Programs for signal recovery from noisy data using the maximum likelihood principle: II. Program implementation
✍ Scribed by V.I. Gelfgat; E.L. Kosarev; E.R. Podolyak
- Publisher
- Elsevier Science
- Year
- 1993
- Tongue
- English
- Weight
- 617 KB
- Volume
- 74
- Category
- Article
- ISSN
- 0010-4655
No coin nor oath required. For personal study only.
✦ Synopsis
University of Belfast, N. Ireland (see application form in this Nature of physical problem issue) The programs allow reconstruction of nonnegative signals from noisy experimental data distorted by the measuring Licensing provi.sions: Persons requesting the program must device [1].Noise may have a Gaussian, binomial or Poissonian sign the standard CPC nonprofit use licence, distribution at each experimental point. These programs may be used for: (a) reduction to an arbitrary instrumental Computer: IBM PS/2 mod.50 function, which depends only on the difference of its arguments (this is the typical spectroscopic problem); (b) the Operating .system under which theprogram has been tested: PC expansion of an exponentially decaying curie which has a DOS 3.30 continuous spectrum of decrements (this problem has applications in time-dependent fluorescence, nuclear physics etc.); Programming language used: IBM FORTRAN/2 and (c) the ultrasoft X-ray spectrum recovery from absorption measurements. Memory required to execute with typical data: 200 Kb Method of solution No. of bits in a word: 16 These programs are basCd on the maximum likelihood principle and use an algorithm of steepest descent class to No. of lines in distributed programs, including test data~etc.: find the maximum of the likelihood function. 4888 Restrictions on the complexit~vof the problem There are no principle restrictions on the usage of the Correspondence to: E