could be exploited for the training of BCIs such as powered prosthetics for disabled person and neurorehabilitation system for stroke patients.

Brain-actuated gait trainer with visual and proprioceptive feedback

OBJECTIVE

Brain-machine interfaces (BMIs) have been proposed in closed-loop applications for neuromodulation and neurorehabilitation. This study describes the impact of different feedback modalities on the performance of an EEG-based BMI that decodes motor imagery (MI) of leg flexion and extension.

APPROACH

We executed experiments in a lower-limb gait trainer (the legoPress) where nine able-bodied subjects participated in three consecutive sessions based on a crossover design. A random forest classifier was trained from the offline session and tested online with visual and proprioceptive feedback, respectively. Post-hoc classification was conducted to assess the impact of feedback modalities and learning effect (an improvement over time) on the simulated trial-based performance. Finally, we performed feature analysis to investigate the discriminant power and brain pattern modulations across the subjects.

MAIN RESULTS

(i) For real-time classification, the average accuracy was [Formula: see text]% and [Formula: see text]% for the two online sessions. The results were significantly higher than chance level, demonstrating the feasibility to distinguish between MI of leg extension and flexion. (ii) For post-hoc classification, the performance with proprioceptive feedback ([Formula: see text]%) was significantly better than with visual feedback ([Formula: see text]%), while there was no significant learning effect. (iii) We reported individual discriminate features and brain patterns associated to each feedback modality, which exhibited differences between the two modalities although no general conclusion can be drawn.

SIGNIFICANCE

The study reported a closed-loop brain-controlled gait trainer, as a proof of concept for neurorehabilitation devices. We reported the feasibility of decoding lower-limb movement in an intuitive and natural way. As far as we know, this is the first online study discussing the role of feedback modalities in lower-limb MI decoding. Our results suggest that proprioceptive feedback has an advantage over visual feedback, which could be used to improve robot-assisted strategies for motor training and functional recovery.

Progress in EEG-Based Brain Robot Interaction Systems

The most popular noninvasive Brain Robot Interaction (BRI) technology uses the electroencephalogram- (EEG-) based Brain Computer Interface (BCI), to serve as an additional communication channel, for robot control via brainwaves. This technology is promising for elderly or disabled patient assistance with daily life. The key issue of a BRI system is to identify human mental activities, by decoding brainwaves, acquired with an EEG device. Compared with other BCI applications, such as word speller, the development of these applications may be more challenging since control of robot systems via brainwaves must consider surrounding environment feedback in real-time, robot mechanical kinematics, and dynamics, as well as robot control architecture and behavior. This article reviews the major techniques needed for developing BRI systems. In this review article, we first briefly introduce the background and development of mind-controlled robot technologies. Second, we discuss the EEG-based brain signal models with respect to generating principles, evoking mechanisms, and experimental paradigms. Subsequently, we review in detail commonly used methods for decoding brain signals, namely, preprocessing, feature extraction, and feature classification, and summarize several typical application examples. Next, we describe a few BRI applications, including wheelchairs, manipulators, drones, and humanoid robots with respect to synchronous and asynchronous BCI-based techniques. Finally, we address some existing problems and challenges with future BRI techniques.

Simultaneous EEG-fNIRS reveals how age and feedback affect motor imagery signatures

Stroke frequently results in motor impairment. Motor imagery (MI), the mental practice of movements, has been suggested as a promising complement to other therapeutic approaches facilitating motor rehabilitation. Of particular potential is the combination of MI with neurofeedback (NF). However, MI NF protocols have been largely optimized only in younger healthy adults, although strokes occur more frequently in older adults. The present study examined the influence of age on the neural correlates of MI supported by electroencephalogram (EEG)-based NF and on the neural correlates of motor execution. We adopted a multimodal neuroimaging framework focusing on EEG-derived event-related desynchronization (ERD%) and oxygenated (HbO) and deoxygenated hemoglobin (HbR) concentrations simultaneously acquired using functional near-infrared spectroscopy (fNIRS). ERD%, HbO concentration and HbR concentration were compared between younger (mean age: 24.4 years) and older healthy adults (mean age: 62.6 years). During MI, ERD% and HbR concentration were less lateralized in older adults than in younger adults. The lateralization-by-age interaction was not significant for movement execution. Moreover, EEG-based NF was related to an increase in task-specific activity when compared to the absence of feedback in both older and younger adults. Finally, significant modulation correlations were found between ERD% and hemodynamic measures despite the absence of significant amplitude correlations. Overall, the findings suggest a complex relationship between age and movement-related activity in electrophysiological and hemodynamic measures. Our results emphasize that the age of the actual end-user should be taken into account when designing neurorehabilitation protocols.

