The objective of this study is to test whether human intentions to sustain or cease movements in right and left hands can be decoded reliably from spatially filtered single trial magneto-encephalographic (MEG) signals. This study was performed using motor execution and motor imagery movements to achieve a potential high performance Brain-Computer interface (BCI). Seven healthy volunteers, naïve to BCI technology, participated in this study. Signals were recorded from 275-channel MEG and synthetic aperture magnetometry (SAM) was employed as the spatial filter. The four-class classification for natural movement intentions was performed offline; Genetic Algorithm based Mahalanobis Linear Distance (GA-MLD) and direct-decision tree classifier (DTC) techniques were adopted for the classification through 10-fold cross-validation. Through SAM imaging, strong and distinct event related desynchronisation (ERD) associated with sustaining, and event related synchronisation (ERS) patterns associated with ceasing of hand movements were observed in the beta band (15 - 30 Hz). The right and left hand ERD/ERS patterns were observed on the contralateral hemispheres for motor execution and motor imagery sessions. Virtual channels were selected from these cortical areas of high activity to correspond with the motor tasks as per the paradigm of the study. Through a statistical comparison between SAM-filtered virtual channels from single trial MEG signals and basic MEG sensors, it was found that SAM-filtered virtual channels significantly increased the classification accuracy for motor execution (GA-MLD: 96.51 ± 2.43 %) as well as motor imagery sessions (GA-MLD: 89.69 ± 3.34%). Thus, multiple movement intentions can be reliably detected from SAM-based spatially-filtered single trial MEG signals. MEG signals associated with natural motor behavior may be utilized for a reliable high-performance brain-computer interface (BCI) and may reduce long-term training compared with conventional BCI methods using rhythm control. This may prove tremendously helpful for patients suffering from various movement disorders to improve their quality of life.

L'attention visuospatiale est un mécanisme de sélection et de traitement d'information qui se manifeste explicitement par l'orientation de la tête ou du regard. En anticipation d'une nouvelle information, le foyer de l'attention s'oriente implicitement en vision périphérique pour dissocier l'orientation du regard et du foyer implicite vers deux emplacements distincts. Dans cette situation, la réaction à une cible qui apparaît à l'emplacement du foyer implicite s'améliore par rapport aux autres cibles qui pourraient s'afficher dans un emplacement non-attendu. La problématique de la thèse est d'étudier comment détecter l'emplacement du foyer de l'attention implicite par décodage de l'activité cérébrale mesurée en électro-encéphalographie (EEG) avant l'affichage d'une cible visuelle dans 3 expériences réalisées chez des sujets sains. La première expérience aborde la problématique dans une condition où l'indication sur l'emplacement de la cible est globalement non-informative pour les sujets. Cependant, leur activité cérébrale suggère que ce type d'indication a tendance à induire un état d'alerte, de préparation ou d'orientation de l'attention dans le temps plutôt que dans l'espace. En lien avec ce résultat, la deuxième expérience aborde la problématique dans une condition ambiguë où l'attention du sujet s'oriente vers un emplacement sans lien systématique avec le contenu des indications. / Visuospatial attention is an information selection and processing mechanism whose overt manifestations consist of head or gaze shifts. In anticipation to new information, the focus of attention can also covertly shift to peripheral vision to share attention between two distinct locations: the overt one (center of gaze) and the covert one in periphery. In such a situation, the reaction to a target appearing at the focus of attention is enhanced with respect to targets appearing at unattended locations. This thesis addresses the problem of detecting the location of covert attention by decoding neural activity measured by electroencephalography (EEG) before target onset in 3 experiments on healthy subjects. The first experiment uses visuospatial cues that are non-informative about the target location. However, the neural activity reflects that non-informative cues tend to bring the subjects into a state related to alertness, motor preparation or temporal expectation rather than a spatial shift of attention. According to this result, the second experiment uses an ambiguous precueing condition in which the sujet's attention is shifted to spatial locations which bear a non-systematic relation to the information contained in the cues. With these ambiguous cues, we find that the proportion of targets displayed at unattended locations is equivalent to a non-informative condition, and that reaction speed and accuracy are dramatically impacted.

No description available.

