资源描述:
《基于事件相关电位的测谎方法研究_本科毕业论》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库。
1、题目:基于事件相关电位的测谎方法研究学院信息科学与工程学院专业自动化年级2010级学号姓名指导老师2014年5月摘要本研究主要利用P300电位作为辨别测谎的重要指标。P300测谎与任务相关性、刺激性质、注意、记忆、电生理干扰等影响因素有关。利用P300测谎的目的是对单一个体进行其是否在说谎的判断,本课题研究主要关注单个被试内的探测刺激和无关刺激的P300是否存在显著差异。本文采用个人相关信息为刺激内容,以被试真实的相关信息作为目标刺激,例如被试的存钱银行名称等,设计实验范式,将实验采集到的脑电信号作为主要研究对象。
2、P300电位的数据处理分为三步:预处理,特征提取和分类。将采集到的数据通过汉明窗低通滤波器滤波,选择导联和时间窗进行降维,然后利用Fisher线性判别进行分类识别。对分类结果进行分析得出:正确率与训练量的多少、刺激重复次数、导联选取个数均有关系。关键词:事件相关电位,P300电位,Fisher线性判别ABSTRACTThisresearchmainlyusestheP300potentialasanimportantindextodistinguishthepolygraph.Therelevantfactorso
3、fP300polygraphandtaskdependencies,stimulatingproperties,attention,memory,electrophysiologicaldisturbance.UsingP300lietothesingleindividualislyingjudgment,thisresearchmainlyfocusonthedetectionofsinglesubjectsandtndifferentstimuliP300whethertherearesignificantdi
4、fferences.Thispaperusespersonalinformationrelatedtostimulatethecontent,relatedtotheinformationistrueastargetstimuli,suchasthebankname,designexperimentalparadigm,theEEGsignalisacquiredfromexperimentsasthemainobjectofstudy.DataprocessingofP300potentialisdividedi
5、ntothreesteps:preprocessing,featureextractionandclassification.ThedatawillbecollectedbytheHammingwindowlow-passfilter,selectleadandtimewindowtoreducethedimension,andthenusetheFisherlinearclassificationdiscrimination.Theclassificationresultsareobtained:thecorre
6、ctrateandamountoftraining,stimulusrepetition,leadthechosennumberof.Keywords:eventrelatedpotential,P300,Fisherlineardiscriminant目录第一章绪论·····················································11.1引言·······························································11.2
7、国内外ERP测谎的研究发展概况·······································11.3本文的研究内容·····················································2第二章ERP用于测谎的原理和实验范式设计··························32.1事件相关电位的概述·················································32.2P300信号介绍·····················
8、··································32.3P300测谎的影响因素················································42.4实验设计···························································52.4.1被试介绍······