A correntropy inspired variable step-size sign algorithm against impulsive noises

被引：21
作者：
Wang, Weihua [1 ]
Zhao, Jihong [1 ]
Qu, Hua [1 ]
Chen, Badong [1 ]
机构：
[1] Xi An Jiao Tong Univ, Sch Elect & Informat Engn, Xian 710049, Shaanxi, Peoples R China
来源：
SIGNAL PROCESSING | 2017年 / 141卷
基金：
中国国家自然科学基金; 国家高技术研究发展计划(863计划);
关键词：
Correntropy; Variable step-size; Sign algorithm; ADAPTIVE FILTERS; CONVERGENCE ANALYSIS; STEADY-STATE; TRACKING ANALYSES; CRITERION;
D O I：
10.1016/j.sigpro.2017.05.028
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：
The adaptive variable step-size technique is an effective way to improve the convergence rate of an adaptive filtering algorithm. However, for most existing variable step-size sign algorithm against impulsive noise, either the performance is not good enough, or the calculation is complex. In this paper, a correntropy inspired variable step-size method for sign algorithm is proposed. The new variable step-size method is computationally simple and robust to impulsive noises. Theoretical analysis and simulation results demonstrate that the proposed algorithm can achieve desirable performance with low computational complexity in presence of impulsive noises. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码：168 / 175
页数：8
相关论文
共 43 条
  • [1] A robust variable step-size LMS-type algorithm: Analysis and simulations
    Aboulnasr, T
    Mayyas, K
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1997, 45 (03) : 631 - 639
  • [2] Al-Naffouri T. Y., 2001, EURASIP Journal on Applied Signal Processing, V2001, P192, DOI 10.1155/S1110865701000348
  • [3] A new class of gradient adaptive step-size LMS algorithms
    Ang, WP
    Farhang-Boroujeny, B
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2001, 49 (04) : 805 - 810
  • [4] [Anonymous], 1986, DENSITY ESTIMATION S, DOI [DOI 10.2307/2347507, 10.2307/2347507]
  • [5] Performance Analysis of the Dual Sign Algorithm for Additive Contaminated-Gaussian Noise
    Bang, Seung Chan
    Ann, Souguil
    Song, Iickho
    [J]. IEEE SIGNAL PROCESSING LETTERS, 1994, 1 (12) : 196 - 198
  • [6] Maximum correntropy Kalman filter
    Chen, Badong
    Liu, Xi
    Zhao, Haiquan
    Principe, Jose C.
    [J]. AUTOMATICA, 2017, 76 : 70 - 77
  • [7] Generalized Correntropy for Robust Adaptive Filtering
    Chen, Badong
    Xing, Lei
    Zhao, Haiquan
    Zheng, Nanning
    Principe, Jose C.
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2016, 64 (13) : 3376 - 3387
  • [8] Convergence of a Fixed-Point Algorithm under Maximum Correntropy Criterion
    Chen, Badong
    Wang, Jianji
    Zhao, Haiquan
    Zheng, Nanning
    Principe, Jose C.
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2015, 22 (10) : 1723 - 1727
  • [9] Steady-State Mean-Square Error Analysis for Adaptive Filtering under the Maximum Correntropy Criterion
    Chen, Badong
    Xing, Lei
    Liang, Junli
    Zheng, Nanning
    Principe, Jose C.
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2014, 21 (07) : 880 - 884
  • [10] Transient and tracking performance bounds of the sign-sign algorithm
    Eweda, E
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1999, 47 (08) : 2200 - 2210
12345