资源简介
独立成分分析:比FastICA可能更好的一种算法RobustICA
代码片段和文件信息
% RobustICA algorithm for independent component analysis (Release 1 - March 31 2008)
% -----------------------------------------------------------------------------------
%
% RobustICA is based on the normalized kurtosis contrast function which is optimized by a
% computationally efficient gradient-descent technique. This technique computes algebraically
% the step size (adaption coefficient) globally optimizing the contrast in the search direction
% at each iteration. Any independent component with non-zero kurtosis can be extracted in this
% manner.
%
% The present implementation performs the deflationary separation of statistically independent
% sources under the instantaneous linear mixture model. Full separation is achieved if at most
% one source has zero kurtosis.
%
% Some advantages of RobustICA are:
%
% - The optimal step-size technique provides some robustness to the presence of saddle points and
% spurious local extrema in the contrast function.
%
% - The method shows a very high convergence speed measured in terms of source extraction quality
% versus number of operations.
%
% - Real- and complex-valued signals are treated by exactly the same algorithm. Both type of source
% signals can be present simultaneously in a given mixture. Complex sources need not be circular.
% The mixing matrix coefficients may be real or complex regardless of the source type.
%
% - Sequential extraction (deflation) can be performed via linear regression. As a result prewhitening
% and the performance limitations it imposes can be avoided. This feature may prove especially
% beneficial in ill-conditioned scenarios the convolutive case and underdetermined mixtures.
%
% - Optionally the algorithm can target sub-Gaussian or super-Gaussian sources in the order defined
% by a kurtosis-sign vector provided by the user.
%
%
% The package is composed of the following M-files:
%
% - ‘robustica.m‘: implements the algorithm itself.
%
% - ‘kurt_gradient_optstep.m‘: computes the optimal step-size of the normalized kurtosis contrast
% using the gradient vector as search direction.
%
% - ‘deflation_regression.m‘: performs deflation via linear regression.
%
% - ‘robustica_demo.m‘: a simple demonstration illustrating the performance of RobustICA
% on synthetic mixtures.
%
%
% More details about the RobustICA algorithm can be found in the references below:
%
% - V. Zarzoso and P. Comon “Comparative Speed Analysis of FastICA“
% in: Proceedings ICA-2007 7th International Conference on Independent Component Analysis
% and Signal Separation London UK September 9-12 200
属性 大小 日期 时间 名称
----------- --------- ---------- ----- ----
文件 6909 2008-03-29 10:47 robustica_demo.m
文件 3944 2008-03-31 14:46 contents.m
文件 1827 2008-03-31 12:42 deflation_regression.m
文件 5738 2008-03-31 12:51 kurt_gradient_optstep.m
文件 8748 2008-03-31 12:48 robustica.m
相关资源
- Statistical Digital Signal Processing and Mode
- HICA -iot V1.0培训教材.pdf
- 有限元 Numerical solution of partial differ
- MIMO Wireless Communications 中文版Claude O
- navicat111_premium_cs_x86简体中文版-附破解
- Navicat+10.0.9+Premium中文版+注册机
- ProtocolsforAuthenticationandKeyEstablishment.
- numerical analysis 2nd edition solution
- 统计学习导论-基于R应用书+思维导图
- PatternClassification2ndEdition.pdf
- Rudin.-.Principles.of.Mathematical.Analysis 3e
- Pattern Classification by Richard O. Duda Davi
- The Elements of Statistical Learning 2nd 带书签
- [Jean_Meeus]_Astronomical_algorithms(2nd).
- Numerical Methods for the Solution of Ill-Pose
- Data Reduction and Error Analysis for the Phys
- OFDM for Underwater Acoustic Communications
- 《Practical Linux Security Cookbook 》 《li
- Adaptive Filtering: Algorithms and Practical I
- ComputerVision(AlgorithmsandApplications)R
- Multiphoton lithography : techniques materials
- An Elementary Introduction to the Wolfram Lang
- Digital Integrated Circuit Design From VLSI Ar
- NotificationListener.zip
- Numerical Analysis - 9th - (Burden & Faires)
- Mathematical analysis of random noise随机噪声
- Picasa管理工具
- SolidWorks Electrical完整教程
- Astronomical Algorithms Jean Meeus 天文算法英
- Mathematical Theory of Optimal Processes
评论
共有 条评论