Author(s)

Ziqiang Wei, Zhaohua Long

Corresponding Author

Ziqiang Wei

ABSTRACT

Aiming at the shortcomings of the traditional normalized least mean square (NLMS) algorithm, an improved variable step size NLMS algorithm is proposed to improve the problem caused by the use of fixed step size, that is contradiction between convergence speed and steady-state error. The proposed algorithm in this paper establishes the relationship between the step size and the cross-correlation function of the error signal and the input signal, which can significantly improve the convergence speed and has a small steady state error. At the same time, when the filter system is abrupt, the algorithm can fast convergence and has good tracking performance.

KEYWORDS

Adaptive Filtering, Least Mean Square, Variable Step Size