Sparsity-Aware Robust Normalized Subband Adaptive Filtering Algorithms With Alternating Optimization of Parameters

This brief proposes a unified sparsity-aware robust normalized subband adaptive filtering (SA-RNSAF) algorithm for identification of sparse systems under impulsive noises. The proposed SA-RNSAF generalizes different algorithms by defining the criterion and penalty. Furthermore, alternating optimization parameters (AOP) algorithm, including step-size sparsity penalty weight, we develop AOP-SA-RNSAF which not only exhibits fast convergence but also obtains low steady-state misadjustment systems. Simulations in various noise scenarios have verified that outperforms existing techniques.