Mining the Bilinear Structure of Data with Approximate Joint Diagonalization - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Mining the Bilinear Structure of Data with Approximate Joint Diagonalization

Abstract

Approximate Joint Diagonalization of a matrix set can solve the linear Blind Source Separation problem. If the data possesses a bilinear structure, for example a spatio-temporal structure, transformations such as tensor decomposition can be applied. In this paper we show how the linear and bilinear joint diagonalization can be applied for extracting sources according to a composite model where some of the sources have a linear structure and other a bilinear structure. This is the case of Event Related Potentials (ERPs). The proposed model achieves higher performance in term of shape and robustness for the estimation of ERP sources in a Brain Computer Interface experiment.
Fichier principal
Vignette du fichier
2016-eusipco-CAJD.pdf (1.54 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01357245 , version 1 (29-08-2016)

Identifiers

  • HAL Id : hal-01357245 , version 1

Cite

Louis Korczowski, Florent Bouchard, Christian Jutten, Marco Congedo. Mining the Bilinear Structure of Data with Approximate Joint Diagonalization. EUSIPCO 2016 - 24th European Signal Processing Conference, EURASIP, Aug 2016, Budapest, Hungary. pp.667-671. ⟨hal-01357245⟩
341 View
277 Download

Share

Gmail Mastodon Facebook X LinkedIn More