MathGroup Archive 2008

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: Wavelet "filter"?

  • To: mathgroup at smc.vnet.net
  • Subject: [mg85081] Re: Wavelet "filter"?
  • From: Bill Rowe <readnewsciv at sbcglobal.net>
  • Date: Sun, 27 Jan 2008 05:48:13 -0500 (EST)

On 1/25/08 at 5:02 AM, edsferr at uol.com.br (edsferr) wrote:

>That's a very clever way to do this task, although this is not what
>I wanted. I don't want to search which are the most commom strings
>IN my data. Based on wavelet analysis I think , if I'm not wrong,
>one is able to select the strings that are the most likely to occur
>among all the possible strings.

I strongly suspect you are misunderstanding the wavelet tool you
are using. Or you are not accurately describing your problem and
what you are trying to do.

Fundamentally, wavelets are simply another way to representing
your data set. For a given data set and a particular wavelet,
this representation is unique to your data set. It cannot
contain information not in your data set. That is any wavelet
representation of your data cannot possibly give you information
about strings not in your data set.


--
To reply via email subtract one hundred and four


  • Prev by Date: Re: List complement operator
  • Next by Date: Re: Better way to write this
  • Previous by thread: Re: Wavelet "filter"?
  • Next by thread: Problems with compling of MathLink Program in VC 2008 [SOLVED]