论文部分内容阅读
综述了独立分量分析(ICA)的基本原理及基于信息最大化原理的各种方法及其特性,介绍了HJ网络、基于信息最大化的Infomax法及其扩展算法、极大似然估计(MLE)法、负熵最大化法、基于高阶累量的ICA法和Bussage法,对各种方法性能做了比较,说明了ICA在生物医学信号处理中的应用,并对ICA的发展作了展望。
This paper summarizes the basic principles of Independent Component Analysis (ICA) and various methods and their characteristics based on the principle of information maximization. The HJ network, Infomax method based on maximization of information and its extended algorithm, maximum likelihood estimation (MLE) Method, maximization of negative entropy, ICA method based on higher-order cumulant, and Bussage method are used to compare the performance of various methods. The application of ICA in biomedical signal processing is described and the development of ICA is prospected.