Unraveling motor imagery brain patterns using explainable artificial intelligence based on Shapley values.

BACKGROUND AND OBJECTIVE: Motor imagery (MI) based brain-computer interfaces (BCIs) are widely used in rehabilitation due to the close relationship that exists between MI and motor execution (ME). However, the underlying brain mechanisms of MI remain not well understood. Most MI-BCIs use the sensorimotor rhythms elicited in the primary motor cortex (M1) and somatosensory cortex (S1), which consist of an event-related desynchronization followed by an event-related synchronization. Consequently, this has resulted in systems that only record signals around M1 and S1. However, MI could involve a more complex network including sensory, association, and motor areas. In this study, we hypothesize that the superior accuracies achieved by new deep learning (DL) models applied to MI decoding rely on focusing on a broader MI activation of the brain. Parallel to the success of DL, the field of explainable artificial intelligence (XAI) has seen continuous development to provide explanations for DL networks success. The goal of this study is to use XAI in combination with DL to extract information about MI brain activation patterns from non-invasive electroencephalography (EEG) signals. METHODS: We applied an adaptation of Shapley additive explanations (SHAP) to EEGSym, a state-of-the-art DL network with exceptional transfer learning capabilities for inter-subject MI classification. We obtained the SHAP values from two public databases comprising 171 users generating left and right hand MI instances with and without real-time feedback. RESULTS: We found that EEGSym based most of its prediction on the signal of the frontal electrodes, i.e. F7 and F8, and on the first 1500 ms of the analyzed imagination period. We also found that MI involves a broad network not only based on M1 and S1, but also on the prefrontal cortex (PFC) and the posterior parietal cortex (PPC). We further applied this knowledge to select a 8-electrode configuration that reached inter-subject accuracies of 86.5% ± 10.6% on the Physionet dataset and 88.7% ± 7.0% on the Carnegie Mellon University's dataset. CONCLUSION: Our results demonstrate the potential of combining DL and SHAP-based XAI to unravel the brain network involved in producing MI. Furthermore, SHAP values can optimize the requirements for out-of-laboratory BCI applications involving real users.

Association between lesion location and sensorimotor rhythms in stroke - a systematic review with narrative synthesis.

BACKGROUND: Stroke causes alterations in the sensorimotor rhythms (SMRs) of the brain. However, little is known about the influence of lesion location on the SMRs. Understanding this relationship is relevant for the use of SMRs in assistive and rehabilitative therapies, such as Brain-Computer Interfaces (BCIs).. METHODS: We reviewed current evidence on the association between stroke lesion location and SMRs through systematically searching PubMed and Embase and generated a narrative synthesis of findings. RESULTS: We included 12 articles reporting on 161 patients. In resting-state studies, cortical and pontine damage were related to an overall decrease in alpha (∼8-12 Hz) and increase in delta (∼1-4 Hz) power. In movement paradigm studies, attenuated alpha and beta (∼15-25 Hz) event-related desynchronization (ERD) was shown in stroke patients during (attempted) paretic hand movement, compared to controls. Stronger reductions in alpha and beta ERD in the ipsilesional, compared to contralesional hemisphere, were observed for cortical lesions. Subcortical stroke was found to affect bilateral ERD and ERS, but results were highly variable. CONCLUSIONS: Findings suggest a link between stroke lesion location and SMR alterations, but heterogeneity across studies and limited lesion location descriptions precluded a meta-analysis. SIGNIFICANCE: Future research would benefit from more uniformly defined outcome measures, homogeneous methodologies, and improved lesion location reporting.

Enhancing neurorehabilitation by targeting beneficial plasticity.

