Brain-computer interfaces (BCIs) might restore communication to people severely disabled by amyotrophic lateral sclerosis (ALS) or other disorders. We sought to: 1) define a protocol for determining whether a person with ALS can use a visual P300-based BCI; 2) determine what proportion of this population can use the BCI; and 3) identify factors affecting BCI performance. Twenty-five individuals with ALS completed an evaluation protocol using a standard 6 × 6 matrix and parameters selected by stepwise linear discrimination. With an 8-channel EEG montage, the subjects fell into two groups in BCI accuracy (chance accuracy 3%). Seventeen averaged 92 (± 3)% (range 71-100%), which is adequate for communication (G70 group). Eight averaged 12 (± 6)% (range 0-36%), inadequate for communication (L40 subject group). Performance did not correlate with disability: 11/17 (65%) of G70 subjects were severely disabled (i.e. ALSFRS-R < 5). All L40 subjects had visual impairments (e.g. nystagmus, diplopia, ptosis). P300 was larger and more anterior in G70 subjects. A 16-channel montage did not significantly improve accuracy. In conclusion, most people severely disabled by ALS could use a visual P300-based BCI for communication. In those who could not, visual impairment was the principal obstacle. For these individuals, auditory P300-based BCIs might be effective.

Approximately 20 million people in the United States suffer from irreversible nerve damage and would benefit from a neuroprosthetic device modulated by a Brain-Computer Interface (BCI). These devices restore independence by replacing peripheral nervous system functions such as peripheral control. Although there are currently devices under investigation, contemporary methods fail to offer adaptability and proper signal recognition for output devices. Human anatomical differences prevent the use of a fixed model system from providing consistent classification performance among various subjects. Furthermore, notoriously noisy signals such as Electroencephalography (EEG) require complex measures for signal detection. Therefore, there remains a tremendous need to explore and improve new algorithms. This report investigates a signal-processing model that is better suited for BCI applications because it incorporates machine learning and fuzzy logic. Whereas traditional machine learning techniques utilize precise functions to map the input into the feature space, fuzzy-neuro system apply imprecise membership functions to account for uncertainty and can be updated via supervised learning. Thus, this method is better equipped to tolerate uncertainty and improve performance over time. Moreover, a variation of this algorithm used in this study has a higher convergence speed. The proposed two-stage signal-processing model consists of feature extraction and feature translation, with an emphasis on the latter. The feature extraction phase includes Blind Source Separation (BSS) and the Discrete Wavelet Transform (DWT), and the feature translation stage includes the Takagi-Sugeno-Kang Fuzzy-Neural Network (TSKFNN). Performance of the proposed model corresponds to an average classification accuracy of 79.4 % for 40 subjects, which is higher than the standard literature values, 75%, making this a superior model.

No description available.

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.

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.

Une Interface Cerveau-Ordinateur (ICO) est un système de communication qui permet à ses utilisateurs d'envoyer des commandes à un ordinateur via leur activité cérébrale, cette activité étant mesurée, généralement par ÉlectroEncéphaloGraphie (EEG), et traitée par le système. Dans la première partie de cette thèse, dédiée au traitement et à la classification des signaux EEG, nous avons cherché à concevoir des ICOs interprétables et plus efficaces. Pour ce faire, nous avons tout d'abord proposé FuRIA, un algorithme d'extraction de caractéris- tiques utilisant les solutions inverses. Nous avons également proposé et étudié l'utilisation des Systèmes d'Inférences Flous (SIF) pour la classification. Nos évaluations ont montré que FuRIA et les SIF pouvaient obtenir de très bonnes performances de classification. De plus, nous avons proposé une méthode utilisant ces deux algorithmes afin de concevoir une ICO complétement interprétable. Enfin, nous avons proposé de considérer la conception d'ICOs asynchrones comme un problème de rejet de motifs. Notre étude a introduit de nouvelles techniques et a permis d'identifier les classifieurs et les techniques de rejet les plus appropriés pour ce problème. Dans la deuxième partie de cette thèse, nous avons cherché à concevoir des applications de Réalité Virtuelle (RV) controlées par une ICO. Nous avons tout d'abord étudié les performances et les préférences de participants qui interagissaient avec une application ludique de RV à l'aide d'une ICO asynchrone. Nos résultats ont mis en évidence le besoin d'utiliser des ICO adaptées à l'utilisateur ainsi que l'importance du retour visuel. Enfin, nous avons développé une application de RV permettant à un utilisateur d'explorer un musée virtuel par la pensée. Dans ce but, nous avons conçu une ICO asynchrone et proposé une nouvelle technique d'interaction permettant à l'utilisateur d'envoyer des commandes de haut niveau. Une première évaluation semble montrer que l'utilisateur peut explorer le musée plus rapidement avec cette technique qu'avec les techniques actuelles.