L'attention focalisée est une fonction cognitive de haut niveau permettant à l'Homme de faciliter sélectivement certaines actions et perceptions. Dans un monde regorgeant de choix d'actions, et de possibilités de perceptions, l'attention focalisée représente une composante vitale de la cognition humaine. Un constat important doit cependant être noté : l'Homme est incapable de maintenir indéfiniment un état stable d'attention focalisée. Cette incapacité est mise en évidence pendant les tâches d'attention soutenue par l'apparition progressive de déficiences sensori-motrices au cours du temps. L'impulsivité motrice augmente alors, ainsi que le temps de réponse aux stimuli impératifs, et la sensibilité perceptive diminue. À l'heure actuelle, les bases neuronales du phénomène restent très peu connues et ce manque de connaissance est clairement perceptible au sein de deux champs disciplinaires - les Neurosciences Cognitives et l'Ingénierie Cognitive. En Neurosciences Cognitives, la question demeure ainsi posée : pourquoi l'Homme est-il incapable de maintenir un niveau de performance sensori-motrice optimal au cours de tâches d'attention soutenue ? En Ingénierie Cognitive, la problématique concerne le développement d'Interfaces Cerveau-Machine (ICM) passives : identifier les marqueurs neuronaux des déficits d'attention permettrait, à terme, de suivre en temps réel l'état cognitif de l'Homme et de l'alerter de la survenue de ces déficits durant son activité. Ces deux problématiques ont été traitées dans cette thèse. Dans un premier temps, je démontre que le maintien d'une attention focalisée sur une stimulation visuelle entraîne une rapide inhibition des aires visuelles corticales. Cette inhibition sensorielle serait liée à l'absence de variation de la stimulation sensorielle. Ainsi, l'inhibition sensorielle serait bénéfique au cours de tâches de recherche visuelle : elle permettrait à l'Homme d'éviter de réexaminer plusieurs fois le même stimulus, le même objet, la même localisation spatiale; mais lorsqu'une attention soutenue est requise, ce mécanisme serait alors à l'origine de l'apparition de déficiences sensorielles. La présence de cette inhibition sensorielle apporte une explication probante à la diminution de sensibilité perceptive et à l'allongement du temps de réaction qui caractérisent le phénomène. Je montre ensuite que l'activité de structures neuronales motrices et d'aires corticales connues pour sous-tendre l'attention focalisée (i.e., tractus cortico-spinal, et aires corticales motrice primaire, préfrontale et pariétale droite) augmente progressivement au cours d'une tâche d'attention soutenue. Ce sur-engagement reflèterait un processus de compensation en réponse au désengagement préalable des aires corticales sensorielles et à la diminution de la qualité des représentations perceptives. Aussi, l'augmentation d'activité des structures neuronales motrices expliquerait l'augmentation de l'impulsivité motrice, une des signatures comportementales des déficits d'attention. Dans un second temps, je teste la possibilité d'exploiter ces corrélats neuronaux des déficits d'attention afin de discriminer deux états attentionnels donnés (i.e., avec ou sans déficits d'attention) au sein d'une ICM passive. Nous avons pour cela appliqué des méthodes de classification supervisées sur des données de spectroscopie proche infra-rouge reflétant l'activité hémodynamique des aires corticales préfrontale et pariétale enregistrées pendant une tâche d'attention soutenue. Nous rapportons des résultats encourageant en termes de performance de classification pour le futur développement d'ICM passives. Pris ensemble, les résultats décrits dans cette thèse apportent une meilleure compréhension des corrélats neuronaux des déficits d'attention et montrent comment cette connaissance peut être exploitée afin de développer des systèmes permettant de limiter la survenue d'accidents et d'incidents liés à l'erreur humaine dans un contexte écologique. / Focused attention represents a high-level cognitive function enabling humans to selectively facilitate specific actions and perceptions. In a world full of choices of action, and of perceptual possibilities, focused attention appears to be a vital component of human cognition. One observation however, is worth making: human-beings are unable to maintain stable states of focused attention indefinitely. This inability manifests during sustained attention tasks with the progressive occurrence of sensory-motor deficiencies with time-on-task. The phenomenon - called attention decrement - is characterized by increases in motor impulsivity and in response times to imperative events, and by a reduction in perceptual sensitivity. So far, the neural underpinnings of attention decrement have not been fully elucidated and this lack of knowledge is clearly palpable within two disciplinary fields : Cognitive Neuroscience and Cognitive Engineering. In Cognitive Neuroscience, the associated question is why are human-beings unable to maintain an optimal sensory-motor performance during sustained attention tasks? In Cognitive Engineering, the lack of a complete scientific understanding of attentional issues impacts the development of efficient passive Brain-Computer interfaces (BCI), capable of detecting the occurrence of potentially dangerous attention decrements during the performance of everyday activities. Both issues have been addressed in this thesis. In terms of Cognitive Neuroscience, I demonstrate that sustaining focused attention on a visual stimulation rapidly leads to an inhibition of the visual cortices. This sensory inhibition can be causally related to the lack of changes in perceptual stimulation typically characterizing sustained attention tasks. While the mechanism may be beneficial during visual search tasks as it helps humans avoid processing the same stimulus, the same object, the same location several times, it can lead to the occurrence of sensory deficiencies when sustained attention is required. As such, the