Brain-computer interfaces are an emerging technology that could provide channels for communication and control to severely disabled people suffering from locked-in syndrome. It has been found that motor imagery can be detected and classified from EEG signals. The motivation of the present work was to compare several algorithms for motor imagery classification in EEG signals as well as to test several novel algorithms. The algorithms tested included the popular method of common spatial patterns (CSP) spatial filtering followed by linear discriminant analysis (LDA) classification of log-variance features (CSP+LDA). A second set of algorithms used classification based on concepts from Riemannian geometry. The basic idea of these methods is that sample spatial covariance matrices (SCMs) of EEG epochs belong to the Riemannian manifold of symmetric positive-definite (SPD) matrices and that the tangent space at any SPD matrix on the manifold is a finite-dimensional Euclidean space. Riemannian classification methods tested included minimum distance to Riemannian mean (MDRM), tangent space LDA (TSLDA), and Fisher geodesic filtering followed by MDRM classification (FGDA). The novel algorithms aimed to combine the CSP method with the Riemannian geometry methods. CSP spatial filtering was performed prior to sample SCM calculation and subsequent classification using Riemannian methods. The novel algorithms were found to improve classification accuracy as well as reduce the computational costs of Riemannian classification methods for binary, synchronous classification on BCI competition IV dataset 2a. / Master of Science

This study focuses on realization of a Brain Computer Interface (BCI)for the paralyzed to control assistive environmental devices. For this purpose, different motor imagery tasks are classified using different signal processing methods. Specifically, band-pass filtering, Laplacian filtering, and common average reference (CAR) filtering areused to enhance the EEG signal. For feature extraction / Common Spatial Pattern (CSP), Power Spectral Density (PSD), and Principal Component Analysis (PCA) are tested. Linear Feature Normalization (LFN), Gaussian Feature Normalization (GFN), and Unit-norm Feature Vector Normalization (UFVN) are studied in Support Vector Machine (SVM) and Artificial Neural Network (ANN) classification. In order to evaluate and compare the performance of the methodologies, classification accuracy, Cohen&rsquo / s kappa coefficient, and Nykopp&rsquo / s information transfer are utilized. The first experiments on classifying motor imagery tasks are realized on the 3-class dataset (V) provided for BCI Competition III. Also, a 4-class problem is studied using the dataset (IIa) provided for BCI Competition IV. Then, 5 different tasks are studied in the METU Brain Research Laboratory to find the optimum number and type of tasks to control a motor imagery based BCI. Thereafter, an interface is designed for the paralyzed to control assistive environmental devices. Finally, a test application is implemented and online performance of the design is evaluated.