New LMS Adaptive Filtering Algorithm with Variable Step Size

Abstract

By building a nonlinear function relationship between μ and the error signal e(n), this paper presents a new variable step size LMS(Least-Mean-Square)adaptive filtering algorithm, and analyzes the algorithm with various parameters α and β. This step size algorithm avoids the shortage of adjusting step size of SVSLMS (variable step size LMS based on Sigmoid function). Also in the process of the adaptive steady state it has the virtue of e(n) slightly changing close to zero. Theoretical analysis and computer simulations show that with the proposed algorithm, convergence rate can be improved than the former.