Hierarchy Graph Convolution Network and Tree Classification for Epileptic Detection on Electroencephalography Signals

The epileptic detection with electroencephalography (EEG) has been deeply studied and developed. However, previous research gave little attention to the physical appearance and early onset warnings of seizure. When a seizure occurs, electrodes near the epileptic foci will exhibit significantly fluctuating and inconsistent voltages. In this article, a novel approach to epileptic detection based on the hierarchy graph convolution network (HGCN) structure is proposed. Multiple features of time or frequency domains extracted from the raw EEG signals are taken as the input of HGCN. The topological relationship between every single electrode is utilized by HGCN. The tree classification (TC) and preictal fuzzification (PF) are proposed to adapt both multiclassification tasks and refine-classification tasks. Experiments are performed on the CHB-MIT and TUH data sets. Compared with the state of the art, our proposed model achieves a 5.77% improvement of accuracy on the CHB-MIT data set, and an improvement of 2.43% and 19.7% for sensitivity and specificity on the TUH data set, respectively.