Date of Award
January 2014
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Electrical Engineering
First Advisor
Reza Fazel-Rezai
Abstract
The goal of this research was to evaluate and compare two types of brain computer interface (BCI) systems, P300 and steady state visually evoked potentials (SSVEP), as spelling paradigms and combine them as a hybrid approach. There were pilot experiments performed for designing the parameters of the SSVEP spelling paradigm including peak detection for different range of frequencies, placement of LEDs, design of the SSVEP stimulus board, and window time for the SSVEP peak detection processing. The next experiment was to evaluate the SSVEP spelling paradigm. Six subjects participated in the task. The accuracy of each frequency and average accuracy for each subject were considered. The second experiment was designed to compare the performance and accuracy of SSVEP, P300, and the combination of both paradigms as a simultaneous task. Ten subjects were considered for performing this experiment. Overall the average accuracy of the SSVEP spelling paradigm was 80.00 % and higher than the P300 spelling paradigm average accuracy which was 72.50 %, and both of the spelling paradigms have better accuracy than the hybrid paradigm with the average accuracy of 64.39 %.
Recommended Citation
Amiri, Setare, "P300, Steady State Visual Evoked Potentials, And Hybrid Paradigms For A Brain Computer Interface Speller" (2014). Theses and Dissertations. 1614.
https://commons.und.edu/theses/1614