Signal characterisation - TR and article

[Danilo P. Mandic]

Dear Connectionists

may I draw your attention to the Technical Report entitled:

On the Characterisation of the Deterministic/Stochastic and
Linear/Nonlinear Nature of Time Series
(T. Gautama, M. M. Van Hulle and D. P. Mandic)=20

It can be downloaded from

http://www.commsp.ee.ic.ac.uk/~mandic

It combines the concept of surrogate data and signal representation in
phase space to provide an insight into the nature of a signal.
We have applied it to fMRI, HRV, and EEG signals and it works fine.

A more rigorous analysis can be found in the following Physica D
article:

Temujin Gautama, Danilo P. Mandic and Marc M. Van Hulle
' The delay vector variance method for detecting determinism and
nonlinearity in time series '
Physica D: Nonlinear Phenomena, 190 (2004) 167-176=20

which can be downloaded from:

 http://134.58.34.50/temu/physD04_preprint.pdf
or http://www.commsp.ee.ic.ac.uk/~mandic=20


The reasoning behind this analysis is that the recent progress in
biomedicine has brought to light problems where an insight into the
nature of a signal is necessary before performing the actual signal
processing. This particularly applies to the linear vs nonlinear and
deterministic vs stochastic signal properties (remember the Wold
decomposition theorem?)

The MatLab code which accompanies the articles can be downloaded from:

DVV-toolbox:
http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do?objectId=3264&objectType=file

and

Surrogates toolbox:
http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do?objectId=4612&objectType=FILE


Your comments are most welcome.

Enjoy!

Danilo

=============================
Dr Danilo Mandic
Senior Lecturer in Signal Processing
Department of Electrical and Electronic Engineering
Imperial College London
United Kingdom
Phone: +44 207 594 6271
Fax: +44 207 594 6234
E-mail: d.mandic at imperial.ac.uk
http://www.commsp.ee.ic.ac.uk/~mandic