Epilepsy detection system based on linear graph convolutional neural network

• Main Authors: ZHANG GAOBO, CHU DENGYU, DONG CHANGXU, ZHENG YUANJIE, XUE MINGRUI, HE JIATONG, ZHAO YANNA
• Format: Patent
• Language: Chinese; English
• Published: 02.02.2021
• Subjects: DIAGNOSIS; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; SURGERY

The invention discloses an epilepsy detection system based on a linear graph convolutional neural network. The system comprises an obtaining module which is configured to obtain a to-be-detected multichannel electroencephalogram signal, a preprocessing module which is configured to preprocess the to-be-detected multi-channel electroencephalogram signal, take the signal of each channel as a node, decide whether a connection edge exists between the corresponding nodes according to whether the correlation degree exists between the channel signals to obtain a graph structure, and obtain a corresponding adjacent matrix according to the graph structure, and a detection module which is configured to input the electroencephalogram signals of all the channels and the adjacency matrix into a pre-trained linear graph convolutional neural network, and output an epilepsy diagnosis result of the to-be-detected multichannel electroencephalogram signals. 本申请公开了基于线性图卷积神经网络的癫痫检测系统，包括：获取模块，其被配置为：获取待检测的多通道脑电信号；预处理模块，其被配置为：对待检测的多