Neurorehabilitation is now one of the most exciting areas in neuroscience. Recognition that the central nervous system (CNS) remains plastic through life, new understanding of skilled behaviors (skills), and novel methods for engaging and guiding beneficial plasticity combine to provide unprecedented opportunities for restoring skills impaired by CNS injury or disease. The substrate of a skill is a distributed network of neurons and synapses that changes continually through life to ensure that skill performance remains satisfactory as new skills are acquired, and as growth, aging, and other life events occur. This substrate can extend from cortex to spinal cord. It has recently been given the name "heksor." In this new context, the primary goal of rehabilitation is to enable damaged heksors to repair themselves so that their skills are once again performed well. Skill-specific practice, the mainstay of standard therapy, often fails to optimally engage the many sites and kinds of plasticity available in the damaged CNS. New noninvasive technology-based interventions can target beneficial plasticity to critical sites in damaged heksors; these interventions may thereby enable much wider beneficial plasticity that enhances skill recovery. Targeted-plasticity interventions include operant conditioning of a spinal reflex or corticospinal motor evoked potential (MEP), paired-pulse facilitation of corticospinal connections, and brain-computer interface (BCI)-based training of electroencephalographic (EEG) sensorimotor rhythms. Initial studies in people with spinal cord injury, stroke, or multiple sclerosis show that these interventions can enhance skill recovery beyond that achieved by skill-specific practice alone. After treatment ends, the repaired heksors maintain the benefits.

Tensor Decomposition Analysis of Longitudinal EEG Signals Reveals Differential Oscillatory Dynamics in Eyes-Closed and Eyes-Open Motor Imagery BCI: A Case Report.

Functional dissociation of brain neural activity induced by opening or closing the eyes has been well established. However, how the temporal dynamics of the underlying neuronal modulations differ between these eye conditions during movement-related behaviours is less known. Using a robotic-assisted motor imagery brain-computer interface (MI BCI), we measured neural activity over the motor regions with electroencephalography (EEG) in a stroke survivor during his longitudinal rehabilitation training. We investigated lateralized oscillatory sensorimotor rhythm modulations while the patient imagined moving his hemiplegic hand with closed and open eyes to control an external robotic splint. In order to precisely identify the main profiles of neural activation affected by MI with eyes-open (MIEO) and eyes-closed (MIEC), a data-driven approach based on parallel factor analysis (PARAFAC) tensor decomposition was employed. Using the proposed framework, a set of narrow-band, subject-specific sensorimotor rhythms was identified; each of them had its own spatial and time signature. When MIEC trials were compared with MIEO trials, three key narrow-band rhythms whose peak frequencies centred at ∼8.0 Hz, ∼11.5 Hz, and ∼15.5 Hz, were identified with differently modulated oscillatory dynamics during movement preparation, initiation, and completion time frames. Furthermore, we observed that lower and higher sensorimotor oscillations represent different functional mechanisms within the MI paradigm, reinforcing the hypothesis that rhythmic activity in the human sensorimotor system is dissociated. Leveraging PARAFAC, this study achieves remarkable precision in estimating latent sensorimotor neural substrates, aiding the investigation of the specific functional mechanisms involved in the MI process.

Investigating the influence of functional electrical stimulation on motor imagery related µ-rhythm suppression.

Background: Motor Imagery (MI) is a well-known cognitive technique that utilizes the same neural circuits as voluntary movements. Therefore, MI practice is widely used in sport training and post-stroke rehabilitation. The suppression of the µ-rhythm in electroencephalogram (EEG) is a conventional marker of sensorimotor cortical activation during motor imagery. However, the role of somatosensory afferentation in mental imagery processes is not yet clear. In this study, we investigated the impact of functional electrical stimulation (FES) on µ-rhythm suppression during motor imagery. Methods: Thirteen healthy experienced participants were asked to imagine their right hand grasping, while a 30-channel EEG was recorded. FES was used to influence sensorimotor activation during motor imagery of the same hand. Results: We evaluated cortical activation by estimating the µ-rhythm suppression index, which was assessed in three experimental conditions: MI, MI + FES, and FES. Our findings shows that motor imagery enhanced by FES leads to a more prominent µ-rhythm suppression. Obtained results suggest a direct effect of peripheral electrical stimulation on cortical activation, especially when combined with motor imagery. Conclusion: This research sheds light on the potential benefits of integrating FES into motor imagery-based interventions to enhance cortical activation and holds promise for applications in neurorehabilitation.

A systematic review of EEG neurofeedback in fibromyalgia to treat psychological variables, chronic pain and general health.

