A robust adaptive decomposable Volterra filter based on the hyperbolic tangent Leclerc function and its performance analysis

Most of the existing adaptive filter algorithms pay more attention to improving performance while ignoring the computational complexity and the impact of the impulsive environment. When encountering the impulsive noise environments, the performance of traditional nonlinear adaptive filter may be significantly reduced and usually needs high computational cost. Therefore, this article proposes a hyperbolic tangent Leclerc robust nonlinear adaptive filter based on the low complexity decomposable Volterra model (HTLNAF-DVM). The filter is implemented by imposing a rank-one structure on the full Volterra model to get a product of linear filters, and employs a hyperbolic tangent Leclerc function as a robust norm to effectively improve the robustness against the impulsive noise. In addition, we give the theoretical analyses of the steady-state mean-square performance of the proposed HTLNAF-DVM. Finally, the simulation results prove that the proposed HTLNAF-DVM algorithm has better performance than the existing algorithms and fit well with the theory.