Share Email Print

Proceedings Paper

Ionogram analysis: a neural network approach
Author(s): V. P. Grozov; V. E. Nosov; Gennadii A. Ososkov; E. G. Zaznobina
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Knowledge of the state of the ionospheric radio channels is of great importance for both ionospere research and radio wave propagation predictions. Diagnostic of ionospheric radio channels is carried out by the analysis of ionograms. An efficient method of ionogram processing is proposed. It uses an artificial neural network (ANN) with the mean field theory updating scheme. Because of a complex character of ionospheric traces with quite a heavy background, a modified rotor model of Hopfield network is used. To speed up the convergence of the ANN evolution, a special initial ANN configuration is constructed in a vicinity of the global minimum of the ANN energy function. It is done by applying a special angular histograming within a sliding window, whose size is determined by the average local track curvature. Our model was tested on ionograms obtained on the chirp- ionosonde (ISTP, Irkutsk). Result analysis shows the efficiency of our approach and its prospects for the solution of the ionograms processing problems.

Paper Details

Date Published: 13 January 1999
PDF: 5 pages
Proc. SPIE 3583, Fifth International Symposium on Atmospheric and Ocean Optics, (13 January 1999); doi: 10.1117/12.337027
Show Author Affiliations
V. P. Grozov, Institution of Solar-Terrestrial Physics (Russia)
V. E. Nosov, Institution of Solar-Terrestrial Physics (Russia)
Gennadii A. Ososkov, Joint Institute for Nuclear Research (Russia)
E. G. Zaznobina, Joint Institute for Nuclear Research (Russia)

Published in SPIE Proceedings Vol. 3583:
Fifth International Symposium on Atmospheric and Ocean Optics
Vladimir E. Zuev; Gennadii G. Matvienko, 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?