Detail publikace

Optimal Step-Size LMS Algorithm Using Exponentially Averaged Gradient Vector

Vladimr Malenovsky, Ing. Zdenek Smekal, Prof., Ing. Ivan Koula, Ing.

Originální název

Optimal Step-Size LMS Algorithm Using Exponentially Averaged Gradient Vector

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This letter proposes a new algorithm, which uses an optimal step-size (OSS) weight-adjustment scheme. This strategy leads to a better convergence rate and misadjustment in environments with sudden changes of parameters and for colored input data. The computational complexity is comparable with the well-known RLS. The performance of the novel approach is verified by simulations under system identification scenario and compared with that of the NLMS and RLS algorithms. The strategy uses averaged values of the correlation matrix and the cross-correlation vector. Experimental results for car-interior echo cancelation are presented including analysis of converegnce rate and misadjustment.

Klíčová slova

adaptive filter, least mean square, recursive least squares, convergence rate, computational complexity, misadjustment, optimal step-size, exponential averaging

Autoři

Vladimr Malenovsky, Ing. Zdenek Smekal, Prof., Ing. Ivan Koula, Ing.

Rok RIV

2005

Vydáno

21. 11. 2005

Nakladatel

Belgrade, Serbia and Montenegro

Místo

Belgrade, Serbia and Montenegro

ISBN

1-4244-0050-3

Kniha

Proceedings of the Intl. Conference EUROCON 2005

Edice

SVAZEK: R23 SIGNAL PROCESSING

Strany od

1554

Strany do

1557

Strany počet

4

BibTex

@inproceedings{BUT15142,
  author="Vladimír {Malenovský} and Zdeněk {Smékal} and Ivan {Koula}",
  title="Optimal Step-Size LMS Algorithm Using Exponentially Averaged Gradient Vector",
  booktitle="Proceedings of the Intl. Conference EUROCON 2005",
  year="2005",
  series="SVAZEK: R23 SIGNAL PROCESSING",
  pages="4",
  publisher="Belgrade, Serbia and Montenegro",
  address="Belgrade, Serbia and Montenegro",
  isbn="1-4244-0050-3"
}