Epilepsy Electroencephalogram Signal Analysis Based on Improved k-nearest Neighbor Network
Yu, X.; Liu, C.; Dai, J.; Li, J.; Wang, J.; Hou, F.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi 33(6): 1039-1045
2016
ISSN/ISBN: 1001-5515 PMID: 29714965 Document Number: 688080
The study of complex networks has become a hot research area of electroencephalogram signal.Electroencephalogram time series generated by the network keeps node information of network,so studying the time series from the network can also achieve the purpose of study epileptic electroencephalogram.In this paper,we propose a method to analyze epileptic electroencephalogram based on time series which is based on improved k-nearest neighbor network.The results of the experiment showed that studying power spectrum of time series from network was easier than power spectrum of time series directly generated from the original brain data to distinguish between normal controls and epileptic patients.In addition,studying the clustering coefficient of improved k-nearest neighbor network was able to distinguish between normal persons and patients with epilepsy.This study can provide important reference for the study of epilepsy and clinical diagnosis.