This paper is the first up-to-date review of the various EEG-neurofeedback treatments for fibromyalgia patients and their psychological, physiological and general health consequences. Searches were made of the PubMed, PsycNet, Google Scholar and Scopus databases according to PRISMA guidelines for empirical peer-reviewed articles on EEG-neurofeedback treatment of fibromyalgia, yielding a final selection of 17 studies that met the inclusion criteria: (1) published articles and doctoral theses; (2) conducted between 2000 and 2022; (3) reporting empirical and quantitative data. These articles show that there is a wide range of protocols with different designs and procedures to treat fibromyalgia using EEG-neurofeedback techniques. The main symptoms that showed improvement were anxiety, depression, pain, general health and symptom severity, whilst the most commonly used method was traditional EEG neurofeedback based on a sensorimotor rhythm protocol. It may be concluded from the review that the lack of consistency and uniqueness of the protocols makes it very difficult to generalise results, despite the individual improvements identified. This review provides instructions and information that could guide future research and clinical practise, with the data extracted helping to gain a deeper understanding of the state of the art and the needs of the technique for this population group.

Discrepancy between inter- and intra-subject variability in EEG-based motor imagery brain-computer interface: Evidence from multiple perspectives.

Introduction: Inter- and intra-subject variability are caused by the variability of the psychological and neurophysiological factors over time and across subjects. In the application of in Brain-Computer Interfaces (BCI), the existence of inter- and intra-subject variability reduced the generalization ability of machine learning models seriously, which further limited the use of BCI in real life. Although many transfer learning methods can compensate for the inter- and intra-subject variability to some extent, there is still a lack of clear understanding about the change of feature distribution between the cross-subject and cross-session electroencephalography (EEG) signal. Methods: To investigate this issue, an online platform for motor-imagery BCI decoding has been built in this work. The EEG signal from both the multi-subject (Exp1) and multi-session (Exp2) experiments has been analyzed from multiple perspectives. Results: Firstly we found that with the similar variability of classification results, the time-frequency response of the EEG signal within-subject in Exp2 is more consistent than cross-subject results in Exp1. Secondly, the standard deviation of the common spatial pattern (CSP) feature has a significant difference between Exp1 and Exp2. Thirdly, for model training, different strategies for the training sample selection should be applied for the cross-subject and cross-session tasks. Discussion: All these findings have deepened the understanding of inter- and intra-subject variability. They can also guide practice for the new transfer learning methods development in EEG-based BCI. In addition, these results also proved that BCI inefficiency was not caused by the subject's unable to generate the event-related desynchronization/synchronization (ERD/ERS) signal during the motor imagery.

Quasi-Movements and "Quasi-Quasi-Movements": Does Residual Muscle Activation Matter?

Quasi-movements (QM) are observed when an individual minimizes a movement to an extent that no related muscle activation is detected. Likewise to imaginary movements (IM) and overt movements, QMs are accompanied by the event-related desynchronization (ERD) of EEG sensorimotor rhythms. Stronger ERD was observed under QMs compared to IMs in some studies. However, the difference could be caused by the remaining muscle activation in QMs that could escape detection. Here, we re-examined the relation between the electromyography (EMG) signal and ERD in QM using sensitive data analysis procedures. More trials with signs of muscle activation were observed in QMs compared with a visual task and IMs. However, the rate of such trials was not correlated with subjective estimates of actual movement. Contralateral ERD did not depend on the EMG but still was stronger in QMs compared with IMs. These results suggest that brain mechanisms are common for QMs in the strict sense and "quasi-quasi-movements" (attempts to perform the same task accompanied by detectable EMG elevation) but differ between them and IMs. QMs could be helpful in research aimed at better understanding motor action and at modeling the use of attempted movements in the brain-computer interfaces with healthy participants.

Voluntary Motor Command Release Coincides with Restricted Sensorimotor Beta Rhythm Phases.

