Share Email Print

Proceedings Paper

Novel approach to the use of neural networks to solve real-world analytical problems
Author(s): Jeremy M. Lerner; Thomas Taiwei Lu; David T. Mintzer; Sean Zhao
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper describes the general architecture of a hybrid neural network used to identify noisy and extremely complex spectra. A hybrid neural network has been built for environmental monitoring, medical diagnosis, and process control applications. The hybrid neural network consists of preprocessing algorithms to enhance the features of the spectra and an interconnect weight matrix for recognition. Results suggest that the hybrid neural network, through careful design of both the preprocessing algorithms and the neural network architecture, is capable of increasing the detection limit and speed of many analytical instruments.

Paper Details

Date Published: 3 April 1995
PDF: 8 pages
Proc. SPIE 2386, Ultrasensitive Instrumentation for DNA Sequencing and Biochemical Diagnostics, (3 April 1995); doi: 10.1117/12.206022
Show Author Affiliations
Jeremy M. Lerner, Physical Optics Corp. (United States)
Thomas Taiwei Lu, Physical Optics Corp. (United States)
David T. Mintzer, Physical Optics Corp. (United States)
Sean Zhao, Physical Optics Corp. (United States)

Published in SPIE Proceedings Vol. 2386:
Ultrasensitive Instrumentation for DNA Sequencing and Biochemical Diagnostics
Gerald E. Cohn; Jeremy M. Lerner; Kevin J. Liddane; Alexander Scheeline; Steven A. Soper, 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?