Journal of Communications and Networks

  • 제5권1호
  • /
  • Pages.7-18
  • /
  • 2003
  • /
  • 1229-2370(pISSN)
  • /
  • 1976-5541(eISSN)
한국통신학회 (The Korean Institute of Commucations and Information Sciences)
권호 표지

Recurrent Neural Network Adaptive Equalizers Based on Data Communication

  • Jiang, Hongrui (Graduate School of Information Technology and Telecommunications, Inha University) ;
  • Kwak, Kyung-Sup (Graduate School of Information Technology and Telecommunications, Inha University)
  • 발행 : 2003.03.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In this paper, a decision feedback recurrent neural network equalizer and a modified real time recurrent learning algorithm are proposed, and an adaptive adjusting of the learning step is also brought forward. Then, a complex case is considered. A decision feedback complex recurrent neural network equalizer and a modified complex real time recurrent learning algorithm are proposed. Moreover, weights of decision feedback recurrent neural network equalizer under burst-interference conditions are analyzed, and two anti-burst-interference algorithms to prevent equalizer from out of working are presented, which are applied to both real and complex cases. The performance of the recurrent neural network equalizer is analyzed based on numerical results.

키워드

참고문헌

  1. G. J. Gibson, S. Siu, and C. F. N. Cowan, 'Application of multilayer per-ceptrons as adaptive channel equalizers,' in Proc. IEEE Internat. Conf.Acoust. Speech Signal Process, Glasgow, Scotland, May 1989, pp. 1183-1186
  2. I. Cha and S. A. Kassam, 'Channel equalization using adaptive complexradial basis function network,' IEEE J. SAC, vol. 13, no. 1, pp. 121-131,Jan. 1995
  3. M. J. Bradley and P. Mars, 'Application of recurrent neural networksto communication channel equalization,' IEEE Trans. NeuraI Networks,vo1.5,no.2,Mar. 1994
  4. G. Kechriotis, E. Zervas, and E. Manolakos, 'Using recun-ent neural net-works for adaptive communication channel equalization,' IEEE Trans.NeuraI Networks, vol. 5, no. 2, pp. 617-620, Mar. 1994
  5. G. Kechriotis and E. S. Manolakos, 'Training fully recurrent neural net-works with complex weights,' IEEE Trans. Circuits and Systems-fI: Ana-log and Digital Signat Processing, vol. 41, no. 3, pp. 235-238, March 1994 https://doi.org/10.1109/82.279210
  6. H. Jiang and K. S. Kwak, 'On neural networks adaptive equalizer fordigital communication,' J. Korean Institute Commun. Sciences, vol. 26,no. 10A, pp. 1639-1644, 2001
  7. H. Ping et at, 'Adaptive equalization technique application to time-variantfading channels,' ACTA ELECTRONICA SWICA, vol. 21, no. 4, PP. 85-89, Apr. 1993
  8. G. M. Georgiou and C. Koutsougeras, 'Complex domain backpropaga-tion,' IEEE Trans. Circuits and Syst.-II, vol. 39, pp. 330-334, May 1992 https://doi.org/10.1109/82.142037