Block sparse reweighted zero-attracting normalised least mean square algorithm for system identification

Block sparse reweighted zero-attracting normalised least mean square algorithm for system identification
复制标题

用于系统辨识的块稀疏重加权零吸引归一化最小均方算法

DOI:
10.1049/el.2017.1115
复制
发表时间:
2017-06
影响因子:
1.1
通讯作者:
Jun Yang
Jun Yang
中科院分区:
工程技术4区
文献类型:
--
作者:
Zhenhai Yan;Feiran Yang;Jun Yang

文献摘要

参考文献

相似文献

为了提高块稀疏系统的辨识性能,本文提出了一种块稀疏重加权零吸引归一化最小均方算法(BS-RZA-NLMS)。该算法是通过对NLMS的成本函数施加块稀疏约束而得到的,NLMS的成本函数是具有相等块分区大小的自适应抽头权重的对数和惩罚。BS-RZA-NLMS的收敛行为进行了分析的零吸引力和块划分。仿真结果表明了该算法在块稀疏系统辨识中的性能优势。
To improve the performance for identifying the block sparse system, a block sparse reweighted zero-attracting normalised least mean square algorithm (NLMS) (BS-RZA-NLMS) is proposed in this Letter. The proposed algorithm is derived by applying block sparsity constraint on the cost function of the NLMS, which is a log-sum penalty of adaptive tap weights with equal block partition sizes. The convergence behaviour of the BS-RZA-NLMS is analysed in terms of the zero attraction and block partition. Simulation results demonstrate the performance advantage of the proposed algorithm in the context of block sparse system identification.
DOI: 10.1109/lsp.2009.2024736
发表时间: 2009-09-01
影响因子: 3.9
作者:
Gu, Yuantao;Jin, Jian;Mei, Shunliang
通讯作者: Mei, Shunliang
DOI: 10.1109/icassp.2011.5947082
发表时间: 2011-05
期刊: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子: --
作者:
O. Taheri;S. Vorobyov
通讯作者: O. Taheri;S. Vorobyov
稀疏系统辨识的非均匀范数约束LMS算法
DOI: 10.1109/lcomm.2013.011113.121586
发表时间: 2013-01
期刊: IEEE Communications Letters
影响因子: --
作者:
Wu, F. Y.;Tong, F.
通讯作者: Tong, F.
DOI: 10.1109/5.387095
发表时间: 1995-06
期刊: Proc. IEEE
影响因子: --
作者:
W. Schreiber
通讯作者: W. Schreiber
用于多聚类系统识别的块稀疏性自适应滤波器
DOI: 10.1109/tsp.2015.2453133
发表时间: 2015-10-15
影响因子: 5.4
作者:
Jiang, Shuyang;Gu, Yuantao
通讯作者: Gu, Yuantao