The Importance of Visual Feedback Design in BCIs; from Embodiment to Motor Imagery Learning

Brain computer interfaces (BCIs) have been developed and implemented in many areas as a new communication channel between the human brain and external devices. Despite their rapid growth and broad popularity, the inaccurate performance and cost of user-training are yet the main issues that prevent their application out of the research and clinical environment. We previously introduced a BCI system for the control of a very humanlike android that could raise a sense of embodiment and agency in the operators only by imagining a movement (motor imagery) and watching the robot perform it. Also using the same setup, we further discovered that the positive bias of subjects' performance both increased their sensation of embodiment and improved their motor imagery skills in a short period. In this work, we studied the shared mechanism between the experience of embodiment and motor imagery. We compared the trend of motor imagery learning when two groups of subjects BCI-operated different looking robots, a very humanlike android's hands and a pair of metallic gripper. Although our experiments did not show a significant change of learning between the two groups immediately during one session, the android group revealed better motor imagery skills in the follow up session when both groups repeated the task using the non-humanlike gripper. This result shows that motor imagery skills learnt during the BCI-operation of humanlike hands are more robust to time and visual feedback changes. We discuss the role of embodiment and mirror neuron system in such outcome and propose the application of androids for efficient BCI training.

Modulation of ERD/S by having a conscious target during lower-extremity motor imagery

In the field of neurorehabilitation with brain-computer interfaces (BCIs) technology, an EEG feature, event-related desynchronization/synchronization (ERD/S) caused by motor imagery (MI) is widely used for estimating human motor intention. However, sufficient neurofeedback training is required for the use of the MI-based BCI system, because the ability to generate ERD/S is highly dependent on individuals. To find an effective MI condition for the BCI system, we hypothesize that having a conscious target during MI would enhance the extent of ERD/S. In the experiments, we investigated the individual effect of two types of MIs: leg extension (L) and leg extension with a conscious target (i.e., kicking a ball (KB)) on the resultant ERD/S. We evaluated time-frequency maps of ERD/S and statistically compared these two conditions (i.e., L and KB). As a result, a significant difference was found in beta-ERD (paired t-test, p <; 0.01), while there were no significant differences in mu-ERD and beta-ERS. These results suggest that having a conscious target during lower extremity MI would strengthen the ERD in beta frequency band compared to the case without target.

Electroencephalographic neurofeedback: Level of evidence in mental and brain disorders and suggestions for good clinical practice

The technique of electroencephalographic neurofeedback (EEG NF) emerged in the 1970s and is a technique that measures a subject's EEG signal, processes it in real time, extracts a parameter of interest and presents this information in visual or auditory form. The goal is to effectuate a behavioural modification by modulating brain activity. The EEG NF opens new therapeutic possibilities in the fields of psychiatry and neurology. However, the development of EEG NF in clinical practice requires (i) a good level of evidence of therapeutic efficacy of this technique, (ii) a good practice guide for this technique. Firstly, this article investigates selected trials with the following criteria: study design with controlled, randomized, and open or blind protocol, primary endpoint related to the mental and brain disorders treated and assessed with standardized measurement tools, identifiable EEG neurophysiological targets, underpinned by pathophysiological relevance. Trials were found for: epilepsies, migraine, stroke, chronic insomnia, attentional-deficit/hyperactivity disorder (ADHD), autism spectrum disorder, major depressive disorder, anxiety disorders, addictive disorders, psychotic disorders. Secondly, this article investigates the principles of neurofeedback therapy in line with learning theory. Different underlying therapeutic models are presented didactically between two continua: a continuum between implicit and explicit learning and a continuum between the biomedical model (centred on "the disease") and integrative biopsychosocial model of health (centred on "the illness"). The main relevant learning model is to link neurofeedback therapy with the field of cognitive remediation techniques. The methodological specificity of neurofeedback is to be guided by biologically relevant neurophysiological parameters. Guidelines for good clinical practice of EEG NF concerning technical issues of electrophysiology and of learning are suggested. These require validation by institutional structures for the clinical practice of EEG NF.

