Improving performance in pulse radar detection using neural networks

Author

Sridhar, G.

Volume

31

Issue

3

fYear

1995

fDate

7/1/1995 12:00:00 AM

Firstpage

1193

Lastpage

1198

Abstract

A new approach using a multilayered feed forward neural network for pulse compression is presented. The 13 element Barker code was used as the signal code. In training this network, the extended Kalman filtering (EKF)-based learning algorithm which has faster convergence speed than the conventional backpropagation (BP) algorithm was used. This approach has yielded output peak signal to sidelobe ratios which are much superior to those obtained with the BP algorithm. Further, for use of this neural network for real time processing, parallel implementation of the EKF-based learning algorithm is indispensable. Therefore, parallel implementation has also been developed

Keywords

Kalman filters; feedforward neural nets; filtering theory; learning (artificial intelligence); microcomputer applications; parallel algorithms; pulse compression; radar detection; Barker code; EKF-based learning algorithm; backpropagation algorithm; convergence speed; extended Kalman filtering; learning algorithm; multilayered feed forward neural network; output peak signal; parallel implementation; pulse compression; pulse radar detection; real time processing; sidelobe ratios; signal code; training; transputers; Backpropagation algorithms; Convergence; Feedforward neural networks; Feeds; Filtering algorithms; Kalman filters; Multi-layer neural network; Neural networks; Pulse compression methods; Radar detection;

fLanguage

English

Journal_Title

Aerospace and Electronic Systems, IEEE Transactions on

Publisher

ieee

ISSN

0018-9251

Type

jour

DOI

10.1109/7.395219

Filename

395219