Non-linear RLS-based algorithm for pattern classification

Emilio Soria‐Olivas

doi:10.1016/j.sigpro.2005.09.004

2006-05-01

PRE

Emilio Soria‐Olivas

Gustau Camps‐Valls

José D. Martín‐Guerrero

Javier Calpe‐Maravilla

Joan Vila‐Francés

Antonio J. Serrano-López

DOI：10.1016/j.sigpro.2005.09.004

原文链接

原文求助

摘要

En 中文

A new non-linear recursive least squares (RLS) algorithm is presented in the context of pattern classification problems. The algorithm incorporates the non-linearity of the filter's output in the updating rules of the classical RLS algorithm. The proposed method yields lower stationary error levels when compared to the standard LMS and RLS algorithms in a classical application of pattern classification, such as the channel equalization problem. (C) 2005 Elsevier B.V. All rights reserved.

Keyword:

pattern classification

LMS

RLS

non-linear

filter

channel equalization