Two Improved Wavelet Transform Domain LMS Sign Adaptive Filter Algorithms Against Impulsive Interferences

被引：1
作者：
Abadi, Mohammad Shams Esfand [1 ]
Mesgarani, Hamid [2 ]
Khademiyan, Seyed Mahmoud [2 ]
机构：
[1] Shahid Rajaee Teacher Training Univ, Fac Elect Engn, POB 16785-163, Tehran, Iran
[2] Shahid Rajaee Teacher Training Univ, Dept Appl Math, POB 16785-163, Tehran, Iran
来源：
CIRCUITS SYSTEMS AND SIGNAL PROCESSING | 2021年 / 40卷 / 02期
关键词：
Adaptive filters; Sign algorithm; Variable step size; Wavelet transform; Impulsive noise interference; STEP-SIZE NLMS;
D O I：
10.1007/s00034-020-01508-5
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In this paper, the improved wavelet transform domain least mean squares (IWTDLMS) adaptive algorithm is established. The IWTDLMS algorithm has a faster convergence speed than the conventional WTDLMS for colored input signals. Since the performances of WTDLMS and IWTDLMS are degraded in impulsive noise interference, the IWTDLMS sign algorithm (IWTDLMS-SA) is proposed. In comparison with IWTDLMS, the IWTDLMS-SA has lower computational complexity. In order to improve the performance of IWTDLMS-SA, the variable step-size IWTDLMS-SA (VSS-IWTDLMS-SA) is introduced. TheVSS-IWTDLMS-SA is derived by minimizing the l(1)-norm of the a posteriori error vector. To increase the tracking ability of the VSS-IWTDLMS-SA, the modified VSS-IWTDLMS-SA (MVSS-IWTDLMS-SA)is presented. The simulation results demonstrate that the proposed algorithms have a faster convergence rate and lower misadjustment than the conventional WTDLMS. The robustness feature of the IWTDLMS-SA, VSS-IWTDLMS-SA, and MVSS-IWTDLMS-SA against impulsive noises is also verified through several experiments in a system identification setup.
引用
收藏
页码：958 / 979
页数：22
相关论文
共 27 条
[1]   A low computational complexity normalized subband adaptive filter algorithm employing signed regressor of input signal [J].
Abadi, Mohammad Shams Esfand ;
Shafiee, Mohammad Saeed ;
Zalaghi, Mehrdad .
EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2018, :1-23
[2]   Diffusion normalized subband adaptive algorithm for distributed estimation employing signed regressor of input signal [J].
Abadi, Mohammad Shams Esfand ;
Shafiee, Mohammad Saeed .
DIGITAL SIGNAL PROCESSING, 2017, 70 :73-83
[3]   The wavelet transform-domain LMS adaptive filter employing dynamic selection of subband-coefficients [J].
Abadi, Mohammad Shams Esfand ;
Mesgarani, Hamid ;
Khademiyan, Seyed Mahmoud .
DIGITAL SIGNAL PROCESSING, 2017, 69 :94-105
[4]  
[Anonymous], 2013, ADAPTIVE FILTER THEO
[5]   The wavelet transform-domain LMS adaptive filter with partial subband-coefficient updating [J].
Attallah, S .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2006, 53 (01) :8-12
[6]   The wavelet transform-domain LMS algorithm: A more practical approach [J].
Attallah, S .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING, 2000, 47 (03) :209-213
[7]   A transform domain LMS adaptive filter with variable step-size [J].
Bilcu, RC ;
Kuosmanen, P ;
Egiazarian, K .
IEEE SIGNAL PROCESSING LETTERS, 2002, 9 (02) :51-53
[8]   A robust mixed-norm adaptive filter algorithm [J].
Chambers, J ;
Avlonitis, A .
IEEE SIGNAL PROCESSING LETTERS, 1997, 4 (02) :46-48
[9]  
Farhang-Boroujeny B., 2013, Adaptive Filters: Theory and Applications, V2nd
[10]   Performance analysis of the DCT-LMS adaptive filtering algorithm [J].
Kim, DI ;
De Wilde, P .
SIGNAL PROCESSING, 2000, 80 (08) :1629-1654
123