By Topic

Improved supervision of NN's AOA determination with limited 1-D phased-array training data

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)
Van Sickle, K. ; Dept. of Electr. & Comput. Eng., Oakland Univ., Rochester, MI, USA ; Abdel-Aty-Zohdy, H.S.

A sixteen-channel linear phased array radar is calibrated by means of Artificial Neural Network (ANN). Limited data are used to train the various layers of the network, for Angle of Arrival (AOA) determinacy. This is designed to increase speed of operation and to prevent over fitting. The designed simulator generates time-series data sets representing continuous span of AOA. The generated datasets are used in multilayer feedforward NNs to find the phase, which is then used as inputs to Spiking Neural Network (SNN) o determine AOA. SNNs are used for hardware implementation feasibility. The designed simulator improved the accuracy of AOA determination, and opens the door for a wide variety of radar classification applications.

Published in:

Aerospace and Electronics Conference (NAECON), Proceedings of the 2011 IEEE National

Date of Conference:

20-22 July 2011