bachelorThesis
Detección y reconocimiento de guiños basado en análisis EEG utilizando redes neuronales
Registro en:
Tesis (Ingeniero Electrónico), Universidad San Francisco de Quito, Colegio de Ciencias e Ingenierías; Quito, Ecuador, 2015
Autor
Silva Guerrero, Adrián Santiago
Toscano Andrade, Sebastián Israel
Institución
Resumen
This paper proposes an automatic eyewink interpretation system based on EEG signal analysis for human-machine interface to benefit people with disabilities. Our system investigates the use of the Emotiv EPOC as a relatively low cost new method for acquiring EEG signals and the implementation of Artificial Neural Networks (ANN) for the classification algorithm. The proposed algorithm has been found effective in detecting and classifying the eyewinks that then can be translated to valid command for human-machine interface. The performance of the proposed approach is investigated using two types of ANN topologies, and the results obtained indicate a high rate of classification accuracy.