摘要
独立分量分析(independentcomponentanalysis,ICA)方法是从一组观测信号中提取统计独立分量的方法。因为用这种方法分解出的各信号分量之间是相互独立的,而测得的脑电信号往往包含若干相对独立的成分,所以用它来分解脑电信号,所得的结果更具有生理意义,有利于去除干扰和伪差。本文简要地回顾了ICA的发展历史和主要算法,综述了它在脑电信号处理中的应用及研究进展,并指出了需要进一步研究解决的问题。
Independent component analysis (ICA) is a technique which extracts statistically independent components from a set of measured signals. Since all components decomposed by ICA are mutually independent, especially the brain signals measured are usually the mixture of several relatively independent sources, the ICA decomposition of brain signals can lead to results more plausible physiologically. ICA also makes it easy to wipe off noises. A short review on the history and main algorithms of ICA is addressed, together with its development and application in brain signal processing. Problems need to be studied further are also discussed.
出处
《北京生物医学工程》
2005年第3期226-229,共4页
Beijing Biomedical Engineering
基金
国家自然科学基金 (3 0 170 2 5 9
60 172 0 72
60 3 72 0 81)
辽宁省科学技术基金 (2 0 0 110 10 5 7)资助