sensory inhibition provides a compelling explanation as to the decrease in perceptual sensitivity and to the increase in reaction time that typify attention decrement. I show in a second study that attention decrement is associated with an increase in the activity of motor- and attention-related neural structures (i.e., cortico-spinal tract, primary motor, prefrontal and right parietal cortices). This excessive engagement reflects a compensatory process occurring in response to the sensory disengagement already highlighted and to the related degradation of the quality of perceptual representations. It is notable that the excessive engagement of the motor neural structures with time-on-task provides a potential explanation for the increase in motor impulsivity typifying attention decrement. In terms of application of these new findings, I investigated the potential of exploiting these neural correlates of attention decrement to discriminate between two different attentional states (i.e., with or without attention decrement) through a passive BCI system. To do so, we applied supervised classification analyses on near-infrared spectroscopy signals reflecting the hemodynamic activity of prefrontal and parietal cortices as recorded during a sustained attention task. We achieved relatively promising classification performance results which bode well for the future development of passive BCI. When considered together, the results described in this thesis contribute towards a better understanding of the neural correlates of attention decrement and demonstrate how this novel knowledge can be exploited for the future development of systems which may enable a reduction in accidents and human error-driven incidents in real world environments.

Une Interface Cerveau-Machine (ICM) est un système permettant de transformer l'activité neurale du cerveau en une commande d'effecteurs externes. Cette étude correspond à une étape vers une ICM totalement autonome fonctionnant dans un environnement naturel ce qui est d'une importance cruciale pour les futures applications cliniques d'une ICM. Pour représenter l'environnement naturel, des expériences avec une ICM binaire asynchrone ont été réalisées avec des animaux libres de se mouvoir. En comparaison avec les études précédentes, des expériences sur le long terme ont été réalisées, ce qui est plus conforme aux exigences des applications de la vie réelle. L'objectif principal de cette étude est de différencier le modèle spécifique neuronal lié à l'intention d'action de l'activité de fond du cerveau chez des animaux libres de tous mouvements. Pour atteindre le niveau nécessaire de sélectivité, l'analyse Multi-Voies PLS a été choisie sachant qu'elle fournit simultanément un traitement du signal dans plusieurs domaines, à savoir, temporel, fréquentiel et spatial. Pour améliorer la capacité de l'approche générique Multi-Voies PLS pour le traitement de données à grandes dimensions, l'algorithme « Itérative NPLS » est introduit dans notre travail. En ayant des besoins plus faibles en mémoire, cet algorithme fournit des traitements de grands ensembles de données, permet une résolution élevée, préserve l'exactitude de l'algorithme générique et démontre une meilleure robustesse. Pour la calibration adaptative d'un système ICM, l'algorithme récursif NPLS est proposé. Finalement, l'algorithme pénalisé NPLS est développé pour la sélection efficace d'un sous-ensemble de fonctions, à savoir, un sous-ensemble d'électrodes. Les algorithmes proposés ont été testés sur des ensembles de données artificielles et réelles. Ils ont démontré une performance qui est comparable à celle d'un algorithme générique NPLS. Leur efficacité de calcul est acceptable pour les applications en temps réel. Les algorithmes développés ont été appliqués à la calibration d'un système ICM et ont été utilisés dans des expériences d'ICM avec bouclage en temps réel chez des animaux. Enfin, les méthodes proposées représentent une approche prospective pour de futurs développements de systèmes ICM humains. / Brain Computer Interface (BCI) is a system for translation of brain neural activity into commands for external devices. This study was undertaken as a step toward the fully autonomous (self-paced) BCI functioning in natural environment which is of crucial importance for BCI clinical applications. To model the natural environment binary self-paced BCI experiments were carried out in freely moving animals. In comparison to the previous works, the long-term experimental sessions were carried out, which better comply with the real-life applications requirements. The main goal of the study was to discriminate the specific neuronal pattern related to the animal's control action against background brain activity of freely-moving animal. To achieve the necessary level of selectivity the Multi-Way Analysis was chosen since it provides a simultaneous signal processing in several domains, namely, temporal, frequency and spatial. To improve the capacity of the generic Multy-Way PLS approach for treatment of high-dimensional data, the Iterative NPLS algorithm is introduced in the current study. Having lower memory requirements it provides huge datasets treatment, allows high resolution, preserves the accuracy of the generic algorithm, and demonstrates better robustness. For adaptive calibration of BCI system the Recursive NPLS algorithm is proposed. Finally, the Penalized NPLS algorithm is developed for effective selection of feature subsets, namely, for subset of electrodes. The proposed algorithms were tested on artificial and real datasets. They demonstrated performance which either suppress or is comparable with one of the generic NPLS algorithm. Their computational efficiency is acceptable for the real-time applications. Developed algorithms were applied for calibration of the BCI system and were used in the real-time close-loop binary BCI experiments in animals. The proposed methods represent a prospective approach for further development of a human BCI system.

