DOI
https://doi.org/10.25772/8ND6-BB58
Author ORCID Identifier
https://orcid.org/0000-0002-1215-8118
Defense Date
2023
Document Type
Thesis
Degree Name
Master of Science
Department
Biomedical Engineering
First Advisor
Dr. Dean Krusienski
Second Advisor
Dr. Cheng Ly
Third Advisor
Dr. Paul Wetzel
Abstract
The human visual system serves as the basis for many modern computer vision and machine learning approaches. While detailed biophysical models of certain aspects of the visual system exist, little work has been done to develop an end-to-end model from the visual stimulus to the signals generated at the visual cortex measured via the scalp electroencephalogram (EEG). The creation of such a model would not only provide a better understanding of the visual processing pathways but would also facilitate the design and evaluation of more robust visual stimuli for brain-computer interfaces (BCIs). A novel experiment was designed and conducted where 15 participants viewed stereotyped visual stimuli while their EEG was recorded simultaneously. The resulting EEG responses were characterized across participants. Furthermore, a Residual Connection Feed Forward system identification Neural Network (ReCon FFNN) was implemented as a preliminary end-to-end model of the visual system that uses the temporal characteristics of the visual stimulus as the model input and the corresponding EEG time series as the model output. This preliminary model was able to reproduce temporal and spectral characteristics of the EEG and serves as a proof of concept for the development of future artificial neural network or biophysical models that incorporate spatio-temporal information.
Rights
© The Author
Is Part Of
VCU University Archives
Is Part Of
VCU Theses and Dissertations
Date of Submission
12-13-2023