Vincent Vandewalle

maître de conférences - Applied mathematics : statistics
CNU : SECTION 26 - MATHEMATIQUES APPLIQUEES ET APPLICATIONS DES MATHEMATIQUES
vincent_vandewalle.jpg

Vincent Vandewalle

maître de conférences - Applied mathematics : statistics

Publications

Article dans des revues

  • Marie Cuvelliez, Vincent Vandewalle, Maxime Brunin, Olivia Beseme, Audrey Hulot, et al.. Circulating proteomic signature of early death in heart failure patients with reduced ejection fraction. Scientific Reports, Nature Publishing Group, 2019, 9, pp.19202. ⟨10.1038/s41598-019-55727-1⟩. ⟨hal-02414293⟩
  • Marie Cuvelliez, Vincent Vandewalle, Maxime Brunin, Olivia Beseme, Audrey Hulot, et al.. Circulating proteomic signature of early death in heart failure patients with reduced ejection fraction - Short title: Proteomic signature of early death in heart failure patients. Scientific Reports, Nature Publishing Group, In press. ⟨hal-02400814⟩
  • Matthieu Marbac, Vincent Vandewalle. A tractable Multi-Partitions Clustering. Computational Statistics and Data Analysis, Elsevier, 2018, ⟨10.1016/j.csda.2018.06.013⟩. ⟨hal-01691417⟩
  • Matthieu Marbac, Christophe Biernacki, Vincent Vandewalle. Model-based clustering of Gaussian copulas for mixed data. Communications in Statistics - Theory and Methods, Taylor & Francis, 2017, 46 (23), pp.11635-11656. ⟨hal-00987760v4⟩
  • Matthieu Marbac, Christophe Biernacki, Vincent Vandewalle. Latent class model with conditional dependency per modes to cluster categorical data. Advances in Data Analysis and Classification, Springer Verlag, 2016, 10 (2), pp.183-207. ⟨10.1007/s11634-016-0250-1⟩. ⟨hal-00950112v2⟩
  • Matthieu Marbac, Christophe Biernacki, Vincent Vandewalle. Model-based clustering for conditionally correlated categorical data. Journal of Classification, Springer Verlag, 2015, 2 (32), pp.145-175. ⟨10.1007/s00357⟩. ⟨hal-00787757v3⟩
  • E. Eirola, Amaury Lendasse, Vincent Vandewalle, Christophe Biernacki. Mixture of Gaussians for Distance Estimation with Missing Data. Neurocomputing, Elsevier, 2014, 131, pp.32-42. ⟨hal-00921023v2⟩
  • Vincent Vandewalle, Christophe Biernacki, Gilles Celeux, Gérard Govaert. A predictive deviance criterion for selecting a generative model in semi-supervised classification. Computational Statistics and Data Analysis, Elsevier, 2013, 64, pp.220-236. ⟨inria-00516991⟩
  • Gérard Grégoire, François-Xavier Jollois, Jean-François Petiot, Abdellah Qannari, Serge Sabourin, et al.. Les logiciels et l'enseignement de la statistique dans les départements " Statistique et Informatique Décisionnelle " (STID) des IUT. Statistique et Enseignement, Société Française de Statistique, 2012, 2 (2), pp.5-24. ⟨hal-00913110⟩
  • Vincent Vandewalle, Christophe Biernacki, Gilles Celeux, Gérard Govaert. A predictive deviance criterion for selecting a generative model in semi-supervised classification. Computational Statistics and Data Analysis, Elsevier, 2012. ⟨hal-00778130⟩
  • Stephane Robin, Sophie Schbath, Vincent Vandewalle. Statistical tests to compare motif count exceptionalities. BMC Bioinformatics, BioMed Central, 2007, 8, pp.84. ⟨10.1186/1471-2105-8-84⟩. ⟨hal-01197501⟩

