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

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

The Improvement of Convergence Characteristic using the New RLS Algorithm in Recycling Buffer Structures

  • Kim, Gwang-Jun (Dept.of Computer Engineering, Yosu National University) ;
  • Kim, Chun-Suck (Dept.of Electronics Communication Engineering, Yosu National University)
  • Published : 2003.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

We extend the sue of the method of least square to develop a recursive algorithm for the design of adaptive transversal filters such that, given the least-square estimate of this vector of the filter at iteration n-l, we may compute the updated estimate of this vector at iteration n upon the arrival of new data. We begin the development of the RLS algorithm by reviewing some basic relations that pertain to the method of least squares. Then, by exploiting a relation in matrix algebra known as the matrix inversion lemma, we develop the RLS algorithm. An important feature of the RLS algorithm is that it utilizes information contained in the input data, extending back to the instant of time when the algorithm is initiated. In this paper, we propose new tap weight updated RLS algorithm in adaptive transversal filter with data-recycling buffer structure. We prove that convergence speed of learning curve of RLS algorithm with data-recycling buffer is faster than it of exiting RLS algorithm to mean square error versus iteration number. Also the resulting rate of convergence is typically an order of magnitude faster than the simple LMS algorithm. We show that the number of desired sample is portion to increase to converge the specified value from the three dimension simulation result of mean square error according to the degree of channel amplitude distortion and data-recycle buffer number. This improvement of convergence character in performance, is achieved at the B times of convergence speed of mean square error increase in data recycle buffer number with new proposed RLS algorithm.

적응 횡단선 필터에서 수렴 속도의 개선을 위해 기존의 최소 평균 자승 알고리즘을 확장한 반복적 최소 자승 알고리즘의 탭 가중치 갱신 메커니즘에 재순환 데이터 버퍼를 이용함으로서 수렴특성을 개선시키는 효율적인 기법을 제시하였다. 본 논문은 기존의 적응 횡단선 필터에 데이터 재순환 버퍼 구조를 제안하여 새로운 RLS 탭 가중치 갱신 알고리즘을 유도하여 조화 평균 학습 곡선의 평균 자승 에러 값에 대한 반복수에 대해서 데이터 재순환 버퍼를 사용한 학습 곡선의 수렴 속도가 버퍼가 없는 경우의 재순환 버퍼 RLS 알고리즘의 수렴 속도보다 비례하여 빠르게 수렴한다는 것을 수학적인 연산을 통해 증명하였다. 채널 진폭의 왜곡의 정도와 재순환 데이터 버퍼 수에 따른 평균 자승 에러에 대한 삼차원 시뮬레이션 결과로부터 고유치 확산이 증가함에 따라 특정 값에 수렴하기 위한 요구된 샘플의 반복수가 비례하여 증가하였으며, 재순환 데이터 버퍼 수 B가 증가함에 따라 요구된 샘플의 반복수가 B배만큼 감소함으로서 제안된 구조에서 RLS 가중치 갱신 알고리즘의 수렴특성이 개선됨을 입증하였다.

Keywords

References

  1. M.G Bellanger, 'Computational complexity and accuracy issues in fast least squares algorithms adaptive filtering', Proc. IEEE ISCAS, pp.2635-2639, Finland, 1988
  2. J.M. Cioffi, 'Limited-precision effects in adaptive filtering', IEEE Trans. CAS. VOL CAS-34, pp.821-833, July, 1987
  3. J.M. Cioffi, 'The fast Householder filters RLS adaptive filter', Proc. IEEE ICASSP, pp.1619-1622, Albuquerque, April 1990
  4. W.M. Gentleman and H.T. Kung, ''Matrix triangularization by systolic arrays", Proc. SPIE, Vol. 298, Real Time Signal Processing IV, pp.298, 1981
  5. G. H. Golub and C. F. Van Loan, Matrix Computations, 2nd ed., Baltimore, MD: Johns Hopkins University Press, 1989
  6. S. Haykin, Adaptive Filter Theory, Prentice HallInc., 1986
  7. D.E Heller and I.C.F. Ipsen, 'Systolic networks for orthogonal decomposition", SIAM J. Sci Stat. Comput. Vol 4, pp.261-269, June, 1983 https://doi.org/10.1137/0904020
  8. L. Johnsson, ': A computational array for the QR-method,' 1982 Conference on Advanced Research in VLSI, M.I.T., pp.123-129
  9. Jiangnan Chen, Roland Prierer, 'An Irequality by Which to Adjust the LMS Algorithm Step-Size", IEEE Trans. Commun. Vol.43, No..2/3/4, pp.1477-1483, Feb./Mar./Apr. 1995 https://doi.org/10.1109/26.380197
  10. S. Kalson and K. Yao, 'Systolic array processing for order and time recursive generalized least-squares estimation, ''Proc, SPIE, Vol, 564, Real Time Signal Processing VIII pp.28-38, 1985
  11. Bergmans, J.W.M.,''Tracking capabilities of the LMS adaptive filter in the presence of gain variations,' IEEE Trans. Acoust. Speech Signal Process. vol.38, pp. 712-714, 1990 https://doi.org/10.1109/29.52711
  12. H.T.Kung and M.S.Lam, 'Wafer-scale integration and two-level pipelined implementation of systolic array', J.Parallel Distrib. Comput., vol.1, pp.32-63, 1984 https://doi.org/10.1016/0743-7315(84)90010-8