Recursive Maximum Correntropy Criteria Algorithm with l1-norm Constraints for Sparse System Identification

To address sparse system identification (SSI) problem under impulsive noise environment, a sparse recursive maximum Correntropy criteria (RMCC) algorithm using l1-norm constraint is proposed to combat the influence of impulse noise for the identification performance. The proposed recursive algorithm is derived by the new cost function combined proposed the maximum Correntropy criteria with forgetting factor and the l1-norm, and it has the faster convergence speed and the smaller steady-state error than the traditional MCC algorithm. Numerical simulations are given to show that the proposed algorithm is robust to SSI problem under the impulsive noise environment.