Optimizing EEG Signal Classification for Motor Imagery BCIs: FilterBank CSP with Riemannian Manifolds and Ensemble Learning Models

Motor imagery (MI) is a compelling cognitive phenomenon situated at the intersection of cognitive neuroscience and technology, offering insights into human cognition and a spectrum of practical applications. Electroencephalography (EEG) emerges as a technology, offering a non-invasive means to record electrical activity within the brain. Motor imagery-based Brain-Computer Interfaces (MI-BCIs) enables the translation of cerebral activity into implementable commands found in the sensorimotor areas of the brain. This paper offers a comprehensive exploration of MI, delving into its practical implications, the complexities it entails, and the critical role this research focuses on enhancing the classification accuracy of EEG signals with Motor Imagery task. We employ a comprehensive approach that integrates Filter Bank Common Spatial Pattern (CSP) and the Riemannian manifold to extract features, aiming at maintaining critical signal details. Furthermore, we utilize Linear Discriminant Analysis (LDA) alongside advanced classification methods, such as AdaBoost and Total Boost, to elevate classification accuracy. Our results, reveal significant improvements in the classification accuracy. This research contributes to the advancement of MI EEG signal classification and opens new avenues for applications in fields such as brain-computer interfaces and medical diagnostics.