By Topic

A robust neural network based pulse radar detection for weak signals

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Aditya V. Padaki ; P.E.S. Centre for Intelligent Systems, P.E.S. Institute of Technology, 100 Feet Ring Road, BSK III Stage, Bangalore 560 085, India ; Koshy George

In this paper we develop a neural network capable of detecting targets with weak echoes in a pulse radar. This is possible as the network is designed as a pattern classifier (in contrast to earlier work) together with a suitable but simple pre-processing of the returns. We demonstrate through simulations that such a network exhibits better range resolution and noise tolerance when compared to previous work based on neural networks. In addition, we examine the Doppler tolerance and the overall robustness of the trained network.

Published in:

2010 IEEE Radar Conference

Date of Conference:

10-14 May 2010