ELECTRICA

A NEW APPROACH BASED ON WAVELET NERO GENETIC NETWORK FOR AUTOMATIC TARGET RECOGNITION WITH X-BAND DOPPLER RADAR

1.

Firat University, Department of Electronic and Computer Science, 23119, Elazig, TURKEY

2.

Firat University, Department of Electronics and Computer Science, 23119, Elazig/TURKEY

3.

Firat University, Engineering Faculty, Department of Electric and Electronic, 23119, Elazig, TURKEY

ELECTRICA 2006; 6: 157-168
Read: 933 Downloads: 600 Published: 02 January 2012

In this study, a Mexican Hat Wavelet scalogram neural genetic network approach is proposed for signal classification. The Wavelet Scalogram network uses a Levenberg-Marquardt multilayer feed- forward neural network-genetic algorithm hybrid structure, and its input layer constitutes the feature extraction part, whereas the hidden layer and output layer constitute the signal classification part. From the physics point of view, it is shown that the time-shifted, frequency-modulated, and scaled Mexican Hat Wavelet scalogram is available for a basic model for the 1-D target Doppler signal of high-resolution radar. Logarithmic Normalization Method (LNM) was proposed for increasing efficiently of feature extraction phase of Wavelet Nero Genetic Network and classification. Two experiment examples show that the Wavelet Nero Genetic Network (WNGN) approach has a higher recognition rate in radar target recognition from Doppler signals as compared with several existing methods.

Files
EISSN 2619-9831