Epileptic EEG Signal Classification Using Convolutional Neural Network Based on Multi-Segment of EEG Signal

High performance in the epileptic electroencephalogram (EEG) signal classification is an important step diagnosing epilepsy. Furthermore, this carried out to determine whether EEG from a person's examination results categorized as or not (healthy). Several automated techniques have been proposed assist neurologists classifying these signals. In general, yielded high average accuracy classification, but still needs be improved. Therefore, we propose convolutional neural network based on multi-segment of signals classify This method built overcome data limitations training process and add ensemble combination process. The formed by splitting without overlapping each channel converting it into spectrogram image short-time Fourier transform value. then used input for in-depth testing. model segment test before entering stage final classification. To evaluate our method, Bonn dataset. dataset consists five records labelled A, B, C, D, E. experiments several datasets (AB-C, AB-D, AB-E, AB-CD, AB-CDE, AB-CD-E) which were arranged showed that (with segment) performs better than segment. Our best 99.33%, 100%, 99.5%, 99.8%, 99.4% AB-C, AB-CD-E.By results, can outperform other methods same