首页 | 本学科首页   官方微博 | 高级检索  
     

基于瞬态视觉诱发电位的识别算法研究
引用本文:吴海静,何庆华,田逢春. 基于瞬态视觉诱发电位的识别算法研究[J]. 传感器与微系统, 2012, 31(4): 47-49
作者姓名:吴海静  何庆华  田逢春
作者单位:1. 重庆大学通信工程学院,重庆,400044
2. 第三军医大学大坪医院野战外科研究所创伤、烧伤与复合伤国家重点实验室,重庆,400042
基金项目:重庆市科技攻关计划资助项目(CSTC,2009AC5023)
摘    要:基于瞬态视觉诱发电位的研究是脑机接口研究中的一种方法,其核心在于瞬态视觉诱发电位的识别算法研究。采用累加平均和小波分解滤波从强噪声背景下提取微弱的视觉诱发电位,采用主成分分析提取诱发电位的特征,用K近邻算法对得到的特征信号进行模式识别。采集三名受试者的脑电数据作为处理对象,识别准确率可以达到95%。实验结果表明:该方法可以比较准确地识别瞬态视觉诱发电位。

关 键 词:瞬态视觉诱发电位  小波变换  主成分分析  K近邻算法

Study of recognition algorithm based on transient visual evoked potential
WU Hai-jing , HE Qing-hua , TIAN Feng-chun. Study of recognition algorithm based on transient visual evoked potential[J]. Transducer and Microsystem Technology, 2012, 31(4): 47-49
Authors:WU Hai-jing    HE Qing-hua    TIAN Feng-chun
Affiliation:1(1.School of Communication Engineering,Chongqing University,Chongqing 400044,China; 2.State Key Laboratory of Trauma,Burns and Combined Injury,Daping Hospital,Surgery Institute of the Third Military Medical University,Chongqing 400042,China)
Abstract:The study based on transient visual evoked potentials is a kind of way to study brain-computer interface,and the key is the study on recognition algorithm of transient visual evoked potential.The accumulation averaging and wavelet filter method are used to extract VEP signal from the background full of noise.PCA are used to extract the feature of VEP signal.KNN is used to recognize the feature signal.The correct recognition rate reaches 95 % when EEG come from three people.The experimental results show that the method can recognize transient visual evoked potentials more correctly.
Keywords:transient visual evoked potential(TSVEP)  wavelet transform  principal component analysis(PCA)  K-nearest neighbor(KNN)algorithm
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号