Satellite communication Equalizer Using Complex Bilinear Recurrent Neural Network

C-BLRNN을 이용한 위성채널 등화기

  • 박동철 (명지대학교 정보제어공학과-정보통신교육센터) ;
  • 정태균 (명지대학교 정보제어공학과)
  • Published : 2000.03.01

Abstract

Equalization of satellite communication using Complex-Bilinear Recurrent Neural Network(C-BLRNN) is proposed in this pater. Since the BLRNN is based on the bilinear polynomial and it has been more effectively used in modeling highly nonlinear systems with time-series characteristics than multi-layer perception type neural networks(MLPNN) , it can be applied to satellite equalizer. the proposed C-BLRNN based equalizer for M-PSK with a channel model is compared with Volterra filter Equalizer, DFE, and conventional Complex MLPNN Equlizer. The results show that the proposed C-BLRNN based equalizer gives very favorable results in both of MSE and BER criteria over other equalizers.

Keywords

References

  1. Digital Transmission Theory S. Benedetto;E. Biglieri;V. Castellani
  2. IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS v.13 no.2 Adaptive Decision Feedback Equalization for Digital Satellite Channels Using Multilayer Neural Networks P. Chang;B. Wang
  3. Proc. IEEE Int'l Conf. Commun. v.1 Performance of adaptive Volterra equalizers on nonlinear satellite channels A. Gutierrez;W. Ryans
  4. Conf. Record of GLOBECOM'93 Nonlinear Channel Equalization in Digital Satellite Systems C. Tseing;E. Powers
  5. Proc. ICASSP 91 Nonlinear Satellite Radio Links Equalizer Using Blind Neural Networks N. Benvenuto(et al.)
  6. IEEE Tr. on Neural Networks v.5 no.2 Training Recurrent Networks : Why and How? An Illustration in Dynamical Process Modeling O. Nerrand(et al.)
  7. IEEE signal processing magazine Adaptive Polynomial Filters V. Mathews
  8. IEEE Trans. on Communications v.COM29 no.11 Frequency-Independent and Frequency-Dependent Nonlinear Models of TWT Amplifiers A. Saleh
  9. IEEE Trans. Aerosp, Electron Syst, AES-15 Modeling and evaluation of nonlinear satellite links - A Volterra series approach S. Benedetto(et al.)
  10. IEEE Trans. J. Select. Areas Commun. v.SAC-1 Nonlinear equalization of digital satellite channels S. Benedetto;E. Biglieri
  11. Proc. of ICNN'94 BiLinear Recurrent Neural Network Dong C. Park;Y. Zhu
  12. IEEE Tr. on Sys., Man, and Cybrn v.10 no.10 An Overview of Bilinear System Theory and Applications M. Mohler;W. Kolodzij
  13. IEEE Trans. on Signal Processing v.40 no.4 On the complex backpropagation algorithm N. Benvenuto;F. Piazza