user

L1-norm constrained normalized subband adaptive filter algorithm with variable norm-bound parameter and improved version

被引：0
|
作者：
Shi, Long [1 ,2 ]
Zhao, Haiquan [1 ,2 ]
机构：
[1] Southwest Jiaotong Univ, Key Lab Magnet Suspens Technol & Maglev Vehicle, Minist Educ, Chengdu 610031, Peoples R China
[2] Southwest Jiaotong Univ, Sch Elect Engn, Chengdu 610031, Peoples R China
来源：
SIGNAL IMAGE AND VIDEO PROCESSING | 2017年 / 11卷 / 05期
基金：
美国国家科学基金会;
关键词：
L-1-norm; Subband; Variable norm-bound parameter; Lagrange multiplier; A posterior error; STEP-SIZE; NLMS; CONVERGENCE;
D O I：
10.1007/s11760-016-1033-z
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 L-1-norm constrained normalized subband adaptive filter with variable norm-bound parameter (L(1)NCNSAF-V) algorithm and its variable step size version VSS-L(1)NCNSAF-V are proposed in this paper, which are more superior to some existing algorithms in the sparse system. The proposed L(1)NCNSAF-V is derived by using the Lagrange multiplier method, and the VSS-L(1)NCNSAF-V is obtained by minimizing the statistical square of the Euclidean norm of the noise-free subband a posterior error vector. The simulation results demonstrate that the proposed algorithms achieve good performance.
引用
收藏
页码：865 / 871
页数：7
相关论文
共 50 条
12345