La chaise roulante contrôlée par ondes cérébrales développée dans le cadre de cette thèse, et ci-après nommée BCW pour "Brain Controlled Wheelchair", est un système robotique pour les personnes qui, comme celles victimes d'un "locked-in syndrom", n'ont pas la capacité d'utiliser une interface conventionnelle. Notre but est de développer un système utilisable dans les hôpitaux et aux domiciles des utilisateurs, avec un minimum de modifications des infrastructures, pour les aider à récupérer un peu de mobilité. La difficulté principale est de contrôler de manière continue et précise les mouvements de la chaise roulante à partir d'une interface cerveau machine, typiquement très limitée en terme de taux de transfert de l'information. Par ailleurs, nous imposons que notre système soit sécuritaire, ergonomique et relativement bon marché. Notre stratégie repose sur 1) contraindre les déplacements de la chaise roulante le long de chemins virtuels prédéfinis, et 2) une interface cerveau machine lente mais précise, basée sur le signal P300, pour sélectionner la destination dans un menu. Cette stratégie réduit le contrôle à la sélection de la destination désirée, et donc ne nécessite que très peu d'effort de concentration de la part de l'utilisateur. Par ailleurs, la trajectoire est prévisible, ce qui contribue à réduire le stress et la frustration induits par des trajectoires générées par un agent artificiel. Nous proposons deux interfaces rapides pour permettre d'arrêter la chaise roulante en cours de déplacement. Nous avons développé une interface hybride qui combine l'interface P300 lente utilisée pour sélectionner la destination, avec une des deux interfaces rapides pour arrêter la chaise. Nous avons conduit des expériences avec des sujets non handicapés, et nous avons montré que, après une courte phase de calibration, il était possible de sélectionner une destination en 15 secondes en moyenne, avec un taux d'erreur de moins de 1%. Les interfaces rapides quant à elles permettent d'arrêter la chaise en moins de 5 secondes en moyenne. Par ailleurs, nous avons constaté que les performances de l'interface restaient égales en mouvement et à l'arrêt. Finalement, nous avons évalué notre stratégie et comparé avec les autres projets de chaise roulantes contrôlées par ondes cérébrales. Malgré le délai requis pour sélectionner une destination sur notre interface, notre chaise est plus rapide que les autres (36% plus rapide que MAIA): grâce à notre contrôle de trajectoire, notre chaise suit toujours le chemin le plus court et il est possible d'autoriser une plus grande vitesse sans compromettre la sécurité de l'utilisateur. Nous avons également comparé en utilisant une fonction de cout qui prends en compte le temps de trajet et l'effort de concentration requis; le cout de notre stratégie est de loin le plus bas (le meilleur autre score est 72% plus grand). Le résultat de ce projet est une chaise roulante contrôlée par ondes cérébrales, entièrement originale et fonctionnelle, qui permet de se déplacer dans un environnement connu en un temps raisonnable. L'accent a été mis sur la sécurité et le confort de l'utilisateur: le contrôle de trajectoire garanti une trajectoire régulière, sans heurts et prévisible, cependant que l'effort mental et minimisé par la réduction du pilotage à la sélection de la destination.

