A hybrid genetic/BP algorithm and its application for radar target classification

Author

Yan, WeI ; Zhu, Zhaoda ; Hu, Rong

Author_Institution

Dept. of Electron. Eng, Nanjing Univ. of Aeron. & Astron., China

Volume

2

fYear

1997

fDate

14-18 Jul 1997

Firstpage

981

Abstract

In this paper, a general purposed real valued genetic algorithm model is presented. For the training of neural networks, the hybrid algorithm integrates the real valued algorithm with the well known BP algorithm. It is used to the training of a feedforward neural networks for radar target classification based on 1-D range profile. 50 range profile samples from the real radar data of each of the three aircrafts are used to train the neural network and another 50 range profile samples are used to test the classification performance. The proposed method can also be used to other optimization problems

Keywords

backpropagation; feedforward neural nets; genetic algorithms; image classification; radar signal processing; radar target recognition; 1-D range profile; aircraft; classification performance; feedforward neural networks; hybrid genetic/BP algorithm; optimization; radar data; radar target classification; range profile samples; training; Airborne radar; Aircraft; Electronic mail; Feedforward neural networks; Genetic algorithms; Multi-layer neural network; Neural networks; Optimization methods; Radar applications; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Aerospace and Electronics Conference, 1997. NAECON 1997., Proceedings of the IEEE 1997 National

Conference_Location

Dayton, OH

Print_ISBN

0-7803-3725-5

Type

conf

DOI

10.1109/NAECON.1997.622762

Filename

622762