Communication dans un congrès

  • Christophe Biernacki, Matthieu Marbac-Lourdelle, Vincent Vandewalle. Gaussian Based Visualization of Gaussian and Non-Gaussian Based Clustering. 3rd International Conference on Econometrics and Statistics (EcoSta 2019), Jun 2019, Taichung, Taiwan. ⟨hal-02398999⟩
  • Vincent Vandewalle, Cristian Preda, Sophie Dabo. Clustering spatial functional data. ERCIM 2018, Dec 2018, Pise, Italy. ⟨hal-01956923⟩
  • Adrien Ehrhardt, Vincent Vandewalle, Christophe Biernacki, Philippe Heinrich. Supervised multivariate discretization and levels merging for logistic regression. 23rd International Conference on Computational Statistics, Aug 2018, Iasi, Romania. ⟨hal-01949128⟩
  • Christophe Biernacki, Vincent Vandewalle, Matthieu Marbac. Gaussian-based visualization of Gaussian and non-Gaussian model-based clustering. 23rd International Conference on Computational Statistics, Aug 2018, Iasi, Romania. ⟨hal-01949127⟩
  • Vincent Vandewalle, Matthieu Marbac. A tractable multi-partitions clustering. COMPSTAT 2018 - 23rd International Conference on Computational Statistics, Aug 2018, Iasi, Romania. ⟨hal-01956922⟩
  • Vincent Vandewalle, Thierry Mottet, Matthieu Marbac. Model-based variable clustering. CMStatistics/ERCIM 2017 - 10th International Conference of the ERCIM WG on Computational and Methodological Statistics, Dec 2017, London, United Kingdom. pp.1-19. ⟨hal-01691421⟩
  • Vincent Vandewalle. Simultaneous dimension reduction and multi-objective clustering . IFCS 2017 - Conference of the International Federation of Classification Societies, Aug 2017, Tokyo, Japan. pp.1-29. ⟨hal-01662271⟩
  • Serge Iovleff, Mathieu Fauvel, Stephane Girard, Cristian Preda, Vincent Vandewalle. Mixture Models with Missing data Classication of Satellite Image Time Series: QUALIMADOS: Atelier Qualité des masses de données scientiques. Journées Science des Données MaDICS 2017, Jun 2017, Marseille, France. pp.1-60. ⟨hal-01649206⟩
  • Vincent Vandewalle, Christophe Biernacki. Survival analysis with complex covariates: a model-based clustering preprocessing step. IEEE PHM 2017, Jun 2017, Dallas, United States. ⟨hal-01667588⟩
  • Vincent Vandewalle, Christophe Biernacki. Dealing with missing data through mixture models. ICB Seminars 2017 - 154th Seminar on ”Statistics and clinical practice”, May 2017, Varsovie, Poland. pp.1-3. ⟨hal-01667614⟩
  • Christophe Biernacki, Gwenaelle Castellan, Stephane Chretien, Benjamin Guedj, Vincent Vandewalle. Pitfalls in Mixtures from the Clustering Angle. Working Group on Model-Based Clustering Summer Session, Jul 2016, Paris, France. ⟨hal-01419755⟩
  • Vincent Vandewalle, Cristina Cozma, Cristian Preda. Clustering categorical functional data Application to medical discharge letters. 8th International Conference of the ERCIM WG on Computational and Methodological Statistics, Dec 2015, Londres, France. ⟨hal-01251284⟩
  • Vincent Vandewalle, C Biernacki. An efficient SEM algorithm for Gaussian Mixtures with missing data. 8th International Conference of the ERCIM WG on Computational and Methodological Statistics, Dec 2015, Londres, United Kingdom. ⟨hal-01242588⟩
  • Matthieu Marbac, Christophe Biernacki, Vincent Vandewalle. Model-based clustering of categorical data by relaxing conditional independence. Classification Society Meeting, Mc Master University, Jun 2015, Hamilton, Ontario, Canada. ⟨hal-01238334⟩
  • Vincent Vandewalle. Sélection prédictive d'un modèle génératif par le critère AICp. 41èmes Journées de Statistique, SFdS, Bordeaux, 2009, Bordeaux, France, France. ⟨inria-00386678⟩

Poster

  • Adrien Ehrhardt, Christophe Biernacki, Vincent Vandewalle, Philippe Heinrich. Model-based multivariate discretization for logistic regression. Data Science Summer School, Aug 2017, Paris, France. 2017. ⟨hal-02075126⟩
  • Vincent Vandewalle, Cristian Preda. Clustering categorical functional data Application to medical discharge letters Medical discharge letters. Working Group on Model-Based Clustering Summer Session: Paris, July 17-23, 2016, Jul 2016, Paris, France. 0010. ⟨hal-01424950⟩

