Idioma:

Improving the Tracking Capability of Adaptive Filters via Convex Combination

Silva, M.T.M. ; Nascimento, V.H.

IEEE transactions on signal processing, 2008-07, Vol.56 (7), p.3137-3149 [Periódico revisado por pares]

New York, NY: IEEE

Texto completo disponível

Citações Citado por

Enviar para

Título:
Improving the Tracking Capability of Adaptive Filters via Convex Combination
Autor: Silva, M.T.M. ; Nascimento, V.H.
Assuntos: Adaptive algorithm ; Adaptive equalizers ; Adaptive filters ; Algorithms ; Applied sciences ; Blind equalizers ; Blinds ; convex combination ; Detection, estimation, filtering, equalization, prediction ; Equalization ; Errors ; Exact sciences and technology ; Filtering algorithms ; Information, signal and communications theory ; Least squares approximation ; least-mean-square (LMS) methods ; Mathematical models ; Miscellaneous ; recursive estimation ; Resonance light scattering ; Signal and communications theory ; Signal processing ; Signal processing algorithms ; Signal, noise ; Statistics ; Steady-state ; Studies ; Telecommunications and information theory ; Tracking ; unsupervised learning
É parte de: IEEE transactions on signal processing, 2008-07, Vol.56 (7), p.3137-3149
Notas: ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
Descrição: As is well known, Hessian-based adaptive filters (such as the recursive-least squares algorithm (RLS) for supervised adaptive filtering, or the Shalvi-Weinstein algorithm (SWA) for blind equalization) converge much faster than gradient-based algorithms [such as the least-mean-squares algorithm (LMS) or the constant-modulus algorithm (CMA)]. However, when the problem is tracking a time-variant filter, the issue is not so clear-cut: there are environments for which each family presents better performance. Given this, we propose the use of a convex combination of algorithms of different families to obtain an algorithm with superior tracking capability. We show the potential of this combination and provide a unified theoretical model for the steady-state excess mean-square error for convex combinations of gradient- and Hessian-based algorithms, assuming a random-walk model for the parameter variations. The proposed model is valid for algorithms of the same or different families, and for supervised (LMS and RLS) or blind (CMA and SWA) algorithms.
Editor: New York, NY: IEEE
Idioma: Inglês

Links

View record in Pascal Francis

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Improving the Tracking Capability of Adaptive Filters via Convex Combination

Silva, M.T.M. ; Nascimento, V.H.

New York, NY: IEEE

Buscando em bases de dados remotas. Favor aguardar.