摘要
介绍了独立分量分析(ICA)的基本原理.针对事件相关电位(ERP)的信号特点及对快速处理的要求,引入一种快速定点ICA算法,并编写了相应的程序.利用该程序,进行了ERP实测数据的处理实验.实验显示,快速ICA算法能有效地分离和消除噪声干扰,并能改善和增强单次ERP的信号特征.文中还就实验结果和独立分量分析在ERP处理中的应用进行了讨论.
Based on the brief description of the basic fundamentals of independent component analysis (ICA), a fast fixedpoint algorithm for ICA used for noise removal of eventrelated potentials (ERP) and its signal feature improvement are presented according to ERP's character and its need of fast processing. The fast ICA and its usage in ERP signal processing are introduced and the corresponding program is given. Using the program the ERP signal processing is actualized. The results show that the ICA algorithm can effectively separate and remove artifacts, and improve the singletrial ERP signal features. At last, it conducts a discussion about the result and using of ICA in ERP.
出处
《武汉理工大学学报(交通科学与工程版)》
北大核心
2003年第4期540-543,共4页
Journal of Wuhan University of Technology(Transportation Science & Engineering)
基金
国家民委重点科研基金资助项目 (批准号 :MZZ0 1 0 0 3 )
中南民族大学自然基金资助 (批准号 :YZY0 2 0 1 2)
关键词
独立分量分析
事件相关电位
伪迹
信号特征
independent component analysis(ICA)
event-related potentials(ERP)
artifacts
signal feature