Sparse normalized subband adaptive filter algorithm with l0-norm constraint

In order to improve the filter's performance when identifying sparse system, this paper develops two sparse-aware algorithms by incorporating the l(0)-norm constraint of the weight vector into the conventional normalized subband adaptive filter (NSAF) algorithm. The first algorithm is obtained from the principle of the minimum perturbation; and the second one is based on the gradient descent principle. The resulting algorithms have almost the same convergence and steady-state performance while the latter saves computational complexity. What's more, the performance of both algorithms is analyzed by resorting to some assumptions commonly used in the analyses of adaptive algorithms. Simulation results in the context of sparse system identification not only demonstrate the effectiveness of the proposed algorithms, but also verify the theoretical analyses. (C) 2016 The Franklin Institute. Published by Elsevier Ltd. All rights reserved.