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 6, Issue 9


Question: Shift-invariance for classification
 
images/spacer.gifimages/spacer.gif Reply into Digest
Previous :: Next  
Author Message
"Godfrey, Susan" (susan.godfrey@dsto.defence.gov.au)
Guest





PostPosted: Mon Aug 25, 1997 6:15 am    
Subject: Question: Shift-invariance for classification
Reply with quote

#18 Question: Shift-invariance for classification

Dear waveleteers,
Recently, I have been applying Saito's Local Discriminant Basis
algorithm to the classification of underwater, acoustic, transient
data. Being transient, I find that great care needs to be taken to
avoid/minimise translations when combining the training data of each
class into the time-frequency energy maps. Having looked at Cohen et
al's algorithm for Orthogonal Shift-invariant wavelet packet
decomposition, I am interested in incorporating this. My question is,
what cost function should I use for determining the 'best',
shift-invariant wavelet packet tree for each time-series ? Any
comments on this, are greatly appreciated,

Thanks,
Susan Godfrey.
All times are GMT + 1 Hour
Page 1 of 1

 
Jump to: 
 


disclaimer - webmaster@wavelet.org
Powered by phpBB

This page was created in 0.024041 seconds : 18 queries executed : GZIP compression disabled