Document associé à des manifestations scientifiques

  • Vincent Vandewalle. Simultaneous dimension reduction and multi-objective clustering using probabilistic factorial discriminant analysis. CMStatistics 2016, Dec 2016, Sevilla, Spain. ⟨hal-01424965⟩
  • Chloé Friguet, Frédérique Letué, Vincent Vandewalle. Table ronde : “pourquoi et comment enseigner l’analyse de données massives (big data)”. 47èmes Journées de Statistique de la SFdS, Jun 2015, Lille, France. ⟨hal-01250812⟩

Chapitre d'ouvrage

  • Sophie Dabo-Niang, Cristian Preda, Vincent Vandewalle. Clustering spatial functional data. Geostatistical Functional Data Analysis : Theory and Methods. Editors: Jorge Mateu, Ramon Giraldo, In press. ⟨hal-01948934⟩

Pré-publication, Document de travail

  • Florent Dewez, Benjamin Guedj, Vincent Vandewalle. From industry-wide parameters to aircraft-centric on-flight inference: improving aeronautics performance prediction with machine learning. 2020. ⟨hal-02570875⟩
  • Christophe Biernacki, Matthieu Marbac, Vincent Vandewalle. Gaussian Based Visualization of Gaussian and Non-Gaussian Based Clustering. 2019. ⟨hal-01949155v2⟩
  • Adrien Ehrhardt, Christophe Biernacki, Vincent Vandewalle, Philippe Heinrich. Feature quantization for parsimonious and interpretable predictive models. 2019. ⟨hal-01949135v2⟩
  • Matthieu Marbac, Christophe Biernacki, Vincent Vandewalle. Classification de données mixtes par un modèle de mélange de copules gaussiennes.. 2014. ⟨hal-00940613⟩

Thèse

  • Vincent Vandewalle. Estimation et sélection en classification semi-supervisée. Mathématiques [math]. Université des Sciences et Technologie de Lille - Lille I, 2009. Français. ⟨tel-00447141⟩

Articles

  1. Matthieu Marbac, Christophe Biernacki, Vincent Vandewalle, Latent class model with conditional dependency per modes to cluster categorical data. Advances in Data Analysis and Classification, 2016, 10, (2)pp. 183–207.

  2. Matthieu Marbac, Christophe Biernacki and Vincent Vandewalle, Model-based clustering for conditionally correlated categorical data. Journal of Classification, Springer Verlag, 2015, 2 (32), 7, pp.145-175.
  1. Emil Eirola, Amaury Lendasse, Vincent Vandewalle and Christophe Biernacki, Mixture of Gaussians for Distance Estimation with Missing Data, Neurocomputing, Elsevier, 2014, 131, pp 32-42.
  2. Vincent Vandewalle, Christophe Biernacki, Gilles Celeux and Gérard Govaert, A predictive de- viance criterion for selecting a generative model in semi-supervised classification. Computational Statistics and Data Analysis, 2013, Volume 64, pp 220-236

  3. Gérard Grégoire,François-XavierJollois, Jean-FrançoisPetiot, Abdellah Qannari, Serge Sabourin, Philippe Swertwaegher, Jean-Christophe Turlot, Vincent Vandewalle and Sylvie Viguier-Pla. Les logiciels et l’enseignement de la statistique dans les départements “Statistique et Informatique Décisionnelle”(STID) des IUT. Statistique et Enseignement, 2(2), 5-24, 2012

  4. Christophe Biernacki and Vincent Vandewalle.Label Switching in Mixtures.In American Institute of Physics Conference Series, 2011, Vol. 1389, pp. 398-401.

  5. Vincent Vandewalle,Les modèles de mélange, un outil utile pour la classification semi-supervisée, Revue MODULAD, 2009, 40, pp 121-145.

  6. Stéphane Robin, Sophie Schbath, and Vincent Vandewalle, Statistical tests to compare motif count exceptionalities, BMC Bioinformatics 2007, 8:84.

More details on my long CV.

PhD Students

  • Adrien Ehrhardt (2015-now) “Modèles prédictifs pour données volumineuses et biaisées. Application à l’amélioration du scoring en risque crédit.”
  • Matthieu Marbac-Lourdelle (2011-2014) “Modèles de mélange pour la classification non supervisée de données qualitatives et mixtes”