Pattern recognition is the process of recognizing patterns and regularities in data about the category or class of the data. One application of pattern recognition is for medical diagnoses. The objective of this study is to determine if the classification of brain activity features can be improved by using a neural network to classify Electroencephalography (EEG) and Near-Infrared Spectroscopy (NIRS) data simultaneously, recorded from a subject during an Immediate Post-Concussion Assessment and Cognitive Testing (ImPACT) test to determine the viability of using both EEG and NIRS data in the diagnosis of concussions. Most current applications of this type of pattern recognition in reference to cognitive processes focus on solely EEG or NIRS. The classification of features from solely EEG data, solely NIRS data, and a combination of both EEG and NIRS data were performed by a convolutional neural network (CNN), a recurrent neural network (RNN), and a support vector machine (SVM) in order to determine which combination of features and classifier results in the highest classification accuracy. These classification methods were first tested with EEG motor imagery data to analyze their classification patterns before being tested with the dual recorded EEG and NIRS ImPACT data. Results show that the NIRS data provided a more accurate classification than either the EEG data or the combined EEG and NIRS data, but the classification of a larger variety of subjects is needed to determine if this behavior is a trend or unique to this one subject.
|Commitee:||Sheikh, Sohail, Yoon, Suk-chung|
|School Location:||United States -- Pennsylvania|
|Source:||MAI 81/11(E), Masters Abstracts International|
|Subjects:||Electrical engineering, Computer science, Neurosciences|
|Keywords:||Deep learning, EEG, Electroencephalography, Machine learning, Near-infrared spectroscopy, NIRS|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be