Steady-state performance of non-negative least-mean-square algorithm and its variants

Jie Chen; José Carlos M. Bermudez; Cédric Richard

doi:10.1109/LSP.2014.2320944

Steady-state performance of non-negative least-mean-square algorithm and its variants

Jie Chen
, José Carlos M. Bermudez
, Cédric Richard

Université de Nice Sophia-Antipolis
Universidade Federal de Santa Catarina

Research output: Contribution to journal › Article › peer-review

26 Scopus citations

Abstract

The Non-Negative Least-Mean-Square (NNLMS) algorithm and its variants have been proposed for online estimation under non-negativity constraints. The transient behavior of the NNLMS, Normalized NNLMS, Exponential NNLMS and Sign-Sign NNLMS algorithms have been studied in the literature. In this letter, we derive closed-form expressions for the steady-state excess mean-square error (EMSE) for the four algorithms. Simulation results illustrate the accuracy of the theoretical results. This work complements the understanding of the behavior of these algorithms.

Original language	English
Article number	6807652
Pages (from-to)	928-932
Number of pages	5
Journal	IEEE Signal Processing Letters
Volume	21
Issue number	8
DOIs	https://doi.org/10.1109/LSP.2014.2320944
State	Published - Aug 2014
Externally published	Yes

Keywords

Non-negative LMS
excess mean-square error
steady-state performance
stochastic behavior

Access to Document

10.1109/LSP.2014.2320944

Cite this

@article{8cbbd2e5d5e54e279302a7964412f5ed,

title = "Steady-state performance of non-negative least-mean-square algorithm and its variants",

abstract = "The Non-Negative Least-Mean-Square (NNLMS) algorithm and its variants have been proposed for online estimation under non-negativity constraints. The transient behavior of the NNLMS, Normalized NNLMS, Exponential NNLMS and Sign-Sign NNLMS algorithms have been studied in the literature. In this letter, we derive closed-form expressions for the steady-state excess mean-square error (EMSE) for the four algorithms. Simulation results illustrate the accuracy of the theoretical results. This work complements the understanding of the behavior of these algorithms.",

keywords = "Non-negative LMS, excess mean-square error, steady-state performance, stochastic behavior",

author = "Jie Chen and Bermudez, \{Jos{\'e} Carlos M.\} and C{\'e}dric Richard",

year = "2014",

month = aug,

doi = "10.1109/LSP.2014.2320944",

language = "英语",

volume = "21",

pages = "928--932",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "8",

}

TY - JOUR

T1 - Steady-state performance of non-negative least-mean-square algorithm and its variants

AU - Chen, Jie

AU - Bermudez, José Carlos M.

AU - Richard, Cédric

PY - 2014/8

Y1 - 2014/8

N2 - The Non-Negative Least-Mean-Square (NNLMS) algorithm and its variants have been proposed for online estimation under non-negativity constraints. The transient behavior of the NNLMS, Normalized NNLMS, Exponential NNLMS and Sign-Sign NNLMS algorithms have been studied in the literature. In this letter, we derive closed-form expressions for the steady-state excess mean-square error (EMSE) for the four algorithms. Simulation results illustrate the accuracy of the theoretical results. This work complements the understanding of the behavior of these algorithms.

AB - The Non-Negative Least-Mean-Square (NNLMS) algorithm and its variants have been proposed for online estimation under non-negativity constraints. The transient behavior of the NNLMS, Normalized NNLMS, Exponential NNLMS and Sign-Sign NNLMS algorithms have been studied in the literature. In this letter, we derive closed-form expressions for the steady-state excess mean-square error (EMSE) for the four algorithms. Simulation results illustrate the accuracy of the theoretical results. This work complements the understanding of the behavior of these algorithms.

KW - Non-negative LMS

KW - excess mean-square error

KW - steady-state performance

KW - stochastic behavior

UR - https://www.scopus.com/pages/publications/84901070066

U2 - 10.1109/LSP.2014.2320944

DO - 10.1109/LSP.2014.2320944

M3 - 文章

AN - SCOPUS:84901070066

SN - 1070-9908

VL - 21

SP - 928

EP - 932

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

IS - 8

M1 - 6807652

ER -

Steady-state performance of non-negative least-mean-square algorithm and its variants

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this