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

  • 제32권8C호
  • /
  • Pages.782-787
  • /
  • 2007
  • /
  • 1226-4717(pISSN)
  • /
  • 2287-3880(eISSN)
한국통신학회 (The Korean Institute of Commucations and Information Sciences)
권호 표지

정규화된 D-QR-RLS 알고리즘의 특성 분석(I)

Characteristic Analysis of Normalized D-QR-RLS Algorithm(I)

  • 안봉만 (전북대학교 Next 사업단) ;
  • 황지원 (익산대학 컴퓨터과학과) ;
  • 조주필 (군산대학교 전자정보공학부)
  • 발행 : 2007.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문은 Givens 회전시킨 입력벡터들을 이용하여 오차 제곱을 최소화하는 고속 알고리즘을 정규화하는 D(Diagonal)-QR-RLS 알고리즘을 제안하고 특징을 해석한다. 이 알고리즘은 계산량이 O(N)이다. 또한 직접적으로 TDL 필터의 계수를 구할 수 있는 장점이 있다. 그리고 제안된 정규화 알고리즘은 NLMS 알고리즘과 유사한 형태를 취하지만 NLMS 알고리즘 보다 우수한 수렴특성을 가지고 있음을 컴퓨터 모의실험을 통하여 확인하였다.

This paper presents the D(Diagonal)-QR-RLS algorithm which normalizes the fast algorithm minimizes the MSE by using Givens rotated inputs and analyzes its characteristic. This proposed one has computational complexity of O(N) and the merit that it obtains the coefficients of TDL filter directly. Although this proposed normalized algorithm has the similar form to NLMS algorithm, we can see that D-QR-RLS has superior convergence characteristic to NLMS by computer simulation.

키워드

참고문헌

  1. Danilo P. Mandic, 'A Generalized Normalized Gradient Descent Algorithm,' IEEE. Signal Processing Letters, vol. 11, No. 2, pp.115-118, Feb. 2004 https://doi.org/10.1109/LSP.2003.821649
  2. V. J. Mathews and Z. Xie, 'A stochastic gradient adaptive filter with gradient adaptive step size,' IEEE Trans. Signal Processing, vol. 41, pp.2075-2087, June 1993 https://doi.org/10.1109/78.218137
  3. W. P. Ang and B. Farhang-Boroujeny, 'A new class of gradient adatpve step-size LMS algorithms,' IEEE Trans. Signal Processing, vol. 49, pp.805-810, Apr. 2001 https://doi.org/10.1109/78.912925
  4. M. T. Morf, T. Kailath and L. Ljung, 'Fast algorithm for recursive identification,' in proc., 1976 Congress Decision Control, Clearwater Beach, FL, 1976, pp.916-921
  5. J. M. Cioffi and T. Kailath, 'Fast RLS Transversal filters for adaptive filtering,' IEEE Trans., Acoust., Speech, Signal Processing, vol. ASSP-32, pp. 304-337, 1984
  6. W. M. Gentleman and H. T. Kung, 'Matrix triangularization by systolic array,' in Proc. SPIE int. Soc., Opt. Eng., vol. 298. pp.298-303, 1981
  7. J. G. McWhiter, 'Recursive least squares minimization using a systolic array,' in Proc. SPIE int. Soc., Opt. Eng., vol. 431. pp.105-112, 1983
  8. J. M. Cioffi, 'A fast adaptive ROTOR's RLS algorithms,' IEEE Trans., Acoust., Speech, Signal Processing, vol. 38, pp.631-653, 1990 https://doi.org/10.1109/29.52704
  9. Z. S. Liu, 'QR methods of O(N) complexity in adaptive parameter estimation,' IEEE Trans, Signal Processing, vol. 43, pp.720-729, 1995 https://doi.org/10.1109/78.370626
  10. Z. S. Liu and J. Li, 'A QR-based least mean squares algorithm for adaptive parameter estimation,' IEEE Trans. Circuits Syst., vol. 45, pp.321-329, Mar. 1998 https://doi.org/10.1109/82.664238
  11. A. A. Rontogiannis and S. Theodoridis, 'New fast QR Decomposition Least Squares Adaptive Algorithms,' IEEE Transaction on Signal Processing, vol. 46, no. 8, pp.2113-2121, August 1998 https://doi.org/10.1109/78.705419
  12. J. A. Apolinario Jr. and P. S. R. Diniz, 'A new fast QR algorithm based on a priori errors,' IEEE Signal Processing Letters, vol. 4, no. 11, pp.307-309, November 1997 https://doi.org/10.1109/97.641395
  13. 안봉만, 황지원, 조수필, '단위 벡터를 이용한 고속 적응 계수 예측 알고리즘.', 한국통신학회 심사중