Epileptic EEG Signal Classification using Multi-class Convolutional Neural Network

Epileptic seizure is a common neurological syndrome wherein patients suffer from repeating seizures. It happens due to many provoking reasons namely genetic, physiologic, brain damage, etc. In this paper, time domain and frequency domain feature set are derived from EEG data and classified using Convolutional Neural Network (CNN) for detecting epileptic seizures. The benchmark EEG dataset Bonn is experimented to compare and examine the result of forthcoming methods. The proposed methodologies have been evaluated using the metrics such as sensitivity, specificity, classification accuracy and execution using two different benchmark datasets and results are compared with exiting methods. It is learned that among various methods the proposed approach using convolutional neural network with time domain features provides enhanced performance measured result. As the time domain features are computationally inexpensive to extract and also required reduced storage, so it can be used in real time automatic seizure detection and monitoring using wireless systems.