• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2010, Vol. 32 ›› Issue (7): 137-139.doi: 10.3969/j.issn.1007130X.2010.

• 论文 • 上一篇    下一篇

基于虚拟通道的ICA的PVEP提取方法的研究

刘钦团1,邱飞岳1,2,李浩君2   

  1. (1. 浙江工业大学信息工程学院,浙江 杭州310032;2. 浙江工业大学教科学院,浙江 杭州310012)
  • 收稿日期:2009-01-03 修回日期:2009-04-09 出版日期:2010-06-25 发布日期:2010-06-25
  • 通讯作者: 刘钦团 E-mail:lqt83@126.com
  • 作者简介:刘钦团(1983),男,浙江金华人,硕士生,研究方向为微弱信号提取和图像处理;邱飞岳,教授,研究方向为数字技术与仪器、微弱信号提取、图像处理;李浩君,讲师,研究方向为微弱信号提取和图像处理。
  • 基金资助:

    浙江省科技计划资助项目(2006C31001)

A Method of the Estimation of Pattern Visual Evoked Potential (PVEP)Based on the ICA of Virtual Channels

LIU Qintuan1,QIU Feiyue1,2,LI Haojun2   

  1. (1.School of Information Engineering,Zhejiang University of Technology,Hangzhou 310032;
    2.Department of Educational Technology,Zhejiang University of Technology,Hangzhou 310012,China)
  • Received:2009-01-03 Revised:2009-04-09 Online:2010-06-25 Published:2010-06-25
  • Contact: LIU Qintuan E-mail:lqt83@126.com

摘要:

本文介绍了独立分量分析算法(ICA)的原理、算法及其特点。采用ICA算法进行PVEP的提取,考虑到仪器实际应用中单通道VEP信号的提取,本文通过引入虚拟通道,构造虚拟多通道,克服了ICA无法直接对单路信号进行独立分量分析的难题,实现PVEP单通道单次的有效提取。经与目前临床通用的相干平均法比较,只需单通道、单次,在波形整体和P100潜伏期的提取上,效果显著,获得医师欢迎,很有进一步开发潜力。

关键词: ICA, PVEP, 虚拟通道, 单次提取

Abstract:

The principle and algorithms of independent component analysis(ICA) is illustrated. The paper introduces virtual channels and  the virtual structure of multichannel, to complete a singletrial estimation of singlechannel pattern PVEP, which overcomes the problem of using ICA directly to singlechannel signals. Compared with the average technology, its encouraging results are illustrated by both computer simulation and clinical data applications. The number of trials needed is reduced to one. By analyzing the time course and spatial pattern of the independent components, a certain component is  found to be closely related with the P100 latent period in the VEP complex.

Key words: ICA;PVEP;virtual channel;singletrial estimation