Re-weighted zero attracting adaptive exponential FLAF with maximum correntropy criterion for robust sparse nonlinear system identification

Abstract

The profoundly employed linear-in-the-parameter nonlinear adaptive filtering techniques of functional link adaptive filter (FLAF) and adaptive exponential FLAF (AEFLAF) often exhibit deteriorated performances in the wake of varying sparsity conditions and impulsive noise interferences. In this regard, a robust nonlinear adaptive filtering technique is introduced leveraging the benefits of nonlinear similarity index maximum correntropy criterion (MCC). Additionally a log sum penalty function is included in the derived cost function in response for sparse system identification. The entire robust nonlinear adaptive filter in this paper is constructed upon the framework of AEFLAF based on affine projection algorithm (APA) as MCC based reweighted zero attracting AEFLAF (MR-AEFLAF). Besides, steady state analysis of the proposed MR-AEFLAF is carried out establishing the condition for stability. Simulations with white, colored noise and speech segment illustrate the efficacy of the proposed technique for robust nonlinear adaptive filtering in system identification and acoustic feedback cancellation in hearing aids scenario. The performance of the designed adaptive filter is assessed quantitatively and qualitatively both.