Incremental combination of RLS and LMS adaptive filters in nonstationary scenarios
Incremental combination of RLS and LMS adaptive filters in nonstationary scenarios
复制标题
DOI：
10.1109/icassp.2013.6638751
复制
发表时间：
2013-05
期刊：
影响因子：
--
通讯作者：
W. B. Lopes;C. G. Lopes
中科院分区：
文献类型：
--
作者：
W. B. Lopes;C. G. Lopes
最近在文献中引入的自适应滤波器的增量组合(AFS)提出了能够改善整体滤波性能的内在特征。在这项工作中，增量组合被扩展到考虑具有不同自适应规则的AFS；当使用递归最小二乘(RLS)和最小均方(LMS)滤波器时，通过跟踪分析和大量的仿真表明，新结构在组合参数方面是均方普适的，特别是在具有高度相关的非平稳信号的情况下。仿真结果与分析模型吻合较好，表明新算法的性能优于并行独立算法。
The incremental combination of adaptive filters (AFs), recently introduced in the literature, presents intrinsic features capable of improving the overall filtering performance. In this work, the incremental combination is extended to account for AFs with different adaptive rules; when Recursive Least-Squares (RLS) and the Least-Mean-Squares (LMS) filters are employed, it is shown, by tracking analysis and extensive simulations, that the new structure is meansquare universal in terms of the combining parameter, particularly in nonstationary scenarios with highly-correlated signals. The simulations and the analytical model match well, showing that the new algorithm outperforms its parallel-independent counterpart.