For a wide range of people with limited upper- and lower-body mobility, interaction with robots remains a challenging problem. Due to various health conditions, they are often unable to use standard joystick interface, most of wheelchairs are equipped with. To accommodate this audience, a number of alternative human-machine interfaces have been designed, such as single switch, sip-and-puff, brain-computer interfaces. They are known as low throughput interfaces referring to the amount of information that an operator can pass into the machine. Using them to control a wheelchair poses a number of challenges. This thesis makes several contributions towards the design of robotic wheelchairs controlled via low throughput human-machine interfaces: (1) To improve wheelchair motion control, an adaptive controller with online parameter estimation is developed for a differentially driven wheelchair. (2) Steering control scheme is designed that provides a unified framework integrating different types of low throughput human-machine interfaces with an obstacle avoidance mechanism. (3) A novel approach to the design of control systems with low throughput human-machine interfaces has been proposed. Based on the approach, position control scheme for a holonomic robot that aims to probabilistically minimize time to destination is developed and tested in simulation. The scheme is adopted for a real differentially driven wheelchair. In contrast to other methods, the proposed scheme allows to use prior information about the user habits, but does not restrict navigation to a set of pre-defined points, and parallelizes the inference and motion reducing the navigation time. (4) To enable the real time operation of the position control, a high-performance algorithm for single-source any-angle path planning on a grid has been developed. By abandoning the graph model and introducing discrete geometric primitives to represent the propagating wave front, we were able to design a planning algorithm that uses only integer addition and bit shifting. Experiments revealed a significant performance advantage. Several modifications, including optimal and multithreaded implementations, are also presented.

La thématique générale de notre thèse porte sur le transfert virtuel/réel de connaissances spatiales, et plus particulièrement sur l’identification de variables susceptibles d’optimiser ce transfert. Notamment, nous nous sommes intéressés à l’influence des interfaces de déplacement, de l’engagement physique et des informations sensorielles relatives au corps sur l’acquisition et le transfert de connaissances spatiales du virtuel vers le réel. L’engagement physique a été manipulé à l’aide de deux interacteurs (tapis roulant Vs joystick) proposant respectivement un fort et un faible engagement physique, ainsi que par une Interface Cerveau Ordinateur (ICO), permettant de commander un déplacement à l’aide de l’activité cérébrale du sujet, supprimant ainsi toute composante motrice effective. Enfin nous avons également manipulé l’expertise en jeu vidéo, variable susceptible de jouer un rôle important dans l’acquisition et l’utilisation des compétences spatiales au sens large, et plus spécifiquement dans le transfert virtuel-réel.Nos expérimentations consistaient à apprendre un trajet à l’aide d’une des situations d’interaction définie ci-dessus. Le transfert virtuel/réel des connaissances spatiales a été ensuite évalué à l’aide de 6 tâches : une tâche de classification chronologique de photos, une tâche d’estimation de la distance parcourue et une tâche d’estimation de directions (tâches égocentriques) ; une tâche de croquis du trajet, une tâche d’estimation de la direction du point de départ du trajet (tâche allocentrique) ; et enfin une tâche globale de wayfinding consistant à reproduire en environnement réel le trajet préalablement appris en virtuel.Nos résultats montrent que les effets de l’engagement physique (en particulier des informations proprioceptives et vestibulaires) et de l’expertise en jeu vidéo sont différents selon la nature de la compétence spatiale sollicitée (composante égocentrique, allocentrique ou reproduction du parcours). De plus, les résultats obtenus à l’aide de l’ICO permettent de préciser le rôle de la composante motrice dans l’acquisition et le transfert virtuel/réel de compétences spatiales.L’ensemble de ces données sont discutées au regard des modèles d’acquisition et d’utilisation des connaissances spatiales, tels que le modèle Landmark-Route-Survey et la théorie des graphes. Les perspectives de notre travail concernent le développement d’interfaces adaptées aux utilisateurs ainsi que l’entraînement ou le réentraînement des compétences spatiales de sujets âgés ou de patients présentant des pathologies lésionnelles et/ou dégénératives. / The general theme of our thesis focuses on the transfer of spatial learning from a virtual to a real