预览加载中，请您耐心等待几秒...

基于EMD与非相干解调算法的FSK-SSVEP系统（英文）.docx

预览
1/2
2/2

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

基于EMD与非相干解调算法的FSK-SSVEP系统（英文） Title:FSK-SSVEPSystembasedonEMDandIncoherentDemodulationAlgorithm Abstract: Inrecentyears,steady-statevisuallyevokedpotential(SSVEP)-basedbrain-computerinterfaces(BCIs)havegainedsignificantattentionduetotheirpotentialapplicationsincommunicationandrehabilitation.ThispaperproposesanovelFSK-SSVEPsystemthatcombinestheempiricalmodedecomposition(EMD)techniquewiththenon-coherentdemodulationalgorithmforimprovedsignaldetectionandclassificationaccuracy.Thesystemarchitectureandsignalprocessingmethodsarediscussed,followedbyanevaluationofthesystem'sperformanceinareal-timeexperiment.TheresultsdemonstratetheeffectivenessandapplicabilityoftheproposedsysteminSSVEP-basedBCIapplications. 1.Introduction Steady-statevisuallyevokedpotentials(SSVEPs)arerhythmicresponsesgeneratedinthehumanbrainwhenexposedtovisualstimulationatspecificfrequencies.SSVEP-basedbrain-computerinterfaces(BCIs)utilizetheseresponsestoallowindividualstocontrolexternaldevicesorcommunicatethroughtheirbrainsignals.Frequency-shiftkeying(FSK)modulationisacommonlyusedtechniquetoencodemultipletargetsinSSVEPsystems.ThispaperpresentsanewFSK-SSVEPsystemthatleveragestheempiricalmodedecomposition(EMD)techniqueandnon-coherentdemodulationalgorithmforimprovedperformance. 2.SystemArchitecture TheproposedFSK-SSVEPsystemconsistsofthreemaincomponents:visualstimulation,signalacquisition,andsignalprocessing.Visualstimulationinvolvespresentingflickeringvisualstimulitotheuser,witheachtargetrepresentingadifferentfrequency.Theuser'sbrainresponsesarethencapturedusingelectroencephalography(EEG)electrodes,andtheacquiredEEGsignalsareprocessedusingtheEMDandnon-coherentdemodulationalgorithm. 3.SignalProcessingMethods TheEMDtechniquedecomposestheacquiredEEGsignalsintoasetofintrinsicmodefunctions(IMFs),whichcapturedifferentfrequencycomponentsofthesignal.EachIMFrepresentsadifferentfrequencyband,allowingforbetterseparationofSSVEPresponsesfromnoiseandartifacts.AfterEMD,thenon-coherentdemodulationalgorithmisemployedtoextrac