Title :
Classification of weather clutter models using neural networks
Author :
Jakubiak, Andrzej
Author_Institution :
Warsaw Univ. of Technol., Poland
Abstract :
A decision system based on Kohonen LVQ2 neural network was used for the classification of weather clutter statistics. Three classes of distributions were distinguished: log-normal, Weibull and K. Data which were observed using L band radar. It was shown that the measured clutter amplitude samples obey a Weibull distribution, according to the classifier decision.
Keywords :
Weibull distribution; log normal distribution; parameter estimation; radar clutter; radar computing; self-organising feature maps; vector quantisation; K distribution; Kohonen LVQ2 neural network; L band radar; Weibull distribution; classifier decision; clutter amplitude samples; decision system; log normal distribution; parameter estimation; weather clutter model classification; weather clutter statistics; Histograms; Neural networks; Parameter estimation; Probability density function; Radar clutter; Radar detection; Random variables; Statistical distributions; Surveillance; Weibull distribution;
Conference_Titel :
Modern Problems of Radio Engineering, Telecommunications and Computer Science, 2004. Proceedings of the International Conference
Conference_Location :
Lviv-Slavsko, Ukraine
Print_ISBN :
966-553-380-0
