sdica
所属分类:matlab编程
开发工具:matlab
文件大小:479KB
下载次数:67
上传日期:2013-03-20 21:20:21
上 传 者:
chjg
说明: 硕博美国留学的中科大本科毕业的研究独立分量分析的一位牛人编写的子带ica的matlab程序。研究盲源分离的必备。
(USTC graduated Shuobo study in the United States of an independent component analysis cattle were prepared subband ica matlab program. Study the blind source separation essential.)
文件列表:
ba_high.m (665, 2004-11-12)
bsica.m (10052, 2006-03-17)
estim_beta_pham.m (312, 2002-07-29)
estim_snr_high_sd.m (758, 2004-11-25)
faceimage.mat (481912, 2006-03-16)
filt_prod_high.m (285, 2004-11-12)
h_from_known_sources.m (4810, 2006-03-16)
perforindex.m (266, 2005-04-14)
scorecond.m (4421, 2002-07-11)
Note: Please install the FastICA toolbox before running the code.
The function 'bsica' is for band selective ICA [1], and the
function 'h_from_known_sources' is used to estimate h(t) from
the known source signals [2]. Please use the 'help' command
to display the help for these functions.
The file 'faceimage.mat' can be loaded in MATLAB 7.x. It
contains the dataset of the four images of human faces, and
can be used to test the algorithms. For instance, you can
use the following commands to test the behavior of band
selective ICA:
>> load faceimage
>> A_mix = rand(4,4) - .5; x = A_mix * s;
>> [yI, y, h, W] = bsica(x, 5, A_mix);
Author: Kun Zhang and Lai-Wan Chan
If you find any bugs or have any questions, please contact
Kun Zhang (kzhang@cse.cuhk.edu.hk)
References:
[1] Kun Zhang and Lai-Wan Chan, "An Adaptive Method for Subband
Decompostion ICA ", Neural Computation, 18(1), 2006,
pp. 191--223
[2] Kun Zhang and Lai-Wan Chan, "Enhancement Source Independence
in Blind Source Separation", In 6th International Conference on
Independent Component Analysis and Blind Signal Separation
(ICA 2006), LNCS 3889, Charleston, SC, USA, Mar., 2006,
pp. 731--738
[3] Kun Zhang and Lai-Wan Chan, "Blind Separation of Sources with
dependent frequency sub-components", technical report, Feb., 2006
近期下载者:
相关文件:
收藏者: