Struktura obiektu

Autor:

Zdunek, Rafał

Współtwórca:

Makowski, Ryszard - ed. ; Zarzycki, Jan - ed.

Tytuł:

Regularized nonnegative matrix factorization: Geometrical interpretation and application to spectral unmixing

Podtytuł:

.

Tytuł publikacji grupowej:

AMCS, Volume 24 (2014)

Temat i słowa kluczowe:

blind source separation ; nonnegative matrix factorization ; active-set algorithm ; regularized NMF ; polytope approximation

Abstract:

Nonnegative Matrix Factorization (NMF) is an important tool in data spectral analysis. However, when a mixing matrix or sources are not sufficiently sparse, NMF of an observation matrix is not unique. Many numerical optimization algorithms, which assure fast convergence for specific problems, may easily get stuck into unfavorable local minima of an objective function, resulting in very low performance. ; In this paper, we discuss the Tikhonov regularized version of the Fast Combinatorial NonNegative Least Squares (FC-NNLS) algorithm (proposed by Benthem and Keenan in 2004), where the regularization parameter starts from a large value and decreases gradually with iterations. A geometrical analysis and justification of this approach are presented. The numerical experiments, carried out for various benchmarks of spectral signals, demonstrate that this kind of regularization, when applied to the FC-NNLS algorithm, is essential to obtain good performance.

Wydawca:

Zielona Góra: Uniwersytet Zielonogórski

Data wydania:

2014

Typ zasobu:

artykuł

DOI:

10.2478/amcs-2014-0017

Strony:

233-247

Źródło:

AMCS, volume 24, number 2 (2014) ; kliknij tutaj, żeby przejść

Jezyk:

eng

Prawa do dysponowania publikacją:

Biblioteka Uniwersytetu Zielonogórskiego