Graph Signal Processing of EEG signals for Detection of Epilepsy
Priyanka Mathur, Vijay Kumar Chakka
Abstract
Epileptic Seizure is a chronic nervous system disorder which is analyzed using Electroencephalogram (EEG) signals. This paper proposes a Graph Signal Processing technique called Graph Discrete Fourier Transform (GDFT) for the detection of epilepsy. EEG data points are projected on the Eigen space of Laplacian matrix of graph to produce GDFT coefficients. The Laplacian matrix is generated from weighted visibility graph constructed from EEG signals. It proposes Gaussian kernel based edge weights between the nodes. The proposed GDFT based feature vectors are then used to detect the seizure class from the given EEG signal using a crisp rule based classification. Simulation results show that the proposed GDFT based features from Gaussian Weighted Visibility Graph (VG) can detect epileptic seizure with 100 % accuracy.