Catálogo de publicaciones - tesis

Compartir en
redes sociales


Título de Acceso Abierto

Algoritmos bioinspirados para la implementación de interfaces cerebro computadoras

Iván Emilio Gareis Hugo Leonardo Rufiner Eric Laciar Leber Pablo Diez Diego Tomassi Enrique Espinelli

acceptedVersion.

Resumen/Descripción – provisto por el repositorio digital
Brain-computer interfaces are systems that provide communication to an external device by means of directly measuring the brain activity. These systems rely on signal processing and machine learning stages to succsefully translate the registered brain-computer interfaces we can find different event related potentials which are usually masked by large noise. This is one of the main signal processing problems to solve when estimating or classifying P300 event related potentials in brain-computer interfaces. Classification and estimation of small repetitive signals usually require recording and processing several different realizations of the signal of interest. Each repetition is a time consuming process that reduces the information transfer rate. To cope with this issue we propose a novel autoencoder variation, called coherent averaging estimation autoencoder with a new multi-objective cost function. We illustrate its use and analyze its performance in the problem of event related potentials processing. Experimental results showing the advantages of the proposed approach are presented as well.
Palabras clave – provistas por el repositorio digital

Brain computer interfaces; Artificial neural networks; Autoencoders; Event related potentials; Electroencephalography; Coherent averaging; Interfaces cerebro computadora; Redes neuronales artificiales; Autocodificadores; Potenciales relacionados con eventos; Electroencefalografía; Promediación coherente

Disponibilidad
Institución detectada Año de publicación Navegá Descargá Solicitá
No requiere 2017 Biblioteca Virtual de la Universidad Nacional del Litoral (SNRD) acceso abierto

Información

Tipo de recurso:

tesis

Idiomas de la publicación

  • español castellano

País de edición

Argentina

Fecha de publicación