Share Email Print
cover

Proceedings Paper

Verification of the performance of Artificial Neural Networks (ANNs) versus Partial Least Squares (PLS) for spectral interference correction in optical emission spectrometry
Author(s): Z. Li; X. Zhang; V. Karanassios
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Interference from overlaps of spectral lines is a key concern in optical emission spectrometry even when a spectrometer with relatively high resolution and a long focal length (e.g., 1 m) is used. The problem becomes more complex when a portable spectrometer (e.g., with a focal length of 12.5 cm) with low resolution is used. Such a spectrometer is better suited for “taking part of the lab to the sample” types of applications. We used Artificial Neural Networks (ANNs) and Partial Least Squares (PLS) to address spectral interference correction and our efforts are described here in some detail.

Paper Details

Date Published: 22 May 2014
PDF: 8 pages
Proc. SPIE 9118, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XII, 911812 (22 May 2014); doi: 10.1117/12.2050326
Show Author Affiliations
Z. Li, Univ. of Waterloo (Canada)
X. Zhang, Univ. of Waterloo (Canada)
V. Karanassios, Univ. of Waterloo (Canada)


Published in SPIE Proceedings Vol. 9118:
Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XII
Harold H. Szu; Liyi Dai, Editor(s)

© SPIE. Terms of Use
Back to Top