Prediction of motor imagery based brain computer interface performance using a reaction time test

Brain computer interfaces (BCIs) enable human brains to interact directly with machines. Motor imagery based BCI (MI-BCI) encodes the motor intentions of human agents and provides feedback accordingly. However, 15-30% of people are not able to perform vivid motor imagery. To save time and monetary resources, a number of predictors have been proposed to screen for users with low BCI aptitude. While the proposed predictors provide some level of correlation with MI-BCI performance, simple, objective and accurate predictors are currently not available. Thus, in this study we have examined the utility of a simple reaction time (SRT) test for predicting MI-BCI performance. We enrolled 10 subjects and measured their motor imagery performance with either visual or proprioceptive feedback. Their reaction time was also measured using a SRT test. The results show a significant negative correlation (r ≈ -0.67) between SRT and MI-BCI performance. Therefore SRT may be used as a simple and reliable predictor of MI-BCI performance.

Lateralization patterns of covert but not overt movements change with age: An EEG neurofeedback study

The mental practice of movements has been suggested as a promising add-on therapy to facilitate motor recovery after stroke. In the case of mentally practised movements, electroencephalogram (EEG) can be utilized to provide feedback about an otherwise covert act. The main target group for such an intervention are elderly patients, though research so far is largely focused on young populations (<30 years). The present study therefore aimed to examine the influence of age on the neural correlates of covert movements (CMs) in a real-time EEG neurofeedback framework. CM-induced event-related desynchronization (ERD) was studied in young (mean age: 23.6 years) and elderly (mean age: 62.7 years) healthy adults. Participants performed covert and overt hand movements. CMs were based on kinesthetic motor imagery (MI) or quasi-movements (QM). Based on previous studies investigating QM in the mu frequency range (8-13Hz) QM were expected to result in more lateralized ERD% patterns and accordingly higher classification accuracies. Independent of CM strategy the elderly were characterized by a significantly reduced lateralization of ERD%, due to stronger ipsilateral ERD%, and in consequence, reduced classification accuracies. QM were generally perceived as more vivid, but no differences were evident between MI and QM in ERD% or classification accuracies. EEG feedback enhanced task-related activity independently of strategy and age. ERD% measures of overt and covert movements were strongly related in young adults, whereas in the elderly ERD% lateralization is dissociated. In summary, we did not find evidence in support of more pronounced ERD% lateralization patterns in QM. Our finding of a less lateralized activation pattern in the elderly is in accordance to previous research and with the idea that compensatory processes help to overcome neurodegenerative changes related to normal ageing. Importantly, it indicates that EEG neurofeedback studies should place more emphasis on the age of the potential end-users.

Enhanced Motor Imagery Training Using a Hybrid BCI With Feedback

GOAL

Motor imagery-related mu/beta rhythms, which can be voluntarily modulated by subjects, have been widely used in EEG-based brain computer interfaces (BCIs). Moreover, it has been suggested that motor imagery-specific EEG differences can be enhanced by feedback training. However, the differences observed in the EEGs of naive subjects are typically not sufficient to provide reliable EEG control and thus result in unintended feedback. Such feedback can frustrate subjects and impede training. In this study, a hybrid BCI paradigm combining motor imagery and steady-state visually evoked potentials (SSVEPs) has been proposed to provide effective continuous feedback for motor imagery training.

METHODS

During the initial training sessions, subjects must focus on flickering buttons to evoke SSVEPs as they perform motor imagery tasks. The output/feedback of the hybrid BCI is based on hybrid features consisting of motor imagery- and SSVEP-related brain signals. In this context, the SSVEP plays a more important role than motor imagery in generating feedback. As the training progresses, the subjects can gradually decrease their visual attention to the flickering buttons, provided that the feedback is still effective. In this case, the feedback is mainly based on motor imagery.

RESULTS

Our experimental results demonstrate that subjects generate distinguishable brain patterns of hand motor imagery after only five training sessions lasting approximately 1.5 h each.

CONCLUSION

The proposed hybrid feedback paradigm can be used to enhance motor imagery training.

SIGNIFICANCE

This hybrid BCI system with feedback can effectively identify the intentions of the subjects.

