Detection of Epilepsy Using Wavelet Coherence and Convolutional Neural Networks

• Published in: 2021 Medical Technologies Congress (TIPTEKNO) pp. 1 - 4
• Main Authors: Bozdogan, Ayse, Ustu, Mehmet, Ileri, Ramis, Latifoglu, Fatma
• Format: Conference Proceeding
• Language: English; Turkish
• Published: IEEE 04-11-2021
• Subjects: Coherence; Convolutional Neural Network; Convolutional neural networks; Electroencephalography; Epilepsy; Neural networks; Organizations; Wavelet analysis; Wavelet Coherence Analysis
• DOI: 10.1109/TIPTEKNO53239.2021.9632964
• EISSN: 2687-7783

According to the World Health Organization, epilepsy is a disease that affects approximately 50 million people worldwide. Due to the unexpected onset of epileptic seizures, it can lead to bodily injury and death. For this reason, it is very important to predict epilepsy. In this study, it was aimed to detect epilepsy by using Electroencephalogram (EEG) signals recorded from Bonn Epilepsy Laboratory. Wavelet Coherence Analysis and Convolutional Neural Networks were used for this aim. Classification results show that accuracy of different clusters in the data set using the proposed method were obtained as 96% for N-S clusters, 96.5% for F-S clusters, 99% for Z-S clusters and 100% for O-S clusters.The results show that the proposed method is promising in estimating epilepsy from EEG signals.