ICA在视觉诱发电位的少次提取与波形分析中的应用

ICA IN THE SINGLE-TRIAL ESTIMATION AND ANALYSIS OF VEP

本文提出一种基于扩展的独立分量分析 (ICA)算法的视觉诱发响应少次提取方法。经与目前临床通用的相干平均法比较 ,只经三次平均 ,在波形整体和P10 0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。

A novel method based on the Extended Infomax of ICA (Independent Component Analysis) was proposed for single-trial estimation of multichannel Visually Evoked Potential (VEP). Its encouraging results were illustrated by both computer simulation and clinical data application. The number of trials needed was reduced to three, but the result was clearer than that obtained by 50 times conventional coherent averaging. By analyzing the time course and spatial pattern of the independent components, a certain component was found to be closely related with the P100 peak in the VEP complex.