| Re: Spectral estimation in IDL [message #4148] |
Thu, 27 April 1995 00:00 |
VUKOVIC
Messages: 6
Registered: December 1994
|
Junior Member |
|
|
In <DAFT.95Apr26155137@debussy.crd.ge.com> daft@debussy.crd.ge.com writes:
> Does anyone know of any IDL code which does spectral estimation by
> maximum entropy methods? For example, is there an implementation of
> Burg's algorithm out there? I checked the Johns Hopkins and NASA IDL
> libraries, without success. Numerical recipes does discuss a maximum
> entropy method, but it's not one of the numerical recipes routines
> which come with ideal.
>
> Any pointers greatly appreciated.
> --
> Chris M.W. Daft <daft@crd.ge.com>
> KWC-1336, GE CR&D 518-387-6615
> P.O. Box 8 518-387-7512 (fax)
> Schenectady, N.Y. 12301-0008
By maximum entropy I presume you mean Autoregressive (AR) type methods,
of which maximum entropy is but one.
It may be a bit wastefull to do it in IDL. I used fortran routines
in L. Marple's Digital Spectral Analysis with Applications (Prentice
Hill, and then wrote IDL routines to call the programs with CALL_EXTERNAL.
The single channel AR methods work all ok, but I could not get the
multiple channel to go.
I cannot send you the fortran stuff (it is copyrighted) but you are
welcome to my IDL calling routines -- not that they are any great feat
of programming.
Mirko
Mirko Vukovic | vukovic@uwmfe.neep.wisc.edu
Dept. of Nucl. Eng. and Eng. Phys. | mvukovic@wiscmacc.bitnet
U of Wisconsin -- Madison | phone: (608) 265-4069
1500 Johnson Drive; Madison WI 53706| fax: (608) 265-2364
|
|
|
|
comp.lang.idl-pvwave archive
Members
Search
Help
Login
Home