A combined view of the human brain and computer-generated virtual realities is motivated by recent developments in cognitive neuroscience and human-computer interaction (HCI). The emergence of new theories of human brain function, together with an increasing use of realistic human-computer interaction, give reason to believe that a better understanding of the relationship between human brains and virtual realities is both possible and valuable. The concept of “presence”, described as the subjective feeling of being in a place that feels real, can serve as a cornerstone concept in the development of such an understanding, as computer-generated presence is tightly related to how human brains work in virtual realities. In this thesis, presence is related both to theoretical discussions rooted in theories of human brain function, and to measurements of brain activity during realistic interaction. The practical implications of such results are further developed by considering potential applications. This includes the development and evaluation of a prototype application, motivated by presented principles. The theoretical conception of presence in this thesis relies on general principles of brain function, and describes presence as a general cognitive function, not specifically related to virtual realities. Virtual reality (VR) is an excellent technology for investigating and taking advantage of all aspects of presence, but a more general interpretation allows the same principles to be applied to a wide range of applications. Functional magnetic resonance imaging (fMRI) was used to study the working human brain in VR. Such data can inform and constrain further discussion about presence. Using two different experimental designs we have investigated both the effect of basic aspects of VR interaction, as well as the neural correlates of disrupted presence in a naturalistic environment. Reality-based brain-computer interaction (RBBCI) is suggested as a concept for summarizing the motivations for, and the context of, applications building on an understanding of human brains in virtual realities. The RBBCI prototype application we developed did not achieve the set goals, but much remains to be investigated and lessons from our evaluation point to possible ways forward. A developed use of methods and techniques from computer gaming is of particular interest. / Ett kombinerat perspektiv på den mänskliga hjärnan och datorgenererade virtuella verkligheter motiveras av den senaste utvecklingen inom kognitiv neurovetenskap och människa-datorinteraktion (MDI). Framväxten av nya teorier om den mänskliga hjärnan, tillsammans med en ökande användning av realistisk människa-datorinteraktion, gör det troligt att en bättre förståelse för relationen mellan mänskliga hjärnor och virtuella verkligheter är både möjlig och värdefull. Begreppet "närvaro", som i detta sammanhang beskrivs som den subjektiva känslan av att vara på en plats som känns verklig, kan fungera som en hörnsten i utvecklingen av en sådan förståelse, då datorgenererad närvaro är tätt kopplat till hur mänskliga hjärnor fungerar i virtuella verkligheter. I denna avhandling kopplas närvaro både till teoretiska diskussioner grundade i teorier om den mänskliga hjärnan, och till mätningar av hjärnans aktivitet under realistisk interaktion. De praktiska konsekvenserna av sådana resultat utvecklas vidare med en närmare titt på potentiella tillämpningar. Detta inkluderar utveckling och utvärdering av en prototypapplikation, motiverad av de presenterade principerna. Den teoretiska diskussionen av närvaro i denna avhandling bygger på allmänna principer för hjärnans funktion, och beskriver känslan av närvaro som en generell kognitiv funktion, inte specifikt relaterad till virtuella verkligheter. Virtuell verklighet (virtual reality, VR) är en utmärkt teknik för att undersöka och dra nytta av alla aspekter av närvaro, men en mer allmän tolkning gör att samma principer kan tillämpas på ett brett spektrum av applikationer. Funktionell hjärnavbildning (fMRI) användes för att studera den arbetande mänskliga hjärnan i VR. Sådant data kan informera och begränsa en vidare diskussion av närvaro. Med hjälp av två olika försöksdesigner har vi har undersökt både effekten av grundläggande aspekter av VR-interaktion, och neurala korrelat av störd närvaro i en naturalistisk miljö. Verklighets-baserad hjärna-dator interaktion (reality-based brain-computer interaction, RBBCI) föreslås som ett begrepp för att sammanfatta motiv och kontext för applikationer som bygger på en förståelse av den mänskliga hjärnan i virtuella verkligheter. Den prototypapplikation vi utvecklade uppnådde inte de uppsatta målen, men mycket återstår att utforska och lärdomar från vår utvärdering pekar på möjliga vägar framåt. En vidare användning av metoder och tekniker från dataspel är speciellt intressant.

In this study, a P300 based Brain-Computer Interface (BCI) system design is realized by the implementation of the Spelling Paradigm. The main challenge in these systems is to improve the speed of the prediction mechanisms by the application of different signal processing and pattern classification techniques in BCI problems. The thesis study includes the design and implementation of a 10 channel Electroencephalographic (EEG) data acquisition system to be practically used in BCI applications. The electrical measurements are realized with active electrodes for continuous EEG recording. The data is transferred via USB so that the device can be operated by any computer. v Wiener filtering is applied to P300 Speller as a signal enhancement tool for the first time in the literature. With this method, the optimum temporal frequency bands for user specific P300 responses are determined. The classification of the responses is performed by using Support Vector Machines (SVM&rsquo / s) and Bayesian decision. These methods are independently applied to the row-column intensification groups of P300 speller to observe the differences in human perception to these two visual stimulation types. It is observed from the investigated datasets that the prediction accuracies in these two groups are different for each subject even for optimum classification parameters. Furthermore, in these datasets, the classification accuracy was improved when the signals are preprocessed with Wiener filtering. With this method, the test characters are predicted with 100% accuracy in 4 trial repetitions in P300 Speller dataset of BCI Competition II. Besides, only 8 trials are needed to predict the target character with the designed BCI system.

This thesis study focuses on the realization of an online cue based Motor Imagery (MI) Brain Computer Interface (BCI). For this purpose, some signal processing and classification methods are investigated. Specifically, several time-spatial-frequency methods, namely the Short Time Fourier Transform (STFT), Common Spatial Frequency Patterns (CSFP) and the Morlet Transform (MT) are implemented on a 2-class MI BCI system. Distinction Sensitive Learning Vector Quantization (DSLVQ) method is used as a feature selection method. The performance of these methodologies is evaluated with the linear and nonlinear Support Vector Machines (SVM), Multilayer Perceptron (MLP) and Naive Bayesian (NB) classifiers. The methodologies are tested on BCI Competition IV dataset IIb and an average kappa value of 0.45 is obtained on the dataset. According to the classification results, the algorithms presented here obtain the 4th level in the competition as compared to the other algorithms in the competition. Offline experiments are performed in METU Brain Research Laboratories and Hacettepe Biophysics Department on two subjects with the original cue-based MI BCI paradigm. Average prediction accuracy of the methods on a 2-class BCI is evaluated to be 76.26% in these datasets. Furthermore, two online BCI applications are developed: the ping-pong game and the electrical wheelchair control. For these applications, average classification accuracy is found to be 70%. During the offline experiments, the performance of the developed system is observed to be highly dependent on the subject training and experience. According to the results, the EEG channels P3 and P4, which are considered to be irrelevant with the motor imagination, provided the best classification performance on the offline experiments. Regarding the observations on the experiments, this process is related to the stimulation mechanism in the cue based applications and consequent visual evoking effects on the subjects.