Sparsity aware normalized least mean p-power algorithms with correntropy induced metric penalty

For identifying the non-Gaussian impulsive noise systems, normalized least mean p-power (NLMP) has been proposed to combat impulsive-inducing instability. However, the standard algorithm is developed without considering the inherent sparse structure distribution of unknown system. To exploit sparsity as well as to mitigate the impulsive noise synchronously, this paper proposes two effective NLMP-type algorithms. The first one is correntropy induced metric (CIM) constraint NLMP (CIMNLMP) algorithm. The second one is an improved CIM constraint variable regularized NLMP (CIMVRNLMP) algorithm, in which variable regularized parameter (VRP) is selected to adjust convergence speed and steady-state error. Numerical simulations are given to confirm the two proposed algorithms.