Detection of Epileptic Seizures via Deep Long Short-Term Memory

The paper deals with the designing and implementation of a computer-aided system capable to detect seizures by classification of EEG records. The system is based on deep learning method using a recurrent long short-term memory neural network. The main purpose of the system is to help neurologists in detecting seizures fast and reliably. The research was carried out using real EEG recordings of epileptic patients as well as healthy subjects prepared with the cooperation of the medical staff of the Clinical Ward of Neurology of the University Hospital of Zielona Gora, Poland.