Electroencephalogram Pathology Detection Using Deep Learning

Abstract

Electroencephalologram or commonly known as the EEG scan is a test that is done on the brain. It is a readily available test providing proof how the brain functions over time. The EEG test is used to find disorders on the brain. It finds the type of disorder along with the location during seizure. Pathologies can affect brain signals so this paper combines the power of deep learning along with brain signals to detect the pathology. In this paper I propose an automated EEG analysis method by combining digital signal processing and neural network techniques, which will remove error and subjectivity, associated with manual analysis and identifies the existence of epilepsy seizure and brain tumor diseases. In this proposed system the raw EEG signals are processed into a spatio-temporal representation and this representation is fed into a convolutional neural network (CNN).