Sensory perception and memory are enhanced during restricted phases of ongoing brain rhythms, but whether voluntary movement is constrained by brain rhythm phase is not known. Voluntary movement requires motor commands to be released from motor cortex (M1) and transmitted to spinal motoneurons and effector muscles. Here, we tested the hypothesis that motor commands are preferentially released from M1 during circumscribed phases of ongoing sensorimotor rhythms. Healthy humans of both sexes performed a self-paced finger movement task during electroencephalography (EEG) and electromyography (EMG) recordings. We first estimated the time of motor command release preceding each finger movement by subtracting individually measured corticomuscular transmission latencies from EMG-determined movement onset times. Then, we determined the phase of ipsilateral and contralateral sensorimotor mu (8-12 Hz) and beta (13-35 Hz) rhythms during release of each motor command. We report that motor commands were most often released between 120 and 140° along the contralateral beta cycle but were released uniformly along the contralateral mu cycle. Motor commands were also released uniformly along ipsilateral mu and beta cycles. Results demonstrate that motor command release coincides with restricted phases of the contralateral sensorimotor beta rhythm, suggesting that sensorimotor beta rhythm phase may sculpt the timing of voluntary human movement.SIGNIFICANCE STATEMENT Perceptual and cognitive function is optimal during specific brain rhythm phases. Although brain rhythm phase influences motor cortical neuronal activity and communication between the motor cortex and spinal cord, its role in voluntary movement is poorly understood. Here, we show that the motor commands needed to produce voluntary movements are preferentially released from the motor cortex during contralateral sensorimotor beta rhythm phases. Our findings are consistent with the notion that sensorimotor rhythm phase influences the timing of voluntary human movement.

Portable rehabilitation system with brain-computer interface for inpatients with acute and subacute stroke: A feasibility study.

The feasibility and safety of brain-computer interface (BCI) systems for patients with acute/subacute stroke have not been established. The aim of this study was to firstly demonstrate the feasibility and safety of a bedside BCI system for inpatients with acute/subacute stroke in a small cohort of inpatients. Four inpatients with early-phase hemiplegic stroke (7-24 days from stroke onset) participated in this study. The portable BCI system showed real-time feedback of sensorimotor rhythms extracted from scalp electroencephalograms (EEGs). Patients attempted to extend the wrist on their affected side, and neuromuscular electrical stimulation was applied only when the system detected significant movement intention-related changes in EEG. Between 120 and 200 training trials per patient were successfully and safely conducted at the bedside over 2-4 days. Our results clearly indicate that the proposed bedside BCI system is feasible and safe. Larger clinical studies are needed to determine the clinical efficacy of the system and its effect size in the population of patients with acute/subacute post-stroke hemiplegia.

Heart rate variability predicts decline in sensorimotor rhythm control.

Objective.Voluntary control of sensorimotor rhythms (SMRs, 8-12 Hz) can be used for brain-computer interface (BCI)-based operation of an assistive hand exoskeleton, e.g. in finger paralysis after stroke. To gain SMR control, stroke survivors are usually instructed to engage in motor imagery (MI) or to attempt moving the paralyzed fingers resulting in task- or event-related desynchronization (ERD) of SMR (SMR-ERD). However, as these tasks are cognitively demanding, especially for stroke survivors suffering from cognitive impairments, BCI control performance can deteriorate considerably over time. Therefore, it would be important to identify biomarkers that predict decline in BCI control performance within an ongoing session in order to optimize the man-machine interaction scheme.Approach.Here we determine the link between BCI control performance over time and heart rate variability (HRV). Specifically, we investigated whether HRV can be used as a biomarker to predict decline of SMR-ERD control across 17 healthy participants using Granger causality. SMR-ERD was visually displayed on a screen. Participants were instructed to engage in MI-based SMR-ERD control over two consecutive runs of 8.5 min each. During the 2nd run, task difficulty was gradually increased.Main results.While control performance (p= .18) and HRV (p= .16) remained unchanged across participants during the 1st run, during the 2nd run, both measures declined over time at high correlation (performance: -0.61%/10 s,p= 0; HRV: -0.007 ms/10 s,p< .001). We found that HRV exhibited predictive characteristics with regard to within-session BCI control performance on an individual participant level (p< .001).Significance.These results suggest that HRV can predict decline in BCI performance paving the way for adaptive BCI control paradigms, e.g. to individualize and optimize assistive BCI systems in stroke.

A neurophysiological approach to spatial filter selection for adaptive brain-computer interfaces.

