Share This Article:

Fast Fading Channel Neural Equalization Using Levenberg-Marquardt Training Algorithm and Pulse Shaping Filters

Abstract Full-Text HTML XML Download Download as PDF (Size:170KB) PP. 71-74
DOI: 10.4236/ijcns.2014.72008    4,209 Downloads   5,688 Views   Citations

ABSTRACT

Artificial Neural Network (ANN) equalizers have been successfully applied to mitigate Inter symbolic Interference (ISI) due to distortions introduced by linear or nonlinear communication channels. The ANN architecture is chosen according to the type of ISI produced by fixed, fast or slow fading channels. In this work, we propose a combination of two techniques in order to minimize ISI yield by fast fading channels, i.e., pulse shape filtering and ANN equalizer. Levenberg-Marquardt algorithm is used to update the synaptic weights of an ANN comprise only by two recurrent perceptrons. The proposed system outperformed more complex structures such as those based on Kalman filtering approach.

Conflicts of Interest

The authors declare no conflicts of interest.

Cite this paper

T. Mota, J. Leal and A. Lima, "Fast Fading Channel Neural Equalization Using Levenberg-Marquardt Training Algorithm and Pulse Shaping Filters," International Journal of Communications, Network and System Sciences, Vol. 7 No. 2, 2014, pp. 71-74. doi: 10.4236/ijcns.2014.72008.

References

[1] J. Choi, A. C. de C. Lima and S. Haykin, “Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels,” IEEE Transactions on Communication, Vol. 3, No. 3, 2005, pp. 472-480.
http://dx.doi.org/10.1109/TCOMM.2005.843416
[2] P. Corral, O. Ludwig and A. C. de C. Lima, “Time-Varying Channel Neural Equalization Using Gauss-Newton Algorithm,” Eletronics Letters, Vol. 46, No. 15, 2010, pp. 1055-1056.
[3] Z. Chen and A. C. de C. Lima, “A New Neural Equalizer for Decision-Feedback Equalization,” IEEE Signal Processing Society Workshop, 2004, pp. 675-684.
[4] F. J. González-Serrano, F. Pérez-Cruz and A. Artés-Rodríguez, “Reduced-Complexity Equaliser for Nonlinear Channels,” Eletronics Letters, Vol. 34, No. 9, 1998, pp. 856-858.
[5] H. Q. Zhao, X. P. Zeng, Z. Y. He, W. D. Jin and T. R. Li, “Complex-Valued Pipelined Decision Feedback Recurrent Neural Network for Non-Linear Channel Equlisation,” Electronics Letters, Vol. 6, No. 9, 2012, pp. 1082-1096.
[6] H. Leung and S. Haykin, “The Complex Backpropagation Algorithm,” IEEE Transactions on Signal Processing, Vol. 3, No. 9, 1991, pp. 2101-2104.
http://dx.doi.org/10.1109/78.134446
[7] N. Benvenuto and F. Piazza, “On the Complex Backpropagation Algorithm,” IEEE Transactions on Signal Processing, Vol. 40, No. 4, 1992, pp. 967-969.
http://dx.doi.org/10.1109/78.127967
[8] T. Kim and T. Adali, “Fully Complex Multi-Layer Perceptron Network for Nonlinear Signal Processing,” The Journal of VLSI Signal Processing, Springer, Berlin, 2002.
[9] M. Peng, C. L. Nikias and J. G. Proakis, “Adaptive Equalization with Neural Networks: New Multi-Layer Perceptron Structures and Their Evaluation,” IEEE International Conference on Acoustics, Speech, and Signal Processing, San Francisco, 23-26 March 1992, pp. 301-304.
[10] A. Shafi, A. Zerguine and M. Bettayeb, “Neural NetworkBased Decision Feedback Equalizer with Lattice Structure,” Eletronics Letters, Vol. 35, No. 20, 1999, pp. 1705-1707.
[11] F. Ling and J. G. Proakis, “Adaptive Lattice DecisionFeedback Equalizer—Their Performance and Application to Time-Variant Multipath Channels,” IEEE Transactions on Communication, Vol. COM-33, No. 4, 1985, pp. 348-356. http://dx.doi.org/10.1109/TCOM.1985.1096300
[12] G. Kechriotis, E. Zervas and E. S. Manolakos, “Using Recurrent Neural Networks for Adaptive Communication Channel Equalizations,” IEEE Transactions on Neural Networks, Vol. 5, No. 2, 1994, pp. 267-278.
http://dx.doi.org/10.1109/72.279190
[13] S. Lawrence, C. L. Giles and A. C. Tsoi, “Lessons in Neural Network Training: Overfitting May Be Harder than Expected,” Proceedings of the 14th National Conference on Artificial Intelligence, AAAI-97, AAAI Press, Menlo Park, California, 1997, pp. 540-545.
[14] K. Mahdaviani, H. Mazyar, S. Majidi and M. H. Saraee, “A Method to Resolve the Overfitting Problem in Recurrent Neural Networks for Prediction of Complex Systems’ Behavior,” International Joint Conference on Neural Networks, Hong Kong, 1-8 June 2008, pp. 3723-3728.

  
comments powered by Disqus

Copyright © 2019 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.