Effects of feedback latency on P300-based brain-computer interface

Feedback has been shown to affect performance when using a Brain-Computer Interface (BCI) based on sensorimotor rhythms. In contrast, little is known about the influence of feedback on P300-based BCIs. There is still an open question whether feedback affects the regulation of P300 and consequently the operation of P300-based BCIs. In this paper, for the first time, the influence of feedback on the P300-based BCI speller task is systematically assessed. For this purpose, 24 healthy participants performed the classic P300-based BCI speller task, while only half of them received feedback. Importantly, the number of flashes per letter was reduced on a regular basis in order to increase the frequency of providing feedback. Experimental results showed that feedback could significantly improve the P300-based BCI speller performance, if it was provided in short time intervals (e.g. in sequences as short as 4 to 6 flashes per row/column). Moreover, our offline analysis showed that providing feedback remarkably enhanced the relevant ERP patterns and attenuated the irrelevant ERP patterns, such that the discrimination between target and non-target EEG trials increased.

Multimodal sensory feedback associated with motor attempts alters BOLD responses to paralyzed hand movement in chronic stroke patients

Electroencephalogram-based brain-computer interfaces (BCI) have been used as a potential tool for training volitional regulation of corticomuscular drive in patients who have severe hemiplegia due to stroke. However, it is unclear whether ERD observed while attempting motor execution can be regarded as a neural marker that represents M1 excitability in survivors of severe stroke. Therefore we investigated the association between ERD and the blood-oxygen-level-dependent (BOLD) fMRI signal during attempted movement of a paralyzed finger in stroke patients. Nine chronic stroke patients received BCI training for finger extension movement 1 h daily for a duration of 1 month. The sensorimotor rhythm was recorded from the sensorimotor area of the damaged hemisphere, and ongoing amplitude variations were monitored using a BCI system. Either a visual alert or the action of a motor-driven orthosis was triggered in response to ERD of the sensorimotor rhythm while patients attempted extension movements of the paralyzed fingers. Inter-subject covariance between ERD and the BOLD response in the sensorimotor areas was calculated. After BCI training, an increased ERD over the damaged hemisphere was confirmed in all participants while they attempted extension of the affected finger and this increase was associated with a BOLD response in primary sensorimotor area. Whole-brain MRI revealed that the primary sensorimotor area and supplementary motor area were activated in the damaged hemisphere after 1 month of BCI training. ERD reflects the BOLD responses of the primary motor areas in either hemisphere while patients who have severe chronic hemiplegia due to a stroke attempt an extension movement of the paralyzed fingers. One month of BCI can alter motor-related brain area activation. Combining BCI with other methods to facilitate such changes may help to implement BCI for motor rehabilitation after stroke.

Exploration of the neural correlates of cerebral palsy for sensorimotor BCI control

Cerebral palsy (CP) includes a broad range of disorders, which can result in impairment of posture and movement control. Brain-computer interfaces (BCIs) have been proposed as assistive devices for individuals with CP. Better understanding of the neural processing underlying motor control in affected individuals could lead to more targeted BCI rehabilitation and treatment options. We have explored well-known neural correlates of movement, including event-related desynchronization (ERD), phase synchrony, and a recently-introduced measure of phase dynamics, in participants with CP and healthy control participants. Although present, significantly less ERD and phase locking were found in the group with CP. Additionally, inter-group differences in phase dynamics were also significant. Taken together these findings suggest that users with CP exhibit lower levels of motor cortex activation during motor imagery, as reflected in lower levels of ongoing mu suppression and less functional connectivity. These differences indicate that development of BCIs for individuals with CP may pose additional challenges beyond those faced in providing BCIs to healthy individuals.

Effect of mindfulness meditation on brain-computer interface performance

Electroencephalogram based brain-computer interfaces (BCIs) enable stroke and motor neuron disease patients to communicate and control devices. Mindfulness meditation has been claimed to enhance metacognitive regulation. The current study explores whether mindfulness meditation training can thus improve the performance of BCI users. To eliminate the possibility of expectation of improvement influencing the results, we introduced a music training condition. A norming study found that both meditation and music interventions elicited clear expectations for improvement on the BCI task, with the strength of expectation being closely matched. In the main 12 week intervention study, seventy-six healthy volunteers were randomly assigned to three groups: a meditation training group; a music training group; and a no treatment control group. The mindfulness meditation training group obtained a significantly higher BCI accuracy compared to both the music training and no-treatment control groups after the intervention, indicating effects of meditation above and beyond expectancy effects.

