基于改进的k-最近邻网络的癫痫脑电信号分析  

Epilepsy Electroencephalogram Signal Analysis Based on Improved k-nearest Neighbor Network

作　　者：余娴[1] 刘程程[1] 戴加飞[2] 李锦[3] 王俊[1] 侯凤贞[4] 

机构地区：[1]南京邮电大学图像处理与图像通信江苏省重点实验室,南京210003 [2]南京军区南京总医院,南京210002 [3]陕西师范大学物理学与信息技术学院,西安710062 [4]中国药科大学理学院,南京210009

出　　处：《生物医学工程学杂志》2016年第6期1039-1045,共7页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(61271082;61401518;31671006);江苏省重点研发计划资助项目(BE2015700;BE2016773);江苏省自然科学基金资助项目(BK20141432);江苏省高校自然科学研究重大项目(16KJA310002);南京军区南京总医院基金资助项目(2014019);南京市医疗卫生科技计划资助项目(201503009);中国药科大学中央高校基本科研业务费专项资金资助项目(FY2014LX0039)

摘　　要：当前复杂网络的研究已经成为脑电信号研究的热点。因为脑电网络产生的时间序列保存了网络结点信息,因此研究网络产生的时间序列同样能够达到研究癫痫脑电信号的目的。基于此,本文提出了一种基于改进的k-最近邻网络产生时间序列来分析癫痫脑电信号的方法。研究结果表明,研究网络产生的时间序列的功率谱比直接研究原始癫痫脑电信号的功率谱更容易区分正常人和癫痫患者。此外,研究改进的k-最近邻网络的聚类系数也能区分正常人和癫痫患者。通过本文研究结果,期望能够为癫痫研究及其今后的临床诊断提供相关参考依据。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.

关 键 词：改进的 k-最近邻网络 时间序列 癫痫 脑电信号分析 

分 类 号：R742.1[医药卫生—神经病学与精神病学] R741.044[医药卫生—临床医学]