Robust Shrinkage Affine-Projection Sign Adaptive-Filtering Algorithms for Impulsive Noise Environments
Robust Shrinkage Affine-Projection Sign Adaptive-Filtering Algorithms for Impulsive Noise Environments
复制标题
DOI：
10.1109/tsp.2014.2324997
复制
发表时间：
2014-07
影响因子：
5.4
通讯作者：
Md. Zulfiquar Ali Bhotto;M. Ahmad;M.N.S. Swamy
中科院分区：
文献类型：
--
作者：
Md. Zulfiquar Ali Bhotto;M. Ahmad;M.N.S. Swamy
提出了两种鲁棒仿射投影符号（RAPS）算法，均能最小化误差信号l1和l2的混合范数。从基于l1范数的目标函数的梯度得到RAPS算法的方向向量，同时解决两个相关的基于l2范数的最小化问题，得到两种RAPS算法的直线搜索。基于l1范数的方向矢量减少了脉冲噪声的影响，而基于l2范数的直线搜索在所提出的算法中产生了无偏解。此外，两种RAPS算法中的一种共享集隶属度（SM）仿射投影（SMAP）算法中使用的数据选择自适应。与伪仿射投影符号（PAPS）算法相比，所提出的算法在收敛速度上有了显著的提高，并且在稳态失调方面有了显著的减少。此外，与PAPS和仿射投影符号（APS）算法相比，所提出的算法在脉冲噪声方面具有鲁棒性，并且改进了未知系统的跟踪。在系统识别和回波消除应用中使用仿真结果证明了所提出算法的这些特性。
Two robust affine projection sign (RAPS) algorithms, both of which minimize the mixed norm of l1 and l2 of the error signal, are proposed. The direction vector of the RAPS algorithms is obtained from the gradient of an l1 norm-based objective function, while two related l2 norm-based minimization problems are solved to obtain the line search of the two RAPS algorithms. The l1 norm-based direction vector reduces the impact of impulsive noise, whereas the l2 norm-based line search produces an unbiased solution in the proposed algorithms. In addition, one of the two RAPS algorithms shares the data selective adaptation used in the set-membership (SM) affine projection (SMAP) algorithm. The proposed algorithms are shown to offer a significant improvement in the convergence speed as well as a significant reduction in the steady-state misalignment relative to the pseudo affine projection sign (PAPS) algorithm. In addition, the proposed algorithms offer robust performance with respect to impulsive noise and improved tracking of the unknown system in comparison to that provided by the PAPS and Affine projection sign (APS) algorithms. These features of the proposed algorithms are demonstrated using simulation results in system-identification and echo-cancellation applications.