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.