Error Analysis of Low-rank Three-Way Tensor Factorization Approach to Blind Source Separation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Error Analysis of Low-rank Three-Way Tensor Factorization Approach to Blind Source Separation

Résumé

In tensor factorization approaches to blind separation of multidimensional sources, two formulas for calculating the source tensor have emerged. In practice, it is observed that these two schemes exhibit different levels of robustness against perturbations of the factors involved in the tensor model. Motivated by both practical reasons and the will to better figure this out, we present error analyses in source tensor estimation performed by low-rank factorization of three-way tensors. To that aim, computer simulations as well as the analytical calculation of the theoretical error are carried out. The conclusions drawn from these numerical and analytical error analyses are supported by the results obtained thanks to tensor-based blind decomposition of an experimental multispectral image of a skin tumor.
Fichier principal
Vignette du fichier
Kopriva_Royer_Thirion_Comon_ICASSP_2014_rev2.pdf (217.5 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00990255 , version 1 (13-05-2014)

Identifiants

  • HAL Id : hal-00990255 , version 1

Citer

Ivica Kopriva, Jean-Philip Royer, Nadège Thirion-Moreau, Pierre Comon. Error Analysis of Low-rank Three-Way Tensor Factorization Approach to Blind Source Separation. ICASSP 2014 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2014, Florence, Italy. pp.3210-3214. ⟨hal-00990255⟩
563 Consultations
447 Téléchargements

Partager

Gmail Facebook X LinkedIn More