this directory
contains the following:
* The acdc algorithm for finding the
approximate general (non-orthogonal)
joint diagonalizer (in the direct Least Squares sense) of a set of Hermitian matrices.
[acdc.m]
* The acdc algorithm for finding the
same for a set of Symmetric matrices.
[acdc_sym.m](note that for Real-Valued matrices the Hermitian and Symmetric cases are similar however, in such cases the Hermitian version
[acdc.m], rather than the Symmetric version[acdc_sym] is preferable.
* A function that finds an initial guess
for acdc by applying hard-whitening
followed by Cardoso s orthogonal joint
diagonalizer. Note that acdc may also
be called without an initial guess,
in which case the initial guess is set by default to the identity matrix.
The m-file includes the joint_diag
function (by Cardoso) for performing
the orthogonal part.
[init4acdc.m]
The frequency domain plays an important role in image
processing to smooth, enhance, and detect edges of images. Although
image data typically does not include imaginary values, the fast Fourier
transform (FFT) has been used for obtaining spectra. In this paper,
the fast Hartley transform (FHT) is used to transform two-dimensional
image data. Because the Hartley transform is real valued, it does
not require complex operations. Both spectra and autocorrelations of
two-dimensional ultrasound images of normal and abnormal livers were
computed.
- XCS for Dynamic Environments
+ Continuous versions of XCS
+ Test problem: real multiplexer
+ Experiments: XCS is explored in dynamic environments with different magnitudes of change to the underlying concepts.
+Reference papers:
H.H. Dam, H.A. Abbass, C.J. Lokan, Evolutionary Online Data Mining – an Investigation in a Dynamic Environment. 2005, accepted for a book chapter in Springer Series on Studies in Computational Intelligence
H.H. Dam, H.A. Abbass, C.J. Lokan, Be Real! XCS with Continuous-Valued Inputs. IWLCS 2005, (International Workshop on Learning Classifier Systems). Washington DC, June 2005.