Cauchy filters versus neural networks when applied for reconstruction of absorption spectra

The computer-based interpretation of spectrometric data {/sub y(n)//sup /spl sim/Tr/} is aimed at identification of the main components of an analyzed substance. The first step of interpretation consists in estimation of its spectrum using an operator of (generalized) deconvolution {/sub x(n)//sup /...

Full description

Saved in:
Bibliographic Details
Main Authors: Sprzeczak, P., Morawski, R.Z.
Format: Conference Proceeding
Language:English
Subjects:
Calibration
Chemical analysis
Convolution
Electromagnetic wave absorption
Information analysis
Neural networks
Optical computing
Optical filters
Parameter estimation
Spectroscopy
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The computer-based interpretation of spectrometric data {/sub y(n)//sup /spl sim/Tr/} is aimed at identification of the main components of an analyzed substance. The first step of interpretation consists in estimation of its spectrum using an operator of (generalized) deconvolution {/sub x(n)//sup /spl circ/Tr/}=/spl Rscr/[{/sub y(n)//sup /spl sim/Tr/}, /sub p/spl Rscr//] were p, is a vector of parameters to be estimated during calibration of the spectrometer. Several new structures of this operator, based on combination of the Cauchy filter with an RBF-type neural network, are proposed and studied in this paper using both synthetic and real-world spectro-photometric data. Their superiority over existing algorithms for spectrum reconstruction is demonstrated.
ISSN:1091-5281
DOI:10.1109/IMTC.2001.928296