摘要
诱发电位(ＥＰ)信号在检测神经系统状态时有重要意义．但ＥＰ信号总是淹没在自发脑电波(ＥＥＧ)信号中,因此,为利用ＥＰ信号诊断神经系统的损伤和病变,需要从二者的混合信号中提取出ＥＰ信号．独立分量分析(ＩＣＡ)是一种新近发展起来的信号分离方法．本文把ＩＣＡ方法应用于ＥＰ信号的提取,并与传统的滤波方法进行了比较．计算机模拟表明,采用ＩＣＡ方法进行噪声分离的结果明显优于信号滤波方法．
The waveform of Evoked Potential (EP) signals is remarkably important for evaluating the status of neural system. Removing or suppressing the noises in EPs is necessary for clinical applications, since they are always contaminated with ongoing electroencephalogram (EEC) and other noises. Independent Component Analysis (ICA) is a new way for signal separation. It is used to recover EP signals from EEG noises in this study. A comparison with a traditional filtering technology is also conducted. Computer simulation results show that the ICA based method is much better than the filtering technology in signal and noise separation.
出处
《大连铁道学院学报》
2002年第2期62-65,共4页
Journal of Dalian Railway Institute
基金
国家自然科学基金资助项目(30170259)
辽宁省科学技术基金资助项目(2001101057)
