Multi-dimensional signal approximation with sparse structured priors using split Bregman iterations
Isaac, Yoann; Barthélemy, Quentin; Gouy-Pailler, Cédric; Sebag, Michèle; Atif, Jamal (2017), Multi-dimensional signal approximation with sparse structured priors using split Bregman iterations, Signal Processing, 130, p. 389-402. 10.1016/j.sigpro.2016.07.013
Type
Article accepté pour publication ou publiéDate
2017Journal name
Signal ProcessingVolume
130Publisher
Elsevier
Pages
389-402
Publication identifier
Metadata
Show full item recordAuthor(s)
Isaac, YoannLaboratoire d'analyse des données et d'intelligence des systèmes [LADIS]
Barthélemy, Quentin
Mensia Technologies [Rennes]
Gouy-Pailler, Cédric

Laboratoire d'analyse des données et d'intelligence des systèmes [LADIS]
Sebag, Michèle
Laboratoire de Recherche en Informatique [LRI]
Atif, Jamal
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Abstract (EN)
This paper addresses the structurally constrained sparse decomposition of multi-dimensional signals onto overcomplete families of vectors, called dictionaries. The contribution of the paper is threefold. Firstly, a generic spatio-temporal regularization term is designed and used together with the standard ℓ1ℓ1 regularization term to enforce a sparse decomposition preserving the spatio-temporal structure of the signal. Secondly, an optimization algorithm based on the split Bregman approach is proposed to handle the associated optimization problem, and its convergence is analyzed. Our well-founded approach yields same accuracy as the other algorithms at the state of the art, with significant gains in terms of convergence speed. Thirdly, the empirical validation of the approach on artificial and real-world problems demonstrates the generality and effectiveness of the method. On artificial problems, the proposed regularization subsumes the Total Variation minimization and recovers the expected decomposition. On the real-world problem of electro-encephalography brainwave decomposition, the approach outperforms similar approaches in terms of P300 evoked potentials detection, using structured spatial priors to guide the decomposition.Subjects / Keywords
Machine learning; Structured sparsity; Overcomplete representations; Analysis prior; Split Bregman; Fused-LASSO; EEG denoisingRelated items
Showing items related by title and author.
-
Bojarski, Mariusz; Choromanska, Anna; Choromanski, Krzysztof; Fagan, Francois; Gouy-Pailler, Cédric; Morvan, Anne; Sakr, Nourhan; Sarlos, Tamas; Atif, Jamal (2017) Communication / Conférence
-
Pinot, Rafael; Morvan, Anne; Yger, Florian; Gouy-Pailler, Cédric; Atif, Jamal (2018) Communication / Conférence
-
Morvan, Anne; Choromanski, Krzysztof; Gouy-Pailler, Cedric; Atif, Jamal (2018) Communication / Conférence
-
Pinot, Rafaël; Meunier, Laurent; Araújo, Alexandre; Kashima, Hisashi; Yger, Florian; Gouy-Pailler, Cedric; Atif, Jamal (2019) Communication / Conférence
-
Pinot, Rafaël; Yger, Florian; Gouy-Pailler, Cedric; Atif, Jamal (2019) Communication / Conférence