摘要
介绍了独立成分分析(ICA)的基本模型及其假设、含混性、非高斯性度量和通用求解过程。讨论了目前ICA的几个研究方向的发展现状和面临的问题,分析了ICA基本模型和几种扩展模型的求解算法,包括盲反卷积、卷积混和的盲分离、非线性瞬时混合的盲分离。提出了ICA未来理论和应用研究中的开放课题。
The standard model of Independent Component Analysis （ICA） and its assumptions, ambiguities, nongaussianity measures and general solution were introduced. Then, the state of the art and the challenge problems in ICA research field are discussed. The algorithms for standard and extended ICA models, including blind deconvolution, blind separation of convolutive mixtures, nonlinear instantaneous mixtures, are briefly analyzed. Finally, the open areas of theoretic and applied research in ICA are brought forward.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2006年第4期992-997,1001,共7页
Journal of System Simulation
基金
湖南省教育厅科研项目(05C776)
湖南城市学院科技计划项目(20057306)
关键词
独立成分分析
盲源信号分离
非高斯性
神经网络
independent component analysis
blind source separation
non-Gaussianity
neural networks