environment, and more precisely on the identification of parameters that might optimize this transfer. Namely, we investigated the influence of displacement interfaces, of the physical involvement, and of the body-based information on the acquisition and the transfer of spatial learning from a virtual to a real world. The physical involvement was manipulated with the help of two interactors (Treadmill vs. Joystick) that respectively propose strong and mild physical involvements as well with the help of a Brain-Computer Interface (BCI). The BCI allows controlling displacements using subject’s brain activity, thus nullifying all effective motor components. Finally, we also manipulated videogame experience, a parameter supposed to play an important role in the acquisition and the use of spatial skills in the widest sense and, more specifically in the virtual-to-real transfer. Our experimentations first consisted in route learning within one of the above described interaction conditions. Then, the virtual-to-real transfer of spatial learning was evaluated with 6 tasks: the picture classification task, the distance estimation task, and the direction estimation task (egocentric task); the sketch-mapping task, the starting point estimation task (exocentric task); and finally the global wayfinding task, consisting in reproducing the previously learned virtual route in the real environment.Our results reveal that the effects of the physical involvement (in particular, of the proprioceptive and vestibular information) and of the videogame experience are different, depending on the nature of the spatial ability needed (egocentric or exocentric component, route reproduction). Moreover, the results obtained with the BCI allow to precise the role of the motor component in the acquisition and the transfer of spatial skills from the virtual to the real environment.These findings are discussed relative to the models of spatial knowledge acquisition and its utilization, such as the Landmark-Route-Survey model and the graph theory. Future trends of our work will concern the development of user-friendly interfaces as well as the training or the retraining of spatial abilities in older adults with or without degenerative disorders and patients with various brain lesions.

Les interfaces cerveau-machine (ICM) permettent de contrôler un appareil électronique grâce aux signaux cérébraux. Plusieurs méthodes de mesure de ces signaux, invasives ou non, peuvent être utilisées. L'électro-encéphalographie (EEG) est la méthode non-invasive la plus étudiée car elle propose une bonne résolution temporelle et le matériel nécessaire est bien moins volumineux que les systèmes de mesure des champs magnétiques.L'EEG a cependant une faible résolution spatiale, ce qui limite les performances des ICM utilisant cette méthode de mesure. Ce souci de résolution spatiale peut être réglé en utilisant le problème inverse de l'EEG, qui permet de passer des potentiels mesurés en surface à une distribution volumique des sources de courant dans le cerveau. Le principal verrou de cette technique est le temps nécessaire (plusieurs heures) pour calculer avec une station de travail la matrice permettant de résoudre leproblème inverse. Dans le cadre de cette thèse, nous avons étudié les solutions actuelles pour accélérer matériellement la conception de cette matrice. Nous avons ainsi proposé, conçu et testé une architecture électronique dédiée à ces traitements pour ICM. Les premiers résultats démontrent que notre solution permet de passer de plusieurs heures de calcul sur une station de travail à quelques minutes sur circuit reconfigurable. Cette accélération des traitements d'imagerie par EEG facilitera grandement la recherche sur l'utilisation du problème inverse et ouvrira ainsi de nouvelles perspectives pour le domaine de l'ICM. / Brain-Computer Interfaces (BCI) are systems that use brain activity to control an external device. Various techniques can be used to collect the neural signals. The measurement can be invasive ornon-invasive. Electroencephalography (EEG) is the most studied non-invasive method. Indeed, EEG offers a fine temporal resolution and ease of use but its spatial resolution limits the performances of BCI based on EEG. The spatial resolution of EEG can be improved by solving the EEG inverse problem, which allows to determine the distribution of electrical sources in the brain from EEG. Currently, the main difficulty is the time needed(several hours) to compute the matrix which is used to solve the EEG inverse problem. This document describes the proposed solution to provide a hardware acceleration of the matrix computation. A dedicated electronic architecture has been implemented and tested. First results show that the proposed architecture divides the calculation time by a factor of 60 on a programmable circuit. This acceleration opens up new perspectives for EEG BCI.

