The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

CPSN (complex Pi-sigma network) equalizer for the compensation of nonlinearities in satellite communication channels

위성 통신 채널의 비선형성 보상을 위한 CPSN (Complex Pi-sigma Network) 신경회로망 등화기

  • Published : 1997.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

Digital satellite communication channels have nonlinearities with memory due to saturation characteristics of traveling wave tube amplifier in the satellite and transmitter/receiver linear filters. In this paper, we propose a network structure and a learning algorithm for complex pi-sigma network (CPSK) and exploit CPSN in the problem of equalization of nonlinear satellite channels. The proposed CPSN is a complex-valued extension of real-valued pi-sigma network that is a higher-order feedforward network with fast learning while greatly reducing network complexity by utilizing efficient form of polynomials for many input variables. The performance of the proposed CPSN is demonstrated by computer simulations on the equalization of complex-valued QPSK input symbols distorted by a nonlinear channel modeled as a Volterra series and additive noise. The results indicate that the CPSN shows good equalization performance, fast convergence, and less computations as compared to conventional higher-order models such as Volterra filters.

디지털 위성 통신 채널은 중계 위성 내에서 사용되는 고출력 증폭기인 traveling wave tube의 비선형 포화 특성과 송신단/수신단 선형 필터들의 영향으로 메모리를 갖는 비선형 특성을 나타낸다. 본 논문에서는 여러 입력 변수들에 대한 효율적인 형태의 다항식을 사용하므로써 빠른 수려, 적은 계산량 등과 같은 장점을 갖는 고차(higher-order) 신경회로망인 pi-sigma network을 복소수 영역으로 확장한 complex pi-sigma network (CPSN)을 제안하고, 이를 이용하여 디지털 위성 통신 채널의 비선형을 보상하는 등화기를 설계하였다. 제안된 CPSN은 Volterra 급수로 모델링된 비선형 채널과 잡음에 의해 왜곡된 QPSK 복소 입력 심벌들에 대한 동화에 이용되었으며, 컴퓨터 모의실험 결과 우수한 등화 성능 및 기존의 Volterra 필터와 같은 고차 모델에 비교해 매우 빠른 수렴 특성 및 적은 계산량을 가짐을 확인하였다.

Keywords

References

  1. IEEE Trans. Commun. v.9 no.11 Frequency-independent and frequence-dependent nonlinear models of TWT amplifier A. A. M. Saleh
  2. IEEE Jour. Sci. Arewas in Commun. v.1 no.1 Nonlineat equalization of digital satellite channels S. Benedetto;E. Biglieri
  3. IEEE Jour. Sci. Areas in Commun. v.6 no.1 Analysis and cpmpensation of nonlinearities in digital transmission systems E. Biglieri;S. Barberis;M. Catena
  4. Proc. IEEE Int'l Conf. Commun. v.1 Performance of adaptive Volterra equalizers on nonlinear satellite channels A. Gutierrez;W. E. Ryan
  5. Proc. IEEE Int'l Conf. Neural Networks v.6 Utilization of neural network signal processing in the design of a predistoter for a nonlinear telecommunication channel C. Eun;E. J. Powers
  6. 한국통신학회눈문지 v.21 no.9 Complex radial basis function metwork을 이용한 비선형 디지털 위성 통신 채널의 등화 신요한;윤병문;임영선
  7. Int'l Jor. Neural Syst. v.3 no.4 Efficient higher-order neural networks for classification and function approximation J. Ghosh;Y. Shin
  8. Neural Networks-A Comprehensive Foundation S. Haykin
  9. The Volterra and Wiener Theory of Nonlinear System M. Schetzen
  10. Digital Communications-Fundamentals and Applications B. Skar
  11. Applied Optics v.26 Learning , invariance and generalization in a high-order neural network C. L. Giles;T. Maxwell
  12. Parallet Distributed Processing v.1 J. McClellan;D. Rumelhart
  13. Adaptive Signal Processing B. Widrow;S. D. Stearns
  14. IEEE Trans. Neural Networks v.6 Ridge polynomial networks Y. Shin;J. Ghosh
  15. Principles of Mathematical Analysis (3rd Ed.) W. Rudin
  16. IEEE Jour. Sci. Areas in Commun. v.13 Predictive dynamic bandwidth alocation for effcienttransp[ort of real-time VBR video ATM S. Chong;S.-Q. Li;J. Ghosh
  17. Proc. IEEE Int'l Conf. Neural Netwoks v.1 Time optimal control using pi-sigma networks K. Iwata;J. Gosh;Y. Shin
  18. Intell. Eng. Syst. through Artifical Neural Networks Relaization of Boolean functions using binary pi-siga networks Y. Shin;J. Ghosh;D. Samani;C. H. Dagli(ed.);R. T. Kumara(ed.);Y. C. Shin(ed.)
  19. Intell. Eng. Syst. through Artificial Neural Networks 2 Computationally effcient invarient pattern classification with higher-order pi-sigma networks Y. S.hin;J. Ghosh;D. Samani;C. H. Dagli(ed.);L. I. Burke(ed.);Y. C. Shin(ed.)
  20. Proc. Int'l Conf. Acoustics. Speech and Signal Proc. v.1 Pi-sigma and hidden control based self-structuring models for tex-independent speaker recognition H. B. D. Sorensen;U. Hartmann
  21. Proc. IEEE Int'l Conf. Neural Networks v.5 Neuroaccuracy compensator for industrial robots X. L. Zhong;J. M. Lewis;H. Rea
  22. Proc. World Congress on Neural Networks v.2 Higher order neural networks with wavelet preprocessing for face recognition R. Foltyniewicz;A. Cichocki