Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Training Algorithm of Recurrent Neural Network Using a Sigma Point for Equalization of Channels

시그마 포인트를 이용한 채널 등화용 순환신경망 훈련 알고리즘

  • 권오신 (군산대학교 전자정보공학부)
  • Published : 2007.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

A recurrent neural network has been frequently used in equalizing the channel for fast communication systems. The existing techniques, however, have mainly dealt with time-invariant chamois. The modern environments of communication systems such as mobile ones have the time-varying feature due to fading. In this paper, powerful decision feedback - recurrent neural network is used as channel equalizer for nonlinear and time-varying system, and two kinds of algorithms, such as extended Kalman filter (EKF) and sigma-point Kalman filter (SPKF), are proposed; EKF is for fast convergence and good tracing function, and SPKF for overcoming the problems which can be developed during the process of first linearization for nonlinear system EKF.

고속 통신 시스템의 채널 등화에 순환 신경망이 자주 이용되고 있다. 기존의 등화방법은 대부분 시불변 채널을 주로 다루었다. 그러나 이동통신과 같은 현대의 통신환경은 페이딩으로 인하여 시변특성을 갖는다. 본 논문에서는 비선형 시변 시스템에 적용하여 성능이 우수한 결정 피드백 순환신경망을 채널등화기로 이용하며, 또한 채널 등화에 빠른 수렴속도와 우수한 추적성능을 지니는 확장된 칼만필터와 시그마 포인트 칼만필터를 이용한 두 종류의 훈련 알고리즘을 제안한다. 확장된 칼만필터를 이용한 경우 비선형 시스템의 1차 선형화 과정에서 커다란 오차를 유발할 수도 있으며, 이에 대한 대안으로 시그마 포인트 칼만필터를 이용하여 이러한 문제점을 극복할 수 있다.

Keywords

References

  1. S. Qureshi, 'Adaptive equalization,' Proceedings of the IEEE, Vol. 73,no.9, pp. 1349-1387, 1985 https://doi.org/10.1109/PROC.1985.13298
  2. S. Chen, B. Mulgrew, and S. Mclaughlin, 'Adaptive Bayesian equalizer with decision feedback,' IEEE Transactions on Signal Processing, Vol. 41, pp. 2918-2927, September 1993 https://doi.org/10.1109/78.236513
  3. S. Haykin,'Neural Networks: a Comprehensive Foundation, 2nd Ed. Upper Saddle River, NJ: Prentice Hall, 1999
  4. J. Elman, 'Finding structure in time,' Congnitive Science, Vol. 14,pp. 179-211, 1990 https://doi.org/10.1016/0364-0213(90)90002-E
  5. S. Haykin, Adaptive Filter Theory, 4th Ed. Upper Saddle River, NJ: Prentice Hall, 2002
  6. S. J. Julier and J. K. Uhlmann, 'A new extension of the Kalman filter to nonlinear systems,' in Proceeding of AeroSence: The 11th International Symposium on Aerospace/Defence Sensing, Simulation and Controls, 1997
  7. H.S. Hong,C. G. Park, J.G. .Lee, 'An Extended Kalman Filter Robust to Linearization Error,' Journal of Cont. and System Eng.,Vol. 12, No.2, pp.93-100, February 2006 https://doi.org/10.5302/J.ICROS.2006.12.2.093
  8. S. Y. Cho,W.S. CHoi, 'Improving the Performance of DR/GPS Integrated System for Land Navigation Using Sigma Point Based RHKF Filter,' Journal of Cont. and System Eng., Vol. 12, No.2, pp. 174-185, February 2006 https://doi.org/10.5302/J.ICROS.2006.12.2.174
  9. J. Choi, M. B. Bouchard, T. H. Yeap, O. Kwon, 'A Derivative-Free Kalman Filter for Parameter Estimation of Recurrent Neural Networks and Its Applications to Nonlinear Channel Equalization,' Eng. of Intelligent Systems EIS' 2004, Portugal, March, 2004
  10. J. Choi, O. Kwon, 'Equalization of Time-varying Channels using a Recurrent Network Trained with Kalman Filters,' Journal of Cont. and System Eng., Vol. 9, No.11,pp. 917-924, 2003 https://doi.org/10.5302/J.ICROS.2003.9.11.917
  11. Rudolph van der Merwe & Eric Wan, 'Sigma-Point Kalman Filters for Probabilistic Inferencein Dynamic State-Space Models,' Journal of Oregon Health & Science University, USA, 2004