隐秘信息的脑电检测
EEG detection of secret information
投稿时间:2018-08-06  修订日期:2018-09-05
DOI:
中文关键词: 自我相关程度  隐秘信息  事件相关电位  小波变换
英文关键词: degree of self-correlation  secret message  event-related potential  wavelet transform
基金项目:国家自然科学基金项目(面上项目,重点项目,重大项目);中央高校基本科研业务费资助项目
作者单位E-mail
官金安 中南民族大学 guanja@tom.com 
段亚峰 中南民族大学  
徐世行 中南民族大学  
李东阁 中南民族大学  
印想 中南民族大学  
彭翰林 中南民族大学  
潘先攀 中南民族大学  
摘要点击次数: 421
全文下载次数: 
中文摘要:
      刑侦中经常需要揭示疑犯隐藏的真实信息,而隐秘信息的脑电检测,将有可能实现这些想法。我们设计了一个猜测受试者真实名字的实验,在探究个体对不同自我相关程度名字刺激的脑电实验中,刺激出现后的300-600ms内,自己的名字诱发的正波幅值大于陌生名字刺激。通过小波变换提取特征,并用支持向量机进行训练和分类。在进行5个试次叠加平均后,采用PO3通道可将自己的名字分类成功,5位被试平均正确率达98%。说明了本研究可应用于个体隐秘信息的脑电检测。
英文摘要:
      In criminal investigation, it is often necessary to reveal the true information hidden by suspects, and EEG detection of hidden intention will make these ideas possible. We designed an experiment to guess the real names of the subjects, in the EEG experiment of exploring the individual stimulation of different self-correlation degrees, the amplitude of positive wave induced by one's own name was larger than the strange name in the 300-600ms after the stimulation. The feature is extracted by wavelet transform and trained and classified by support vector machine. After 5 times of superposition averaging, the average accuracy of 5 subjects can be reached 98% by PO3 channel. The results show that this study can be applied to the EEG detection of individual secret message.
View Fulltext   查看/发表评论  下载PDF阅读器
关闭