Whatever works: a systematic user-centered training protocol to optimize brain-computer interfacing individually

This study implemented a systematic user-centered training protocol for a 4-class brain-computer interface (BCI). The goal was to optimize the BCI individually in order to achieve high performance within few sessions for all users. Eight able-bodied volunteers, who were initially naïve to the use of a BCI, participated in 10 sessions over a period of about 5 weeks. In an initial screening session, users were asked to perform the following seven mental tasks while multi-channel EEG was recorded: mental rotation, word association, auditory imagery, mental subtraction, spatial navigation, motor imagery of the left hand and motor imagery of both feet. Out of these seven mental tasks, the best 4-class combination as well as most reactive frequency band (between 8-30 Hz) was selected individually for online control. Classification was based on common spatial patterns and Fisher's linear discriminant analysis. The number and time of classifier updates varied individually. Selection speed was increased by reducing trial length. To minimize differences in brain activity between sessions with and without feedback, sham feedback was provided in the screening and calibration runs in which usually no real-time feedback is shown. Selected task combinations and frequency ranges differed between users. The tasks that were included in the 4-class combination most often were (1) motor imagery of the left hand (2), one brain-teaser task (word association or mental subtraction) (3), mental rotation task and (4) one more dynamic imagery task (auditory imagery, spatial navigation, imagery of the feet). Participants achieved mean performances over sessions of 44-84% and peak performances in single-sessions of 58-93% in this user-centered 4-class BCI protocol. This protocol is highly adjustable to individual users and thus could increase the percentage of users who can gain and maintain BCI control. A high priority for future work is to examine this protocol with severely disabled users.

Flaws in current human training protocols for spontaneous Brain-Computer Interfaces: lessons learned from instructional design

While recent research on Brain-Computer Interfaces (BCI) has highlighted their potential for many applications, they remain barely used outside laboratories. The main reason is their lack of robustness. Indeed, with current BCI, mental state recognition is usually slow and often incorrect. Spontaneous BCI (i.e., mental imagery-based BCI) often rely on mutual learning efforts by the user and the machine, with BCI users learning to produce stable ElectroEncephaloGraphy (EEG) patterns (spontaneous BCI control being widely acknowledged as a skill) while the computer learns to automatically recognize these EEG patterns, using signal processing. Most research so far was focused on signal processing, mostly neglecting the human in the loop. However, how well the user masters the BCI skill is also a key element explaining BCI robustness. Indeed, if the user is not able to produce stable and distinct EEG patterns, then no signal processing algorithm would be able to recognize them. Unfortunately, despite the importance of BCI training protocols, they have been scarcely studied so far, and used mostly unchanged for years. In this paper, we advocate that current human training approaches for spontaneous BCI are most likely inappropriate. We notably study instructional design literature in order to identify the key requirements and guidelines for a successful training procedure that promotes a good and efficient skill learning. This literature study highlights that current spontaneous BCI user training procedures satisfy very few of these requirements and hence are likely to be suboptimal. We therefore identify the flaws in BCI training protocols according to instructional design principles, at several levels: in the instructions provided to the user, in the tasks he/she has to perform, and in the feedback provided. For each level, we propose new research directions that are theoretically expected to address some of these flaws and to help users learn the BCI skill more efficiently.

Upper alpha neurofeedback training over the motor cortex increases SMR desynchronization in motor tasks

Desynchronization of sensorimotor rhythms (SMR) is a distinctive feature that provides a discriminative pattern for BCI operation. However, individuals such as BCI illiterates can not produce these discriminable patterns with sufficient reliability. Additionally, SMR desynchronization can become deteriorated or extinct in patients with spinal cord injury or a cerebrovascular accident. In all these situations BCI usage is compromised. This paper proposes an intervention based on neurofeedback training of the upper alpha band to improve SMR desynchronization. The feasibility of this intervention is demonstrated in a preliminary study in which five healthy subjects were trained to increase their upper alpha band power. Such increases produced higher SMR desynchronization and better discrimination between rest and execution states of a motor task.

Daily training with realistic visual feedback improves reproducibility of event-related desynchronisation following hand motor imagery

OBJECTIVE

Few brain-computer interface (BCI) studies have addressed learning mechanisms by exposure to visual feedback that elicits scalp electroencephalogram. We examined the effect of realistic visual feedback of hand movement associated with sensorimotor rhythm.

