The Wavelet Digest Homepage
Return to the homepage
Search the complete Wavelet Digest database
Help about the Wavelet Digest mailing list
About the Wavelet Digest
The Digest The Community
 Latest Issue  Back Issues  Events  Gallery
The Wavelet Digest
   -> Volume 5, Issue 9


Question: Wavelet dictionary - system identification
 
images/spacer.gifimages/spacer.gif Reply into Digest
Previous :: Next  
Author Message
Frode Martinsen (frodem@itk.ntnu.no)
Guest





PostPosted: Fri Oct 11, 1996 10:50 am    
Subject: Question: Wavelet dictionary - system identification
Reply with quote

#21 Question: Wavelet dictionary - system identification

This inquiry is a bit unprecise. I've "heard" that the term "wave
dictionary" implicates adapting basis-functions on the data (i.e.
switching between gaussian/mexican hat automatically). This can be of
great interest to us. In system identification adapting to different
styles on nonlinearity might improve the representation. (Discontinous
vs. smooth nonlinearities etc.) We have been using wavelet networks
for systemidentification with good results, but the number of required
parameteres is troublesome. Are the any other ways/ideas on how to
apply wavelets to control theory/system identification? Replacing the
constants in the network-weights with functions (an operating regime
decomposition approach, NARMAX) might be favourable. Anyone out there
with comments on this?

Frode Martinsen

Phone : +47 7352 6251 (private) +47 7359 4368 (office)
Telefax : +47 7359 4399 (reception at NTNU)
E-mail : Frode.Martinsen@itk.ntnu.no
WWW-info : http://www.itk.ntnu.no/ansatte/Martinsen_Frode/
All times are GMT + 1 Hour
Page 1 of 1

 
Jump to: 
 


disclaimer - webmaster@wavelet.org
Powered by phpBB

This page was created in 0.025992 seconds : 18 queries executed : GZIP compression disabled