Objective. The common spatial patterns (CSP) algorithm is an effective method to extract discriminatory features from electroencephalography (EEG) to be used by a brain-computer interface (BCI). However, informed selection of CSP filters typically requires oversight from a BCI expert to accept or reject filters based on the neurophysiological plausibility of their activation patterns. Our goal was to identify, analyze and automatically classify prototypical CSP patterns to enhance the prediction of motor imagery states in a BCI.Approach. A data-driven approach that used four publicly available EEG datasets was adopted. Cluster analysis revealed recurring, visually similar CSP patterns and a convolutional neural network was developed to distinguish between established CSP pattern classes. Furthermore, adaptive spatial filtering schemes that utilize the categorization of CSP patterns were proposed and evaluated.Main results. Classes of common neurophysiologically probable and improbable CSP patterns were established. Analysis of the relationship between these categories of CSP patterns and classification performance revealed discarding neurophysiologically improbable filters can decrease decoder performance. Further analysis revealed that the spatial orientation of EEG modulations can evolve over time, and that the features extracted from the original CSP filters can become inseparable. Importantly, it was shown through a novel adaptive CSP technique that adaptation in response to these emerging patterns can restore feature separability.Significance. These findings highlight the importance of considering and reporting on spatial filter activation patterns in both online and offline studies. They also emphasize to researchers in the field the importance of spatial filter adaptation in BCI decoder design, particularly for online studies with a focus on training users to develop stable and suitable brain patterns.

Eficacia del protocolo SMR en mujeres con fibromialgia para la mejora del dolor crónico, el sueño y la calidad de vida / Efficacy of the SMR protocol in women with fibromyalgia for the improvement of chronic pain, sleep and quality of life

El objetivo del estudio fue analizar cómo el moldeamiento cerebral proporcionado por el protocolo de ritmos sensoriomotores (SMR), aplicado sobre áreas somatosensoriales, afecta al dolor, al sueño y a la calidad de vida de mujeres con fibromialgia. Participaron 37 mujeres con fibromialgia a quienes se les aplicó un protocolo de SMR durante 20 sesiones y fueron evaluadas antes y después del tratamiento. Los datos mostraron un aumento de la amplitud de los SMR (p= 0,026) y una disminución de la amplitud de la banda zeta (p= 0,011) en la corteza somatosensorial tras la aplicación de la terapia, lo que provocó un aumento de la ratio SMR/zeta (p= 0,048). Además, mejoraron significativamente las puntuaciones en la “Escala de dolor crónico” (p= 0,002), el “Índice de calidad del sueño de Pittsburgh” (p= 0,001) y la “Encuesta de salud” (SF-36) (p= 0,000). El protocolo SMR aplicado en la corteza somatosensorial favorece el moldeamiento de los SMR, lo que repercute en la inhibición estimular del sistema nervioso central de los pacientes con fibromialgia mejorando síntomas como el dolor, el sueño y la calidad de vida (AU)

he sensorimotor rhythm protocol (SMR), applied on somatosensory areas, affects pain, sleep and the quality of life in women with fibromyalgia. Thirty-seven women with fibromyalgia who received an SMR protocol in 20 sessions participated and were evaluated before and after treatment. The data showed an increase in the amplitude of the SMR (p= .026) and a decrease in the amplitude of the theta band (p= .011) in the somatosensory cortex after the application of therapy, which caused an increase in the SMR/theta ratio (p= .048). In addition, the scores on the Chronic Pain Scale (p= .002), the Pittsburgh Sleep Quality Index (p= .001), and the SF-36 Health Survey (p= .000) improved significantly. The SMR protocol applied to the somatosensory cortex favors the shaping of SMRs, which has an impact on stimulating the inhibition of the central nervous system of patients with fibromyalgia, improving symptoms such as pain, sleep and quality of life (AU)

Relieving peripheral neuropathic pain by increasing the power-ratio of low-ß over high-ß activities in the central cortical region with EEG-based neurofeedback: Study protocol for a controlled pilot trial (SMRPain study).

