DOI QR코드

DOI QR Code

기울기 평균 벡터를 사용한 가변 스텝 최소 평균 사승을 사용한 음향 채널 추정기

An acoustic channel estimation using least mean fourth with an average gradient vector and a self-adjusted step size

  • 임준석 (세종대학교 전자정보통신공학과)
  • Lim, Jun-Seok (Department of Electrical Engineering, Sejong University)
  • 투고 : 2018.03.09
  • 심사 : 2018.05.30
  • 발행 : 2018.05.31

초록

LMF(Least Mean Fourth) 알고리즘은 특히 비정규 잡음 상황에서 안정성 및 빠른 수렴성을 나타낼 뿐만아니라 추정 오차도 낮은 것으로 잘 알려져 있다. 최근 LMS (Least Mean Square) 알고리즘 분야에서는 가변 스텝 크기를 적용한 알고리즘들에 대한 관심이 증대되어 왔다. 그 이유는 가변 스텝 크기 LMS가 다양한 환경에서 고정 스텝 크기 LMS보다 우수한 결과를 내기 때문이다. 본 논문에선 LMF에 대한 가변 스텝 크기의 한 방법으로 기울기 평균 벡터를 사용한 가변 스텝 크기를 사용하는 LMF 알고리즘을 제안한다. 제안된 방법은 가변 스텝 크기 LMS와 마찬가지로 고정 스텝 크기 LMF보다 우수할 것이 예상된다. 본 논문은 그 우수성을 시불변 채널과 시변 채널 각각의 채널 환경하에서 시뮬레이션을 통하여 보인다.

The LMF (Least Mean Fourth) algorithm is well known for its fast convergence and low steady-state error especially in non-Gaussian noise environments. Recently, there has been increasing interest in the LMS (Least Mean Square) algorithms with self-adjusted step size. It is because the self-adjusted step-size LMS algorithms have shown to outperform the conventional fixed step-size LMS in the various situations. In this paper, a self-adjusted step-size LMF algorithm is proposed, which adopts an averaged gradient based step size as a self-adjusted step size. It is expected that the proposed algorithm also outperforms the conventional fixed step-size LMF. The superiority of the proposed algorithm is confirmed by the simulations in the time invariant and time variant channels.

키워드

참고문헌

  1. B. Farhang-Boroujeny, Adaptive Filters: Theory and Applications, 2nd Edition (John Wiley & Sons, Inc. Hoboken, NJ, 2013), pp. 62.
  2. A. H. Sayed, Adaptive Filters (IEEE Press, Wiley-Inter science, New York, 2008), pp.167.
  3. E. Walach and B. Widrow, "The least mean fourth (LMF) adaptive algorithm and its family," IEEE Trans. IT. 30, 275-283 (1984). https://doi.org/10.1109/TIT.1984.1056886
  4. P. I. Hubscher and J. C. Bermudez, "An improved statistical analysis of the least mean fourth (LMF) adaptive algorithm," IEEE Trans. SP. 51, 664-671 (2003).
  5. B. Farhang-Boroujeny, "Varaible-step-size LMS algo- rithm: new developments and experiments," IEE Proc. -Vis. Image Signal Process. 141, 311-317 (1994). https://doi.org/10.1049/ip-vis:19941425
  6. R. H. Kwong and E. W. Johnston, "A variable step size LMS algorithm," IEEE Trans. SP. 40, 1633-1642 (1992). https://doi.org/10.1109/78.143435
  7. J. S. Lim, "A constant modulus algorithm based on an orthogonal projection" (in Korean), J. Acoust. Soc. Kr. 28, 640-645 (2009).
  8. J. S. Lim and Y. K. Pyeon, "A variable step sized constant modulus algorithm based on an averaged gradient," KICS. 35, 79-82 (2010).
  9. S. M. Asad, A. Zerguine, and M. Moinuddin, "On the convergence analysis of a variable step-size LMF algorithm of the quotient form," Proc. ICASSP 2010, 3722-3725 (2010).
  10. V. Malenovsky, Z. Smekal, and I. Koula, "Optimal step-size LMS algorithm using exponentially averaged gradient vector," Proc. EUROCON 2005, 1554-1557 (2005).