Two novel methods for the determination of the number of components in independent components analysis models
2012
Jouan-Rimbaud Bouveresse, Delphine | Moya-Gonzalez, A., A. | Ammari, F., F. | Rutledge, Douglas N., D.N. | Ingénierie Procédés Aliments (GENIAL) ; Institut National de la Recherche Agronomique (INRA)-AgroParisTech-Conservatoire National des Arts et Métiers [Cnam] (Cnam)-Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (IRSTEA) | LPF Tagralia ; Universidad Politécnica de Madrid (UPM) | Faculté des Sciences de Bizerte [Université de Carthage] ; Université de Carthage (Tunisie) = University of Carthage (UCAR)
Independent Components Analysis is a Blind Source Separation method that aims to find the pure source signals mixed together in unknown proportions in the observed signals under study. It does this by searching for factors which are mutually statistically independent. It can thus be classified among the latent-variable based methods. Like other methods based on latent variables, a careful investigation has to be carried out to find out which factors are significant and which are not. Therefore, it is important to dispose of a validation procedure to decide on the optimal number of independent components to include in the final model. This can be made complicated by the fact that two consecutive models may differ in the order and signs of similarly-indexed ICs. As well, the structure of the extracted sources can change as a function of the number of factors calculated. Two methods for determining the optimal number of ICs are proposed in this article and applied to simulated and real datasets to demonstrate their performance. (c) 2012 Elsevier B.V. All rights reserved.
Mostrar más [+] Menos [-]Palabras clave de AGROVOC
Información bibliográfica
Este registro bibliográfico ha sido proporcionado por Institut national de la recherche agronomique