Share Email Print

Proceedings Paper

Separation of merged mass-spectral patterns by feed-forward neural network filtering
Author(s): Thomas G. Thomas; Dennis G. Smith
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper describes the separation of merged signals from a mass-selective chromatographic detector by means of an adaptive filtering technique. The technique is based on parallel feed-forward neural networks, which are trained to resolve the mass spectra of two merged chemical compounds. Specifically, the chemical mass spectra of the compounds ethyl benzene and xylene were used to evaluate a filter based on probabilistic neural networks (PNN). The results are that the PNN filter shows good noise rejection and is fast enough computationally to be utilized in real time. The filter technique has applications in on-line processing of environmental monitoring instrumentation data and direct processing of pixel spectral data, such as hyperspectral image cubes.

Paper Details

Date Published: 15 November 2002
PDF: 8 pages
Proc. SPIE 4788, Photonic Devices and Algorithms for Computing IV, (15 November 2002); doi: 10.1117/12.460277
Show Author Affiliations
Thomas G. Thomas, Univ. of South Alabama (United States)
Dennis G. Smith, Univ. of Alabama at Birmingham (United States)

Published in SPIE Proceedings Vol. 4788:
Photonic Devices and Algorithms for Computing IV
Khan M. Iftekharuddin; Abdul Ahad S. Awwal, Editor(s)

© SPIE. Terms of Use
Back to Top