International Journal of Fuzzy Logic and Intelligent Systems

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Blind channel equalization using fourth-order cumulants and a neural network

  • Han, Soo-whan (Dept. of Multimedia Engineering Dongeui University)
  • Published : 2005.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper addresses a new blind channel equalization method using fourth-order cumulants of channel inputs and a three-layer neural network equalizer. The proposed algorithm is robust with respect to the existence of heavy Gaussian noise in a channel and does not require the minimum-phase characteristic of the channel. The transmitted signals at the receiver are over-sampled to ensure the channel described by a full-column rank matrix. It changes a single-input/single-output (SISO) finite-impulse response (FIR) channel to a single-input/multi-output (SIMO) channel. Based on the properties of the fourth-order cumulants of the over-sampled channel inputs, the iterative algorithm is derived to estimate the deconvolution matrix which makes the overall transfer matrix transparent, i.e., it can be reduced to the identity matrix by simple recordering and scaling. By using this estimated deconvolution matrix, which is the inverse of the over-sampled unknown channel, a three-layer neural network equalizer is implemented at the receiver. In simulation studies, the stochastic version of the proposed algorithm is tested with three-ray multi-path channels for on-line operation, and its performance is compared with a method based on conventional second-order statistics. Relatively good results, withe fast convergence speed, are achieved, even when the transmitted symbols are significantly corrupted with Gaussian noise.

Keywords

References

  1. J.G. Proakis, Digital Communications, New York: McGraw Hill, 2001
  2. A. Benveniste, M. Goursat, identification of a nonrninimum 'Robudt identification of a nonminimum phase system: Blind adjustment of a linear equalizer in data communications', IEEE Trans. Automat. Contr., pp.385-399, June, 1980
  3. Y. Sato, 'A method of self recovering equalization for multilevel amplitude modulation', IEEE Trans. Commun., vol.23, no.6, pp.679-682, June, 1975 https://doi.org/10.1109/TCOM.1975.1092854
  4. L. Tong, G. Xu, T. Kailath, 'Blind identification and equalization based on second order statistics: a time domain approach', IEEE Trans. Inform. Theory, vol.40, pp.340-349, 1994 https://doi.org/10.1109/18.312157
  5. Y. Fang, W.S. Chow, K.T. Ng, 'Linear neural network based blind equalization', Siganl Processing, vol.76, pp.37-42, 1999 https://doi.org/10.1016/S0165-1684(98)00245-X
  6. E. Serpedin, G.B. Giannakis, 'Blind channel identification and equalization with modulation induced cydostationarity', IEEE Trans. Siganl Processing, vol.46, pp.1930-1944, 1998 https://doi.org/10.1109/78.700965
  7. Y. Hua, 'Fast maximum likelihood for blind identification of multiple FIR channels', IEEE Trans. Signal Process, vol.44, pp.661-672, 1996 https://doi.org/10.1109/78.489039
  8. M. Kristensson, B. Ottersten, 'Statiscal analysis of a sub space method for blind channel identification', Proc. IEEE ICASSP, vol.5, pp.2435-2438, Atlanta, U.S.A., 1996
  9. W. Qiu, Y.Hua, 'A GCD method for blind channel identification', Digital Signal Process, vol.7, pp.199-205, 1997 https://doi.org/10.1006/dspr.1997.0293
  10. G. Xu, H. Liu, L. Tong, T. Kailath, 'A least squares approach to blind channel identification', IEEE Trans. Signal Processing, vol.43, pp.2982-2993, 1995
  11. Z. Ding, J. Liang, 'A cumulant matrix subspace algorithm for blind single FIR channel identification', IEEE Trans. Signal Processing, vol.49, pp.325-333, 2001 https://doi.org/10.1109/78.902114
  12. D. Boss, K. Kameyer, T. Pertermann, 'Is blind channel estimation feasible in mobile communication systems? A study based on GSM', IEEE J. Select. Areas Commun., vol.16, pp.1479-1492, 1998 https://doi.org/10.1109/49.730455
  13. Z. Ding, G. Li, 'Single channel blind equalization for GSM cellular systems', IEEE J. Select. Areas Commun., vol.16, pp.1493-1505, 1998 https://doi.org/10.1109/49.730456
  14. S. Cruces, L. Castedo, 'A. Cichocki, Robust blind source separation algorithms using cumulants', Neurocomputing, vol.49, pp.87-118, 2002 https://doi.org/10.1016/S0925-2312(02)00525-8
  15. Ham, F.M., Kostanic, I., Principles of Neurocomputing for Science and Engineering, New York: McGraw Hill, 2001
  16. Fausett, L., Fundamentals of Neural Networks: Architectures, Algorithm, and Applications, Prentice Hall, 1994
  17. Shaornin Mo, Bahram Shafai, 'Blind equalization using higher order cumulants and neural network', IEEE Trans. Signal Processing, vol.42, pp.3209-3217, 1994 https://doi.org/10.1109/78.330378
  18. X.R. Cao, R.W. Liu, 'General approach to blind source seperation', IEEE Trans. Signal Processing, vol.44, pp.562-571, 1996 https://doi.org/10.1109/78.489029
  19. C.T. Kelly, 'Iterative methods for linear and nonlinear equation', Frontiers in Applied mathematics, vol. 1, pp.71-78,SIAM,1995