Orientador: Douglas Domingues Bueno / Resumo: A busca por uma melhor compreensão das regiões do cérebro e suas funções nas ações humanas tem sido uma tarefa árdua, porém muito útil, principalmente para aplicações da engenharia de interface cérebro-máquina (ICM), bem como para o auxílio a diagnósticos médicos a partir de sinais obtidos dos pacientes em avaliação. No contexto do presente trabalho, destacam-se os trabalhos de interface cérebro-máquina (ICM) pela abrangência no envolvimento de técnicas, métodos e ferramentas comumente estudadas nos cursos de engenharia. Em particular, análises envolvendo técnicas de processamento de sinais de eletroencefalograma (EEG) têm se mostrado de significativa importância para o desenvolvimento dessa área. Uma abordagem amplamente utilizada nesse contexto é a ICM usando Potenciais Visuais Evocados de Estados Estacionários (SSVEP, do inglês Steady-State Visual Evoked Potentials), que, de forma geral, são sinais caracterizados pela resposta evocada do cérebro a estímulos visuais modulados em uma frequência específica. Assim, este trabalho tem o objetivo de propor uma generalização do coeficiente de correlação, conceito-base da análise de correlação canônica (CCA), técnica que tem se mostrado robusta e eficiente no reconhecimento de padrões, especialmente no caso dos SSVEP, e detalhar seu comportamento em função dos parâmetros relevantes para se estabelecer melhores práticas de uso em aplicações de ICM, incluindo fatores fisiológicos, técnicos e operacionais. / Abstract: The search for a better understanding of the brain's anatomy and its functions on human actions has been a harsh yet very useful task, especially for brain-computer interface engineering applications, as well as for medical diagnosis using signals from patients. In the context of this work, brain-computer interface (BCI) applications are highlighted due to their compreehensiveness related to techniques, methods and tools commonly studied in engineering. In particular, analyses involving eletroencephalogram (EEG) signals processing have proven to be of great significance for developing this field of study. A widely used approach is Steady State Visual Evoked Potentials (SSVEP) based BCI, which, in general, are signals characterized by the brain’s evoked response to visual stimuli modulated at a certain frequency. This work aims thus to propose a generalization of the correlation coefficient, which entails Canonical Correlation Analysis (CCA), a technique that has presented robustness and efficiency for pattern recognition, especially in SSVEP-based BCIs, and describe its behavior under relevant varying parameters to stablish better use practices in BCI applications, comprising physiological, technical and operational factors. / Mestre

Normal movement execution requires proper coupling of motor and sensory activation. An increasing body of literature supports the idea that incorporation of sensory stimulation into motor rehabilitation practices increases its effectiveness. Paired associative stimulation (PAS) studies, in which afferent and efferent pathways are activated in tandem, have brought attention to the importance of well-timed stimulation rather than non-associative (i.e., open-loop) activation. In patients with tetraplegia resulting from spinal cord injury (SCI), varying degrees of upper limb function may remain and could be harnessed for rehabilitation. Incorporating associative sensory stimulation coupled with self-paced motor training would be a means for supplementing sensory deficits and improving functional outcomes. In a motor rehabilitation setting, it seems plausible that sensory feedback stimulation in response to volitional movement execution (to the extent possible), which is not utilized in most PAS protocols, would produce greater benefits. This capability is developed and tested in the present study by implementing a brain-computer interface (BCI) to apply sensory stimulation synchronized with movement execution through the detection of movement intent in real time from electroencephalography (EEG). The results demonstrate that accurate sensory stimulation application in response to movement intent is feasible in SCI patients with chronic motor deficit and often precedes the onset of movement, which is deemed optimal by PAS investigations that do not involve a volitional movement task.