Derivation of a new normalized least mean squares algorithm with modified minimization criterion

Abstract

In this letter, we propose a normalized least mean squares (NLMS) algorithm with a new minimization criterion that minimizes the summation of each squared Euclidean norm of difference between the currently updated coefficient vector and past coefficient vectors. Through simulations, we show that the proposed NLMS algorithm has lower misalignment than the conventional NLMS algorithm. (C) 2008 Elsevier B.V. All rights reserved.