A Robust Group-Sparse Proportionate Affine Projection Algorithm with Maximum Correntropy Criterion for Channel Estimation

In many engineering applications, noise often exhibits strongly impulsive characteristics, while the conventional adaptive filtering (AF) algorithms are less robust to the impulsive noise. The AF algorithms based on maximum correntropy criterion (MCC) have been devised to effectively enhance the adaptive estimation performance in impulsive noise environments. In this paper, a robust group-sparse proportionate affine projection (RGS-PAP) algorithm based on MCC is proposed for estimating group-sparse channels which often occur in network echo paths and satellite communications channels. The constructed RGS-PAP algorithm is derived via exerting a mixed l(2,1) norm constraint of AF weights into the updating equation of the affine projection algorithm with MCC to utilize the group sparse characteristics. The developed RGS-PAP algorithm is analyzed by setting up various simulation experiments to verify its robustness and effectiveness. Simulation results indicate that the proposed RGS-PAP algorithm provides faster convergence and lower estimation bias compared with other algorithms under various input signals in impulse noise environments.