Adaptive FSK decoding with an artificial neural network

Author

Hayes, Paul V. ; Uhey, Jeffrey R. ; Sayegh, Samir I.

Author_Institution

Div. Aerospace/Commun., ITT Defence, USA

fYear

1994

fDate

10-12 May 1994

Firstpage

197

Lastpage

208

Abstract

We describe an empirical study of the capability of an artificial neural network (ANN) to decode a frequency shift key (FSK) signal. An algorithm for generating a minimal, yet comprehensive ANN training data set is discussed. The FSK signal is over sampled. The samples are presented to the ANN as a window in time. The window is one symbol wide. After initial training, white Gaussian noise is added to the samples and the ANN´s ability to generalize is tested. We then conduct additional training, using the noisy data, to test the ANN´s ability to adaptively recover. Simulation results are reported

Keywords

Gaussian noise; adaptive decoding; frequency shift keying; neural nets; telecommunication computing; adaptive FSK decoding; algorithm; artificial neural network; empirical study; noisy data; simulation; training data set; white Gaussian noise; Artificial neural networks; Data communication; Decoding; Digital modulation; Forward error correction; Frequency shift keying; Gaussian noise; Redundancy; Signal to noise ratio; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Tactical Communications Conference, 1994. Vol. 1. Digital Technology for the Tactical Communicator., Proceedings of the 1994

Conference_Location

Fort Wayne, IN

Print_ISBN

0-7803-2004-2

Type

conf

DOI

10.1109/TCC.1994.472089

Filename

472089