Nombre: LEANDRO BUENO

Fecha de publicación: 06/06/2017
Supervisor:

Nombre	Papel
ANDRE FERREIRA	Co-advisor *
TEODIANO FREIRE BASTOS FILHO	Advisor *

Junta de examinadores:

Nombre	Papel
ALESSANDRO BOTTI BENEVIDES	External Examiner *
ANDRE FERREIRA	Co advisor *
ANSELMO FRIZERA NETO	Internal Examiner *
EDUARDO ROCON DE LIMA	External Examiner *
JORGE LEONID ACHING SAMATELO	External Examiner *

Páginas

Sumario: This Doctoral Thesis presents the development of a Brain Computer Interface (BCI) system using Electroencephalography (EEG) signals and Self Organizing
Maps (SOM) artifcial neural networks as classifer. In this Thesis the problems of
a BCI are analyzed and the classifcation results of the system is presented. This system uses a clinic acquisition equipment for EEG signal acquisition and a personal computer to process the data, using the energy of the frequency components of the EEG signal as characteristics and a classifer based on a Self Organizing Map as classifer. The great challenge in using SOM as a classifer is the interpretation of the outputs of the map, as it has as many outputs as it has neurons in the map. The contribution of this Thesis is in the interpretation method of the outputs of the map, which is done by means of the use of a set of masks that represents the probability of the activation of a neuron in the map representing a specifc class. The algorithms used on this Doctoral Thesis can be easily adapted to be executed in embedded systems with less processing power, like Digital Signal Processors (DSP) or microcontrollers. The Brain Computer Interface developed in this Doctoral Thesis was tested and validated off–line, with an external database, and with data from volunteers, presenting satisfactory results in both cases, according to similar results
from the literature.

Acceso al documento