Browse > Article
http://dx.doi.org/10.5302/J.ICROS.2003.9.11.917

Equalization of Time-Varying Channels using a Recurrent Neural Network Trained with Kalman Filters  

최종수 (School of Information Technology & Engineering, University of Ottawa, Canada)
권오신 (School of Information Technology & Engineering, University of Ottawa, Canada)
Publication Information
Journal of Institute of Control, Robotics and Systems / v.9, no.11, 2003 , pp. 917-924 More about this Journal
Abstract
Recurrent neural networks have been successfully applied to communications channel equalization. Major disadvantages of gradient-based learning algorithms commonly employed to train recurrent neural networks are slow convergence rates and long training sequences required for satisfactory performance. In a high-speed communications system, fast convergence speed and short training symbols are essential. We propose decision feedback equalizers using a recurrent neural network trained with Kalman filtering algorithms. The main features of the proposed recurrent neural equalizers, utilizing extended Kalman filter (EKF) and unscented Kalman filter (UKF), are fast convergence rates and good performance using relatively short training symbols. Experimental results for two time-varying channels are presented to evaluate the performance of the proposed approaches over a conventional recurrent neural equalizer.
Keywords
recurrent neural network; extended kalman filter; unscented kalman filter; channel equalization; time-varying channel;
Citations & Related Records
연도 인용수 순위
  • Reference
1 P. J. Werbos, 'Back-propagation through time: What it does and how to do it,' Proceedings of the IEEE, vol. 78, pp. 1550-1560, October 1990   DOI   ScienceOn
2 L. A. Feldkamp and G. V. Puskorius, 'A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering and classification,' Proceedings of the IEEE, vol. 86, pp. 2259-2277, 1998   DOI   ScienceOn
3 S. J. Julier and J. K. Uhlmann, 'A new extension of the Kalman filter to nonlinear systems,' in Proceedings of AeroSence: The 11th International Symposium on Aerospace/Defence Sensing, Simulation and Controls, 1997
4 E. A. Wan and R. van der Merwe, 'The unscented Kalman filter,' in Kalman Filtering and Neural Networks, Edited by S. Haykin. John Wiley and Sons, Inc., 2001
5 S. Chen, B. Mulgrew, and S. McLaughlin, 'Adaptive equalization of finite nonlilear channels using multilayer perceptions,' Signal Processing, vol. 20, 1990
6 S. Ong, C. You, S. Choi, and D. Hong, 'A decision response filter,' IEEE Transactions on Signal Processing, vol. 45, pp. 2851-2858, November 1997   DOI   ScienceOn
7 S. Qureshi, 'Adaptive equalization,' Proceedings of the IEEE, vol. 73, no. 9, pp. 1349-1387, 1985   DOI   ScienceOn
8 S. Chen, B. Mulgrew, and S. McLaughlin, 'Adaptive Bayesian equalizer with decision feedback,' IEEE Transactions on Signal Processing, vol. 41, pp. 2918-2927, September 1993   DOI   ScienceOn
9 A. Zerguine, A. Shafi, and M. Bettayeb, 'Multilayer perception-based DFE with lattice structure,' IEEE Transactions on Neural Networks, vol. 12, pp. 532-545, May 2001   DOI   ScienceOn
10 B. Mulgrew, 'Applying radial basis function networks,' IEEE Signal Processing Magazine, pp. 50-65, March 1996
11 S. Siu, G. J. Gibson, and C. F. N. Cowan, 'Decision feedback equalization using neural network structures and performance comparison with standard architecture,' IEEE Proceedings: Part I, vol. 137, no. 4, pp. 221-225,1990   DOI   ScienceOn
12 J. D. Ortiz-Fuentes and M. L. Forcada, 'A comparison Conference on Acoustics, Speech, and Signal Processing, pp. 3281-3284,1997
13 C. Cowan and S. Semnani, 'Time-variant equalization using a novel non-linear adaptive structure,' International Journal of Adaptive Control and Signal Processing, vol. 12, no. 2, pp. 195-206,1998   DOI   ScienceOn
14 S. Haykin, Neural Networks: a Comprehensive Foundation, 2nd Ed. Upper Saddle River, NJ: Prentice Hall, 1999
15 G. Kechriotis, E. Zervas, and E. S. Manolakos, 'Using recurrent neural networks for adaptive communication channel equalizations,' IEEE Transactions on Neural Networks, vol. 5, pp. 267-278, March 1994   DOI   ScienceOn
16 R. J. Williams and D. Zipser, 'A learning algorithm for continually running fully recurrent neural networks,' Neural Computation, vol. 1, pp. 270-280,1989   DOI
17 F. Ling and J. G. Proakis, 'Adaptive lattice decision feedback equalizers-Their performance and application to time-variant multipath channels,' IEEE Transactions on Communications, vol. 33, pp. 348-356, April 1985
18 R. Parisi, E. D. D. Claudio, G. Orlandi, and B. D. Rao, 'Fast adaptive digital equalization by recurrent neural networks,' IEEE Transactions on Signal Processing, vol. 45, pp. 2731-2739, November 1997   DOI   ScienceOn
19 K. Hacioglu, 'An improved recurrent neural network for M-PAM symbol detection,'IEEE Transactions on Neural Networks, vol. 8, pp. 779-783, May 1997   DOI   ScienceOn
20 S. Haykin, Adaptive Filter Theory, 4th Ed. Upper Saddle River, NJ: Prentice Hall, 2002
21 Q. Liang and J. M. Mendel, 'Equalization of nonlinear time-varying channels using type-2 fuzzy adaptive filters,'IEEE Transactions on Fuzzy Systems, vol. 8, pp. 551-563, October 2000   DOI   ScienceOn
22 E. A. Wan and R. van der Merwe, 'The unscented Kalman filter for nonlinear estimation,' in Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications and Control Symposium (AS-SPCC), pp. 153-158,2000   DOI
23 M. Solazzi, A. Uncini, E. D. D. Claudio, and R. Parisi, 'Complex discriminative learning Bayesian neural equalizer,'in Proceedings of the 1999 IEEE International Symposium on Circuits and Systems (ISCAS '99), pp. 343-346,1999   DOI
24 J. Elman, 'Finding structure in time,' Congnitive Science, vol. 14, pp. 179-211, 1990   DOI   ScienceOn