Description:

Description: The open-source C-package fastICA implements the fastICA algorithm of Aapo Hyvarinen et al. <URL: http://www.cs.helsinki.fi/u/ahyvarin/> to perform Independent Component Analysis (ICA) and Projection Pursuit. fastICA is released under the GNU Public License (GPL).

Project homepage: http://www.public.iastate.edu/~maitra/Software/fastICA.html

Dependencies: gcc compiler, glibc library, Rmath library

Installation: fastICA can be installed in two easy steps:

• extract files from "fastICA.tar.bz2":

• compile files running the makefile:

• make

To check the integrity of the package, run the command:

make check

To remove the installed files, use the command:

make clean

Usage: $./run_fastICA -n <int> -p <int> -# <int> -a -s -O <dir> -i <file> -v -h

OPTIONS

run_fastICA has the following options:

-n <int>   number of observations
-p <int>   number of dimensions
-# <int>   desired number of independent components
-a <real>  alpha constant in (1, 2) for logcosh  neg-entropy (default: 1.0)
-s         if symmetric fastICA should be performed (default: deflation)
-O <dir>   working directory for results (default: OUTPUT)
-i <file>  file with the n (row) observations of p (column) attributes
-v         verbose output, (default: no verbosity)

EXAMPLE:

./run_fastICA -n326900 -p3 -#3 -a1.25 -s -iTEST/karbagan.dat

Go to TEST/README.R for information on how to validate results.

References:

 A. Hyvarinen and E. Oja (2000) Independent Component Analysis:
 Algorithms and Applications, _Neural Networks_, *13(4-5)*:411-430

Changes to previous version:

Initial Announcement on mloss.org.

BibTeX Entry: Download

Supported Operating Systems: Agnostic

Data Formats: Txt

Tags: Independent Component Analysis

Archive: download here

Comments

No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.