Study on Segmented Correlation in EEG Based on Principal Component Analysis

在线阅读 下载PDF 导出详情
摘要 InordertoexplorethecorrelationbetweentheadjacentsegmentsofalongtermEEG,animprovedprincipalcomponentanalysis(PCA)methodbasedonmutualinformationalgorithmisproposed.Aone-dimensionEEGtimeseriesisdividedequallyintomanysegments,sothateachsegmentcanberegardedasanindependentvariablesandmulti-segmentedEEGcanbeexpressedasadatamatrix.Then,wesubstitutemutualinformationmatrixforcovariancematrixinPCAandconducttherelevanceanalysisofsegmentedEEG.Theexperimentalresultsshowthatthecontributionrateoffirstprincipalcomponent(FPC)ofsegmentedEEGismorelargerthanothers,whichcaneffectivelyreflectthedifferenceofepilepticEEGandnormalEEGwiththechangeofsegmentnumber.Inaddition,theevolutionofFPCconducetoidentifythetime-segmentlocationsofabnormaldynamicprocessesofbrainactivities,theseconclusionsarehelpfulfortheclinicalanalysisofEEG.
机构地区 不详
出版日期 2013年03月13日(中国期刊网平台首次上网日期,不代表论文的发表时间)
  • 相关文献