Spline Adaptive Filtering based on Variable Leaky Least Mean Square Algorithm

This paper conducts a variable leaky least mean square algorithm based on nonlinear adaptive filtering with adaptive lookup table using spline interpolation. A leaky constraint is implemented with a leaky quantized function for adjustment. Proposed algorithm merges a modified variable leaky method with least mean square algorithm for linear and nonlinear network part of spline adaptive filtering in term of fast convergence enhancement. Experimental results show that proposed algorithm can notably perform the convergence rate in comparison with the conventional algorithm.