BACKGROUND: Chronic neuropathic pain associated with peripheral neuropathies cannot be attributed solely to lesions of peripheral sensory axons and likely involves alteration in the processing of nociceptive information in the central nervous system in most patients. Few data are available regarding EEG correlates of chronic neuropathic pain. The fact is that effective cortical neuromodulation strategies to treat neuropathic pain target the precentral cortical region, i.e. a cortical area corresponding to the motor cortex. It is not known how these strategies might modulate brain rhythms in the central cortical region, but it can be speculated that sensorimotor rhythms (SMRs) are modified. Another potent way of modulating cortical rhythms is to use EEG-based neurofeedback (NFB). Rare studies previously aimed at relieving neuropathic pain using EEG-NFB training. METHODS/DESIGN: The objective of this single-centre, single-blinded, randomized controlled pilot study is to assess the value of an EEG-NFB procedure to relieve chronic neuropathic pain in patients with painful peripheral neuropathy. A series of 32 patients will be randomly assigned to one of the two following EEG-NFB protocols, aimed at increasing either the low-ß(SMR)/high-ß ratio (n=16) or the α(µ)/θ ratio (n=16) at central (rolandic) cortical level. Various clinical outcome measures will be collected before and one week after 12 EEG-NFB sessions performed over 4weeks. Resting-state EEG will also be recorded immediately before and after each NFB session. The primary endpoint will be the change in the impact of pain on patient's daily functioning, as assessed on the Interference Scale of the short form of the Brief Pain Inventory. DISCUSSION: The value of EEG-NFB procedures to relieve neuropathic pain has been rarely studied. This pilot study will attempt to show the value of endogenous modulation of brain rhythms in the central (rolandic) region in the frequency band corresponding to the frequency of stimulation currently used by therapeutic motor cortex stimulation. In the case of significant clinical benefit produced by the low-ß(SMR)/high-ß ratio increasing strategy, this work could pave the way for using EEG-NFB training within the armamentarium of neuropathic pain therapy.

Week-long visuomotor coordination and relaxation trainings do not increase sensorimotor rhythms (SMR) based brain-computer interface performance.

Brain-computer interfaces (BCI) translate brain activity into control signals or commands for a device. Motor imagery of the limbs allows for modulating the sensorimotor rhythms (SMR), but there are up to 30% of the participants for whom electroencephalography (EEG) based SMR-BCI cannot detect any imagery-related changes. Individual variables, such as ability to concentrate on a task and error duration in a two-hand visuomotor coordination (VMC) task have been previously found to predict accuracy in an SMR-BCI. A first study attempted to substantiate those predictors by introducing a 30 min relaxation or VMC training period prior to an SMR-BCI session, but performance did not increase when compared to a control group. As the predictor training may have been too short, we applied 4 such training sessions on consecutive days in the current study. In a pre-post design, SMR-BCI accuracy of n = 39 participants increased from session 1 before to session 2 after the predictor training. While the manipulation of the predictor variables was successful, there was no effect on SMR-BCI performance. BCI accuracy correlated positively with the neurophysiological SMR predictor identified by Blankertz et al. [3], consolidating its predictive value, and with the state mindfulness scale. No other psychological predictor could be identified or replicated. Further studies should therefore focus more on delineating (partially) replicated or potential predictors such as VMC or mindfulness to help refining a sound model to predict SMR-BCI accuracy.

Intra- and Inter-subject Variability in EEG-Based Sensorimotor Brain Computer Interface: A Review.

Brain computer interfaces (BCI) for the rehabilitation of motor impairments exploit sensorimotor rhythms (SMR) in the electroencephalogram (EEG). However, the neurophysiological processes underpinning the SMR often vary over time and across subjects. Inherent intra- and inter-subject variability causes covariate shift in data distributions that impede the transferability of model parameters amongst sessions/subjects. Transfer learning includes machine learning-based methods to compensate for inter-subject and inter-session (intra-subject) variability manifested in EEG-derived feature distributions as a covariate shift for BCI. Besides transfer learning approaches, recent studies have explored psychological and neurophysiological predictors as well as inter-subject associativity assessment, which may augment transfer learning in EEG-based BCI. Here, we highlight the importance of measuring inter-session/subject performance predictors for generalized BCI frameworks for both normal and motor-impaired people, reducing the necessity for tedious and annoying calibration sessions and BCI training.

