Automatic Epileptic Seizure Prediction Based on Convolutional Neural Network and EEG Signal
Abstract
G. Alizadeh, T. Yousefi Rezaii and S. Meshgini
Epilepsy is a neurological disorder that affects approximately 1% of the world's population. To diagnose and estimate the occurrence of epilepsy, neurologists analyze recorded brain activity. However, this process is not only time-consuming and tedious but also susceptible to occasional human error. Therefore, researchers have aimed to develop an automated method for diagnosing and estimating the occurrence of epilepsy in recent decades. In this study, we propose two new methods based on brain signals and a convolutional neural network (CNN). Our approach utilizes a sequential three- layer structure in the CNN. We conducted numerous experiments, and the proposed methods achieved an accuracy of 95% without feedback and 97% with feedback for estimating epilepsy. Our proposed methods outperform previous methods and have the potential to be employed as a physician's assistant in the field of operation.