Abstract
This paper considers the equalisation problem in Quadrature Phase-Shift Keying (QPSK) modulated signals which have been distorted by the passage through a transmission channel. The channel is modelled as a Rician fading channel to simulate the behaviour of the transmission channel in the mobile satellite context. The equalisation is treated as the generalisation of the channel behaviour, and some algorithms with the structure of an artificial neural network using the Multilayer Perceptron, Volterra Series and Radial Basis Function are described. Results for the BER performance of typical transversal equalisers, with Square-Root Kalman adaptation algorithm, and algorithms with artificial neural network structure are also reported and evaluated. Improved performance is exhibited by the artificial neural network approaches.
Similar content being viewed by others
References
Qureshi S. Adaptive equalization. Proc IEEE 1985; 73(9): 1349–1387
Siu S, Gibson GJ, Cowan CFN. Decision feedback equalisation using neural network structures and performance comparison with standard architecture. IEE Proc 1990; 137, Pt I (4): 221–225
Chen S, Gibson GJ, Cowan CFN, Grant PM. Adaptive equalisation of finite non-linear channels using multilayer perceptrons. Signal Process 1990; 20(2): 107–119
Chen S, Gibson GJ, Cowan CFN, Grant PM. Reconstruction of binary signals using an adaptive radial-basis-function equaliser. Signal Process 1991; 22(1): 77–93
Grant PM, Mulgrew B, McLaughlin S, Chen S. Nonlinear architectures for equalisation, signal prediction and system modelling. In: Proc Euro Conf DSP — the Enabling Technology for Communications, Amsterdam, Netherlands, March 9–10 1993; 6.3.1–6.3.10
Davarian F. Channel simulation to facilitate mobile-satellite communications research. IEEE Trans Comm 1987; 35(1): 47–56
Jakes WC. Microwave Mobile Communications, Wiley, New York, 1974, Ch. 1
Schwartz M. et al. Communications Systems and Techniques, McGraw-Hill, New York, 1966
Widrow B, Hoff ME. Jr. Adaptive switching circuits. IRE WESCON Conv Rec 1960; Pt. 4: 96–104
Shukla PK. Adaptive equalization of fading radio channels. PhD Thesis, Imperial College of Science, Technology and Medicine, University of London, 1988
Shukla PK, Turner LF. Channel-estimation-based adaptive DFE for fading multipath radio channels. IEE Proc 1991; 138, Pt. I (6): 525–543.
Hsu FM. Square root Kalman filtering for high-speed data received over fading dispersive HF channels. IEEE Trans Infor Theory 1982; 28 (5): 753–763
Rumelhart DE, McClelland JL. Parallel Distributed Processing. Volume 1: Foundations, Bradford Book, London, 1986, Ch. 8
Lynch MR, Rayner PJ. Optical character recognition using a new connectionist model. In: Proc Int Conf Image Process, Warwick, UK, 1989; 63–67
Chen S, Gibson GJ, Cowan CNF. Adaptive channel equalisation using a polynomial-perceptron structure. IEE Proc 1990; 137 Pt I (5): 257–264
Houselander PK, Taylor JT. On the use of pre-defined regions to minimise the training and complexity of multi-layer neural networks. In: 1st IEE Int Conf on Artificial Neural Networks, 1989; 383–386
Broomhead DS, Lowe D. Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks. Royal Signals & Radar Establishment, RSRE Memorandum No. 4148, March 1988
Coloma J, Corden IR, Carrasco RA. Adaptive artificial neural network algorithms for MCD applications. In: IEE Colloquium on Adaptive Filtering, Non-Linear Dynamics and Neural Networks, London, UK, November 1991; 9/1–9/8
Coloma J, Carrasco RA. Adaptive algorithms for MCD applications over Rician fading channels. In: Proc EUSIPCO-92. Sixth Euro Signal Process Conf, Brussels, Belgium, August 24–27 1992; 1689–1692
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Coloma, J., Carrasco, R.A. Nonlinear adaptive algorithms for equalisation in mobile satellite communications. Neural Comput & Applic 2, 97–110 (1994). https://doi.org/10.1007/BF01414353
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01414353