Share Email Print

Proceedings Paper

Neural network and classical least squares methods for quantitative analysis in remote sensing FTIR systems
Author(s): C. David Wang; William T. Walter; Robert H. Kagann
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Remote monitoring of molecular species in the atmosphere is accomplished using a Fourier transform infrared (FTIR) spectrometer. Advanced processing algorithms utilized by AIL Systems include the classical least squares (CLS) technique as well as a more recently developed approach which combines digital finite impulse response filtering, adaptive sampling, and artificial neural networks (ANN) to improve detection sensitivity and estimation accuracy. This paper presents a comparison between the CLS and the ANN methods in estimating concentrations of multicomponent mixtures. Detection improvement of ANN over CLS has been demonstrated by examining SF6 in a stack plume and toluene in a laboratory experiment.

Paper Details

Date Published: 10 February 1995
PDF: 12 pages
Proc. SPIE 2366, Optical Instrumentation for Gas Emissions Monitoring and Atmospheric Measurements, (10 February 1995); doi: 10.1117/12.205566
Show Author Affiliations
C. David Wang, AIL Systems Inc. (United States)
William T. Walter, AIL Systems Inc. (United States)
Robert H. Kagann, AIL Systems Inc. (United States)

Published in SPIE Proceedings Vol. 2366:
Optical Instrumentation for Gas Emissions Monitoring and Atmospheric Measurements
Michael G. Yost; Dennis K. Killinger; Joseph Leonelli; William Vaughan; Dennis K. Killinger; William Vaughan; Michael G. Yost, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?