Neurological Status Classification Using Convolutional Neural Network

Abstract In this study we show that a Convolutional Neural Network (CNN) model is able to accurately discriminate between 4 different phases of neurological status in a non-Electroencephalogram (EEG) dataset recorded in an experiment in which subjects are exposed to physical, cognitive and emotional stress. We demonstrate that the proposed model is able to obtain 99.99% Area Under the Curve (AUC) of Receiver Operation characteristic (ROC) and 99.82% classification accuracy on the test dataset. Furthermore, for comparison, we show that our models outperforms traditional classification methods such as SVM, and RF. Finally, we show the advantage of CNN models, in comparison to other methods, in robustness to noise by 97.46% accuracy on a noisy dataset.