Target discrimination using neural networks with time domain or spectrum magnitude response

Several different memory-based neural networks are used to discriminate radar targets based on their early-time, aspect-dependent response. The beginning of the response is difficult to locate in practice, so we use only the magnitude of the time response's DFT Spectrum as input to the neural network, thus eliminating time-shift uncertainty. Especially promising is the Recurrent Correlation Accumulation Adaptive Memory-Generalized Inverse (RCAAM-GI) cascade neural network. From the simulation results, the network demonstrates a decision strategy which is flexible, parallel adaptive, computation space efficient, and highly noise tolerant. Performances of the networks presented in this paper are compared with those of existing networks.

[1]  Edward J. Rothwell,et al.  A radar target discrimination scheme using the discrete wavelet transform for reduced data storage , 1994 .

[2]  D. Moffatt,et al.  Natural Resonances of Radar Targets Via Prony's Method and Target Discrimination , 1976, IEEE Transactions on Aerospace and Electronic Systems.

[3]  Carl E. Baum,et al.  The singularity expansion method and its application to target identification , 1991, Proc. IEEE.

[4]  Hsueh-Jyh Li,et al.  Experimental discrimination of wire stick targets using multiple-frequency amplitude returns , 1992 .

[5]  Yean-Woei Kiang,et al.  Target discrimination using multiple-frequency amplitude returns , 1990 .

[6]  Rodney M. Goodman,et al.  High-capacity exponential associative memories , 1988, IEEE 1988 International Conference on Neural Networks.

[7]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[8]  J. Young.  Radar imaging from ramp response signatures , 1976 .

[9]  C. Bennett,et al.  Time domain inverse scattering , 1981 .

[10]  Rodney M. Goodman,et al.  Recurrent correlation associative memories , 1991, IEEE Trans. Neural Networks.

[11]  Edward J. Rothwell,et al.  Performance of an automated radar target discrimination scheme using E pulses and S pulses , 1993 .

[12]  Edward J. Rothwell,et al.  Time-domain imaging of airborne targets using ultra-wideband or short-pulse radar , 1995 .

[13]  M. Morgan.  Scatterer Discrimination Based Upon Natural Resonance Annihilation , 1988 .

[14]  K-pulse estimation for a right-angled bent wire using more than one impulse response (radar target classification) , 1990 .

[15]  Mohamad H. Hassoun.  Dynamic Associative Memories , 1991 .

[16]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[17]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[18]  Daniel H. Schaubert,et al.  Target identification using optimization techniques , 1990 .

[19]  Kun-mu Chen,et al.  Frequency domain E-pulse synthesis and target discrimination , 1985 .

[20]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[21]  Jose B. Cruz,et al.  Guaranteed recall of all training pairs for bidirectional associative memory , 1991, IEEE Trans. Neural Networks.

[22]  Hsueh-Jyh Li,et al.  Using range profiles as feature vectors to identify aerospace objects , 1993 .