Adopting Artificial Intelligence Powered ConvNet To Detect Epileptic Seizures

Neural networks and deep learning has gained much attention in the recent years in the medical field. Recent improvements in deep learning has led to computer-aided analysis of medical data, thereby contributing to automated disease diagnosis and detection. Seizures, commonly referred to as epilepsy, is normally detected by neurologists using the traditional approach of visual inspection of EEG waveforms that contain information about the electrical activity of the brain. However, since this is a laborious and time-consuming process, automated and accurate identification of epileptic seizures can improve efficiency and patient's quality of life. In this study, One-dimensional Convolutional Neural network (1D CNN) is used for automated detection of epileptic seizures based on the electroencephalogram (EEG) signal data. Our main objective in this work is to represent a methodology for automatic seizure detection through a 1D CNN model. The proposed model is a binary classification model that can detect whether a person is healthy or epileptic with an accuracy of 99 percent.