METHODS

Thirty-two healthy participants performed in five daily training in which they were shown motor imagery of their dominant hand. Participants were randomly assigned to 1 of 4 experimental groups receiving different types of visual feedback on event-related desynchronisation (ERD) derived over the contralateral sensorimotor cortex: no feedback as a control, bar feedback with changing bar length, anatomically incongruent feedback in which the hand open/grasp picture on screen was animated at eye level, and anatomically congruent feedback in which the same hand open/grasp picture was animated on the screen overlaying the participant's hand.

RESULTS

Daily training with all types of visual feedback induced more robust ERD than the no feedback condition (p < 0.05). The anatomically congruent feedback produced the highest reproducibility of ERD with the smallest inter-trial variance (p < 0.05).

CONCLUSION

Realistic feedback training is a suitable method to acquire the skill to control a BCI system.

SIGNIFICANCE

This finding highlights the possibility of improvement of reproducibility of ERD and can help to use BCI techniques.

Evaluation of feature extraction methods for EEG-based brain-computer interfaces in terms of robustness to slight changes in electrode locations

To date, most EEG-based brain-computer interface (BCI) studies have focused only on enhancing BCI performance in such areas as classification accuracy and information transfer rate. In practice, however, test-retest reliability of the developed BCI systems must also be considered for use in long-term, daily life applications. One factor that can affect the reliability of BCI systems is the slight displacement of EEG electrode locations that often occurs due to the removal and reattachment of recording electrodes. The aim of this study was to evaluate and compare various feature extraction methods for motor-imagery-based BCI in terms of robustness to slight changes in electrode locations. To this end, EEG signals were recorded from three reference electrodes (Fz, C3, and C4) and from six additional electrodes located close to the reference electrodes with a 1-cm inter-electrode distance. Eight healthy participants underwent 180 trials of left- and right-hand motor imagery tasks. The performance of four different feature extraction methods [power spectral density (PSD), phase locking value (PLV), a combination of PSD and PLV, and cross-correlation (CC)] were evaluated using five-fold cross-validation and linear discriminant analysis, in terms of robustness to electrode location changes as well as regarding absolute classification accuracy. The quantitative evaluation results demonstrated that the use of either PSD- or CC-based features led to higher classification accuracy than the use of PLV-based features, while PSD-based features showed much higher sensitivity to changes in EEG electrode location than CC- or PLV-based features. Our results suggest that CC can be used as a promising feature extraction method in motor-imagery-based BCI studies, since it provides high classification accuracy along with being little affected by slight changes in the EEG electrode locations.

Long-term evaluation of a 4-class imagery-based brain-computer interface

OBJECTIVE

The study aimed to improve brain-computer interface (BCI)-usability by using distinct control strategies and evaluating performance, brain activity and psychological variables on a long-term basis over several months.

METHODS

Fourteen able-bodied users participated in 10 sessions, plus a follow-up session. Users were trained to control an EEG-based 4-class BCI with the mental tasks, word association, mental subtraction, spatial navigation, and motor imagery.

RESULTS

Eight users reached mean accuracies of 61-72% and managed to control all 4 classes above chance in single-sessions. Performance and brain patterns stayed stable over 10 weeks without training. Motor imagery showed the best performance and most distinct brain patterns. Participants' fear of incompetence decreased while the quality of their imagery and task ease increased over sessions. The evaluation of feedback differed between tasks and correlated with performance.

CONCLUSION

Users can control a real-time 4-class BCI, driven by distinct mental tasks, with stable performance over months. However, general performance was rather low for effective BCI control in daily life. Possibilities for future optimizations to increase performance are discussed.

SIGNIFICANCE

The evaluation of alternatives to motor imagery, long-term BCI use, and psychological variables is important to improve usability for mental imagery-based BCIs.

Discriminative tandem features for HMM-based EEG classification

We investigate the use of discriminative feature extractors in tandem configuration with generative EEG classification system. Existing studies on dynamic EEG classification typically use hidden Markov models (HMMs) which lack discriminative capability. In this paper, a linear and a non-linear classifier are discriminatively trained to produce complementary input features to the conventional HMM system. Two sets of tandem features are derived from linear discriminant analysis (LDA) projection output and multilayer perceptron (MLP) class-posterior probability, before appended to the standard autoregressive (AR) features. Evaluation on a two-class motor-imagery classification task shows that both the proposed tandem features yield consistent gains over the AR baseline, resulting in significant relative improvement of 6.2% and 11.2% for the LDA and MLP features respectively. We also explore portability of these features across different subjects.