Epileptic seizure detection using EEG

• Main Author: Ye, Ruofan
• Other Authors: Rajapakse Jagath Chandana
• Format: Final Year Project
• Language: English
• Published: 2017
• Subjects: DRNTU::Engineering::Computer science and engineering
• Online Access: http://hdl.handle.net/10356/70408
• Institution: Nanyang Technological University

Seizures occur at unpredictable times and is usually without warnings. Seizures can be dangerous and potentially life-threatening if left without assistance and treatments. This poses a challenge for medical personnel as immediate assistance is required should a patient suffers from a seizure. This project aims to develop an algorithm to allow detection of epileptic seizures of a patient through the use of electroencephalogram (EEG) signal. This algorithm will determine if the input EEG data is epileptic or not. This algorithm consists of two processes: feature extraction and classification. For this purpose, power spectral density is used to extract features of the EEG signals. Classification is done by using a Support Vector Machine (SVM). With a working algorithm in detection of seizure, future implementation of such detection methods could be used in real-life situations where an alarm could be triggered to notify the medical personnel of a seizure of patient so that immediate response could be activated.