DOI QR코드

DOI QR Code

Two regularization constant selection methods for recursive least squares algorithm with convex regularization and their performance comparison in the sparse acoustic communication channel estimation

볼록 규준화 RLS의 규준화 상수를 정하기 위한 두 가지 방법과 희소성 음향 통신 채널 추정 성능 비교

  • 임준석 (세종대학교 전자정보통신공학과) ;
  • 홍우영 (세종대학교 국방시스템공학과)
  • Received : 2016.07.18
  • Accepted : 2016.09.02
  • Published : 2016.09.30

Abstract

We develop two methods to select a constant in the RLS (Recursive Least Squares) with the convex regularization. The RLS with the convex regularization was proposed by Eksioglu and Tanc in order to estimate the sparse acoustic channel. However the algorithm uses the regularization constant which needs the information about the true channel response for the best performance. In this paper, we propose two methods to select the regularization constant which don't need the information about the true channel response. We show that the estimation performance using the proposed methods is comparable with the Eksioglu and Tanc's algorithm.

본 논문은 볼록 규준화 RLS(Recursive Least Squares)에 쓰이는 규준화를 위한 상수를 정하는 법을 제안한다. Eksioglu와 Tanc는 희소성 음향 채널 추정을 위해서 볼록 규준화 RLS 알고리즘을 구현하였다. 그러나 이 알고리즘은 더 좋은 추정 성능을 위해서 채널의 참 임펄스 응답 정보가 사용된다. 본 논문에서는 이 같은 참 임펄스 응답 정보가 필요 없는 규준화 상수를 위한 두 가지 선정법을 제안한다. 그리고 제안한 방법을 사용했을 때 Eksioglu와 Tanc의 방법에 필적한 추정 성능을 유지함을 보인다.

Keywords

References

  1. A. H. Sayed, Fundamentals of Adaptive Filtering (Wiley, NewYork, 2003), pp. 212-280.
  2. J. S. Lim, "A constant modulus algorithm based on an orthogonal projection" (in Korean), J. Acoust. Soc. Kr. 28, 640-645 (2009).
  3. J. S. Lim, "A constant modulus algorithm for blind acoustic communication channel equalization with improved convergence using switching between projected CMA and algebraic step size CMA" (in Korean), J. Acoust. Soc. Kr. 35, 55-62 (2016). https://doi.org/10.7776/ASK.2016.35.1.055
  4. M. Kocic, D. Brady, and M. Stojanovic, "Sparse equalization for real-time digital underwater acoustic communications," Proc. OCEANS'95, 1417-1422 (1995).
  5. W. F. Schreiber, "Advanced television systems for terrestrial broadcasting: Some problems and some proposed solutions," Proc. IEEE, 83, 958-981 (1995). https://doi.org/10.1109/5.387095
  6. W. Bajwa, J. Haupt, G. Raz, and R. Nowak, "Compressed channel sensing," in Proc. of CISS, 5-10 (2008).
  7. E. J. Candes and M. B. Wakin, "An introduction to compressive sampling," IEEE Signal Process. Mag. 25, 21-30 (2008). https://doi.org/10.1109/MSP.2007.914731
  8. C. R. Berger, Z. Wang, J. Huang, and S. Zhou, "Application of compressive sensing to sparse channel estimation," IEEE Commun. Mag. 48, 164-174 (2010).
  9. Y. Gu, J. Jin, and S. Mei, "$l_0$ norm constraint LMS algorithm for sparse system identification," IEEE Signal Process. Lett. 16, 774-777 (2009). https://doi.org/10.1109/LSP.2009.2024736
  10. Y. Chen, Y. Gu, and A. O. Hero, "Sparse LMS for system identification," in Proc. ICASSP, 3125-3128 (2009).
  11. B. Babadi, N. Kalouptsidis, and V. Tarokh, "SPARLS: The sparse RLS algorithm," IEEE Trans. Signal Process. 58, 4013-4025 (2010). https://doi.org/10.1109/TSP.2010.2048103
  12. E. M. Eksioglu, "Sparsity regularized RLS adaptive filtering," IET Signal Processing Journal 5, 480-487 (2011). https://doi.org/10.1049/iet-spr.2010.0083
  13. E. M. Eksioglu and A. K. Tanc, "RLS Algorithm with Convex Regularization," IEEE Signal Processing Lett. 18, 470-473 (2011). https://doi.org/10.1109/LSP.2011.2159373
  14. M. R. Petraglia and D. B. Haddad, "New adaptive algorithms for identification of sparse impulse responses - Analysis and comparisons," in Proc. of Wireless Communication Systems, 384-388 (2010).