Title :
On the Design of a Compact Neural Network-Based DOA Estimation System
Author :
Fonseca, Nelson Jorge G ; Coudyser, Michael ; Laurin, Jean-Jacques ; Brault, Jean-Jules
Author_Institution :
Poly-Grames Res. Centre, Montreal, QC, Canada
Abstract :
A system to measure the direction of arrival (DOA) of a signal within a 45-degree conical sector is demonstrated. The system is compact and uses only four circularly polarized patch elements. A printed beamforming network is used to create a set of partially overlapping beams allowing DOA estimation without ambiguity. Neural networks are used to first classify the antenna signals and then estimate the DOA. The proposed system was validated experimentally in C band and, in spite of the highly disturbed beams caused by the finite size of the antenna platform, it was shown that DOA estimation errors in the order of one degree were achievable under signal-to-noise ratios of 10 dB.
Keywords :
antennas; array signal processing; direction-of-arrival estimation; neural nets; 45-degree conical sector; DOA estimation errors; DOA estimation system; antenna platform; antenna signals; circularly polarized patch elements; compact neural network; direction of arrival; finite size; partially overlapping beams; printed beamforming network; Adaptive arrays; Array signal processing; Base stations; Direction of arrival estimation; Directive antennas; Neural networks; Polarization; Portable computers; Radar antennas; Receiving antennas; Signal to noise ratio; Array feeding network; direction finding antenna; monopulse radar; neural network;
Journal_Title :
Antennas and Propagation, IEEE Transactions on
DOI :
10.1109/TAP.2009.2037766
