Neural approaches to ship target recognition

Author

Inggs, M.R. ; Robinson, A.R.

Author_Institution

Cape Town Univ., Rondebosch, South Africa

fYear

1995

fDate

8-11 May 1995

Firstpage

386

Lastpage

391

Abstract

This paper summarizes current research into the applications of neural networks for radar ship target recognition. Three very different neural architectures are investigated and compared, namely; the feedforward network with backpropagation, Kohonen´s (1990) supervised learning vector quantization network, and Simpson´s (see IEEE Trans on Neural Networks, vol.3, no.5, p.776-787, 1992) fuzzy min-max neural network. In all cases, preprocessing in the form of the Fourier-modified discrete Mellin transform is used as a means of extracting feature vectors which are insensitive to the aspect angle of the radar. Classification tests are based on both simulated and real data. Classification accuracies of up to 93% are reported

Keywords

backpropagation; discrete Fourier transforms; feature extraction; feedforward neural nets; fuzzy neural nets; learning (artificial intelligence); minimax techniques; neural net architecture; radar applications; radar computing; radar signal processing; radar target recognition; radionavigation; self-organising feature maps; ships; vector quantisation; Fourier-modified discrete Mellin transform; Kohonen´s network; aspect angle; backpropagation; classification accuracies; classification tests; feature vectors extraction; feedforward network; fuzzy min-max neural network; neural architectures; neural networks; noncoherent navigation radar; preprocessing; radar recognition; real data; research; ship target recognition; simulated data; supervised learning vector quantization network; Backpropagation; Discrete Fourier transforms; Feedforward neural networks; Fuzzy neural networks; Marine vehicles; Neural networks; Radar applications; Supervised learning; Target recognition; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Radar Conference, 1995., Record of the IEEE 1995 International

Conference_Location

Alexandria, VA

Print_ISBN

0-7803-2121-9

Type

conf

DOI

10.1109/RADAR.1995.522577

Filename

522577