EEG dataset classification using CNN method
W-L Mao, Haris Imam Karim Fathurrahman, Yu-Hsu Lee, Teng-Wen Chang
Abstract
Abstract This paper proposes a simple Convolutional Neural Network (CNN) program to classify epileptic seizure. The diagnosis of epileptic seizure involves the identification and different characteristic of the Electroencephalography (EEG) signal. As such, it needs a method for identifying and classifying epileptic seizure. Deep learning is part of a neural network that has the ability and pattern to identify and classify epileptic seizure. CNN has been demonstrated high performance on image classification and pattern detection. In this paper, we combine the continuous wavelet transform (CWT) and CNN to classify epileptic seizure. This experiment uses the wavelet transform to convert signal data of EEG to time-frequency domain images. The output of the wavelet transform is an image that will classify into five attributes. In this experiment, we develop a simple program that will compare with other CNN approach (AlexNet and GoogleNet). The results of this experiment are two kinds of data, accuracy, and loss. The resulting accuracy is 72.49%, and the loss is 0.576. This result has a better learning time than GoogleNet and smaller loss result than AlexNet.