1. Inicio
  2. Atrás
Título: EEG/ECoG-based BCI systems: a NeuroFuzzy approach using recurrent neural networks and adaptive filters
Autores: EMMANUEL MORALES FLORES
Fecha: 2015-03-17
Publicador: INAOE
Fuente:
Tipo: info:eu-repo/semantics/doctoralThesis
Tema: info:eu-repo/classification/Cerebral/Brain computer
info:eu-repo/classification/Redes neuronales/Neurophysiological signls
info:eu-repo/classification/Electroencefalografía/Electroencephalography
info:eu-repo/classification/Dinámica recurrente/Dynamical recurrent networks
info:eu-repo/classification/Sistemas difusos/Fuzzy systems
info:eu-repo/classification/cti/1
info:eu-repo/classification/cti/22
info:eu-repo/classification/cti/2203
Descripción: A brain computer interface (BCI) is a system aimed to provide the brain with an additional channel of communication and control, which does not depend on the normal output pathways. This dissertation is focused on the study of signal processing techniques to address two issues of current BCI methodologies. These issues are related to spatial filtering techniques and approaches for capturing temporal behavior of electrical brain signals recorded through two different modalities: Electroencephalography (EEG) and electrocorticography (ECoG). Concerning to spatial filtering, a non-supervised algorithm based on the steepest descent method to adapt spatial filter’s coefficients for preprocessing ECoG signals is proposed.
Idioma: eng