Share Email Print

Proceedings Paper

Distributed physical field monitoring by using a photomatrix neural-like system
Author(s): Yuri N. Kulchin; Igor V. Denisov; Oleg T. Kamenev; Andrey V. Panov; Yuri S. Petrov
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In the given paper principles of organization of neural-like system consisting of a matrix of photoelectric cells are represented. The practical realization of this system allows to obtain a parallel processing of an optical information for environmental physical field monitoring . A computer model of the feed-forward neural network with the hidden layer is developed to reconstruct physical field investigated by the fiber optic measuring system. The Gaussian distributions of some physical quantity are selected as learning patterns. Neural network is learned by error back-propagation using the conjugate gradient and coordinate descent minimization of deviation. Learned neural network reconstructs the two-dimensional scalar physical field with distribution having one or two Gaussian peaks.

Paper Details

Date Published: 8 May 2001
PDF: 4 pages
Proc. SPIE 4416, Optical Engineering for Sensing and Nanotechnology (ICOSN 2001), (8 May 2001); doi: 10.1117/12.427065
Show Author Affiliations
Yuri N. Kulchin, Far Eastern State Technical Univ. (Russia)
Igor V. Denisov, Far Eastern Marine Academy (Russia)
Oleg T. Kamenev, Far Eastern State Technical Univ. (Russia)
Andrey V. Panov, Institute for Automation and Control Processes (Russia)
Yuri S. Petrov, Far Eastern State Technical Univ. (Russia)

Published in SPIE Proceedings Vol. 4416:
Optical Engineering for Sensing and Nanotechnology (ICOSN 2001)
Koichi Iwata, Editor(s)

© SPIE. Terms of Use
Back to Top