Neural network beamformer for narrow-band HF transmission

Author

Naumovski, M. ; Carrasco, R.A.

Author_Institution

Sch. of Eng., Staffordshire Polytech., Stafford, UK

fYear

1995

fDate

11/14/1995 12:00:00 AM

Firstpage

42491

Lastpage

42498

Abstract

The multi-layer perceptron (MLP), an artificial neural network, is applied to adaptive beamforming over narrow-band HF channels. An HF data transmission system is simulated, incorporating QPSK modulation, demodulation, space diversity channel model and adaptive beamforming. The simulated diversity channels are characterised by Rayleigh fading and have time-varying characteristics. MLP beamformer has the ability to learn the statistical behaviour of the channels and to correct the distortion they introduce to the transmitted signals. Simulation results for the MLP beamformer using the back-propagation algorithm and for the conventional beamformer using the least-mean square (LMS) algorithm are reported and evaluated. Improved performance is exhibited by MLP beamforming techniques

Keywords

Rayleigh channels; array signal processing; backpropagation; data communication; diversity reception; fading; interference suppression; least mean squares methods; multilayer perceptrons; quadrature phase shift keying; radiofrequency interference; time-varying channels; HF data transmission system; MLP beamforming; QPSK modulation; Rayleigh fading; adaptive beamforming; back-propagation algorithm; demodulation; distortion; least-mean square algorithm; multi-layer perceptron; narrow-band HF channels; narrow-band HF transmission; neural network beamformer; space diversity channel model; statistical behaviour; time-varying characteristics; transmitted signals;

fLanguage

English

Publisher

iet

Conference_Titel

HF Antennas and Propagation, IEE Colloquium on

Conference_Location

London

Type

conf

DOI

10.1049/ic:19951273

Filename

499599