CaltechAUTHORS
  A Caltech Library Service

Fast neural algorithms for detecting moving targets in highly noisy environments

Barhen, Jacob and Toomarian, Nikzad and Zak, Michail (1992) Fast neural algorithms for detecting moving targets in highly noisy environments. In: Signal and Data Processing of Small Targets 1992. Proceedings of SPIE. No.1698. Society of Photo-Optical Instrumentation Engineers (SPIE) , Bellingham, WA, pp. 32-41. ISBN 0-8194-0863-8. https://resolver.caltech.edu/CaltechAUTHORS:20170913-104611644

[img] PDF - Published Version
See Usage Policy.

328kB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20170913-104611644

Abstract

The detection of targets moving in an environment dominated by "noise" is addressed from the perspective of nonlinear dynamics. Sensor data are used to drive a Korteweg-deVries (soliton) equation, inducing a resonance-type phenomenon which indicates the presence of hidden target signals. The algorithm is implemented in terms of a novel neural architecture, which we have named "spectral network", which can easily be implemented in optoelectronic hardware.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1117/12.139392DOIArticle
https://www.spiedigitallibrary.org/conference-proceedings-of-spie/1698/1/Fast-neural-algorithms-for-detecting-moving-targets-in-highly-noisy/10.1117/12.139392.fullPublisherArticle
Additional Information:© 1992 Society of Photo-Optical Instrumentation Engineers (SPIE). This research was carried out at the Jet Propulsion Laboratory, California Institute of Technology. Support for the work came from the Naval Weapons Center, China Lake, California, through an agreement with the National Aeronautics and Space Administration. We thank A. Agranat, C. Neugebauer and A. Yariv (Caltech), as well as R. Tawel and A. Thakoor (JPL) for enlightening discussions concerning possible hardware implementation of our algorithms.
Funders:
Funding AgencyGrant Number
Naval Weapons CenterUNSPECIFIED
NASAUNSPECIFIED
Subject Keywords:target detection, driven solitons, spectral neural networks, optoelectronic implementation.
Series Name:Proceedings of SPIE
Issue or Number:1698
DOI:10.1117/12.139392
Record Number:CaltechAUTHORS:20170913-104611644
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20170913-104611644
Official Citation:Jacob Barhen, Nikzad Toomarian, Michail Zak, "Fast neural algorithms for detecting moving targets in highly noisy environments", Proc. SPIE 1698, Signal and Data Processing of Small Targets 1992, (1992/08/25) http://dx.doi.org/10.1117/12.139392
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:81410
Collection:CaltechAUTHORS
Deposited By: Ruth Sustaita
Deposited On:14 Sep 2017 22:15
Last Modified:15 Nov 2021 19:43

Repository Staff Only: item control page