Most Popular Signal Processing Methods in Motor-Imagery BCI: A Review and Meta-Analysis.

Brain-Computer Interfaces (BCI) constitute an alternative channel of communication between humans and environment. There are a number of different technologies which enable the recording of brain activity. One of these is electroencephalography (EEG). The most common EEG methods include interfaces whose operation is based on changes in the activity of Sensorimotor Rhythms (SMR) during imagery movement, so-called Motor Imagery BCI (MIBCI).The present article is a review of 131 articles published from 1997 to 2017 discussing various procedures of data processing in MIBCI. The experiments described in these publications have been compared in terms of the methods used for data registration and analysis. Some of the studies (76 reports) were subjected to meta-analysis which showed corrected average classification accuracy achieved in these studies at the level of 51.96%, a high degree of heterogeneity of results (Q = 1806577.61; df = 486; p < 0.001; I 2 = 99.97%), as well as significant effects of number of channels, number of mental images, and method of spatial filtering. On the other hand the meta-regression failed to provide evidence that there was an increase in the effectiveness of the solutions proposed in the articles published in recent years. The authors have proposed a newly developed standard for presenting results acquired during MIBCI experiments, which is designed to facilitate communication and comparison of essential information regarding the effects observed. Also, based on the findings of descriptive analysis and meta-analysis, the authors formulated recommendations regarding practices applied in research on signal processing in MIBCIs.

Brain-computer interface control in a virtual reality environment and applications for the internet of things.

Brain-computer interfaces (BCIs) have enabled individuals to control devices such as spellers, robotic arms, drones, and wheelchairs, but often these BCI applications are restricted to research laboratories. With the advent of virtual reality (VR) systems and the internet of things (IoT) we can couple these technologies to offer real-time control of a user's virtual and physical environment. Likewise, BCI applications are often single-use with user's having no control outside of the restrictions placed upon the applications at the time of creation. Therefore, there is a need to create a tool that allows users the flexibility to create and modularize aspects of BCI applications for control of IoT devices and VR environments. Using a popular video game engine, Unity, and coupling it with BCI2000, we can create diverse applications that give the end-user additional autonomy during the task at hand. We demonstrate the validity of controlling a Unity-based VR environment and several commercial IoT devices via direct neural interfacing processed through BCI2000.

Classification of Imaginary Motor Task from Electroencephalographic Signals: A Comparison of Feature Selection Methods and Classification Algorithms / Clasificación de una Motricidad Imaginaria por medio de Señales Electroencefalográficas: Una Comparación de Métodos de Selección de Características y Algoritmos de Clasificación

Abstract: In this work, a Brain Computer interface able to decode imagery motor task from EEG is presented. The method uses time-frequency representation of the brain signal recorded in different regions of the brain to extract important features. Principal Component Analysis and Sequential Forward Selection methods are compared in their ability to represent the feature set in a compact form, removing at the same time unnecessary information. Finally, two method based on machine learning are implemented for the task of classification. Results show that it is possible to decode the mental activity of the subjects with accuracy above 80%. Furthermore, visualization of the main components extracted from the brain signal allow for physiological insights on the activity that take place in the sensorimotor cortex during execution of imaginary movement of different parts of the body.

Resumen: En este trabajo es presentada una Interfaz Cerebro Computadora que tiene la capacidad de decodificar actividades motrices. El método utiliza representación en el dominio de la frecuencia y el tiempo de las señales del cerebro grabadas en distintas regiones de este mismo, con el fin de extraer características importantes. Los métodos: Análisis de Componentes Principales y Selección Secuencial, son comparados en términos de su capacidad para representar características de la señal de una forma compacta, removiendo de esta forma, información innecesaria. Finalmente, dos métodos basados en aprendizaje de máquinas fueron implementados para la clasificación de actividades motrices utilizando solo las señales cerebrales. Los resultados muestran que es posible decodificar la actividad mental en los sujetos con una precisión superior al 80%. Además, la visualización de las componentes principales extraídas de las señales del cerebro permite un analísis de la actividad que toma lugar en la corteza cerebral sensorimotora durante la ejecución de la imaginación de movimientos de distintas partes del cuerpo.