Steady-state performance analysis of the convex combination algorithm of frequency-domain adaptive filters

  • HOU Xin ,
  • LIN Bin ,
  • AN Yu-kun
Expand
  • (College of Information Engineering, Dalian Maritime University, Dalian 116026, China)

Received date: 2020-03-02

  Revised date: 2020-06-11

  Online published: 2020-06-11

Abstract

In order to further study the steady-state performance of the convex combination algorithm of frequency-domain adaptive filters (COSFDAF), a method to analyze the performance of the frequency-domain adaptive filtering (FDAF) was proposed. Different from the traditional method of using average weight error vector and state recursive equation of weight error covariance matrix to analyze the performance of adaptive algorithm, the closed analytic expression of steady state mean square error (MSE) of COSFADAF algorithm was obtained by deducing the energy conservation relationship of frequency domain adaptive filter and using separation hypothesis. The simulation results show that the simulation value of the steady MSE of COSFDAF algorithm matches the theoretical value well whether in the case of Gaussian noise input or correlated Gaussian noise input, which verifies the accuracy of the theoretical analysis.

Cite this article

HOU Xin , LIN Bin , AN Yu-kun . Steady-state performance analysis of the convex combination algorithm of frequency-domain adaptive filters[J]. Journal of Dalian Maritime University, 2020 , 46(3) : 124 -130 . DOI: 10.16411/j.cnki.issn1006-7736.2020.03.015

References

[1]马凯,王平波,武彩.一种基于正态分布曲线的变步长算法[J].计算机仿真, 2019, 36(09):295-299
[2]MA K, WANG P B, WU C.A variable-step-size LMS algorithm based on normal distribution curve[J].Computer Simulation, 2019, 36(09):295-299
[3] J Arenas-Garcia, A R Figueiras-Vidal, A. H. Sayed.Mean-square performance of a convex combination of two adaptive filters[J]. IEEE Signal Processing, 2006, 54(3):1078-1090
[4] E. R.Ferrara.Fast implementation of LMS adaptive filters[J].IEEE Transactions on Acoustics, Speech, and Signal Processing, 1980, 28(4):474-475
[5]S. Guan, Z. Li.Convex combination of overlap-save frequency-domain adaptive filters[J].arXiv preprint:1805.01307, 2018, , :-
[6]F. Yang, G. Enzner, J. Yang.. . , 2019, 67(7), 1785-1796.[J].IEEE Transactions on Signal Processing, 2019, 67(7):1785-1796
[7]B. Lin, R. He, X. Wang, B. Wang.The steady-state mean-square error analysis for least mean p-order algorithm[J].IEEE Signal Processing Letters, 2009, 16(3):176-179
[8]B. Farhang-Boroujeny, K. S. Chan.Analysis of the frequency-domain block LMS algorithm[J].2000 IEEE International Conference on Acoustics, Speech and Signal Processing, Istanbul, , :-
[9]K. Shi, X. Ma.A frequency domain step-size control method for LMS algorithm[J]. IEEE Signal Processing Letters, 2010, 17(2):125-128
[10] A.Fundamentals of Adaptive Filtering[J].Wiley, New York, 2008, :398-399
Outlines

/