|
2nd MIXMOD One Day Conference on December 4 2008 in Lille (France) |
|
Information and registrationThe purpose is to present MIXMOD features and to illustrate them through original case studies. It is also the opportunity for MIXMOD users to meet and exchange their own experience. |
|
Contact
|
Address: |
Université des Sciences et Technologies de Lille (Lille 1) - UFR de Mathematiques - UMR CNRS 8524 (laboratoire Painlevé) Cité Scientifique - 59655 Villeneuve d'Ascq Cedex - FRANCE |
|
Email: |
|
|
Phone: |
+03 20 43 68 76 (International: +33 3 20 43 68 76) |
|
Fax: |
+03 20 43 43 02 (International: +33 3 20 43 43 02) |
Professor at the University of Lille 1
Assistant-professor at the University of Franche-Comté
Post-PhD at INRIA Rhône-Alpes (MOVI project and IS2 project)
Teaching Assistant at the Pierre Mendès France University (Grenoble II)
PhD Thesis of the University of Technology of Compiègne (UTC)
Model-based clustering and discriminant analysis
Image indexing by using statistical tools
Reliability of pipings in nuclear power plants of EDF (Électricité de France)
Quality development
The MIXMOD (MIXture MODelling) software fits mixture models (Gaussian, Bernoulli, multinomial) to a given data set described by continuous or categorical variables with either a clustering or a discriminant analysis purpose. It is publicly available under the GPL license and is distributed for different platforms (Linux, Unix, Windows). It is developed jointly by INRIA futurs (SELECT project), the laboratory of mathematics of Besançon and the Heudiasyc laboratory of Compiègne .
|
NEW MIXMOD new release (version 2.1.1) includes now high dimensional data processing for a discriminant analysis purpose. |
The software, the statistical documentation and also the userguide are available on the internet.
Documents of MIXMOD Conference – October 2006
C. Biernacki (2009). Pourquoi les modèles de mélange pour la classification ? La Revue de Modulad, 40, 1-22. (PDF file)
J. Jacques and C. Biernacki (2009). Extension of model-based classification for binary data when training and test populations differ. Journal of applied Statistics, to appear. (PDF file)
I. Thomas, P. Frankhauser and C. Biernacki (2008). The morphology of built-up landscapes in Wallonia (Belgium): a classification using fractal indices. Landscape and Urban Planning, 84, 99-115. (PDF file)
C. Biernacki (2007). Degeneracy in the Maximum Likelihood Estimation of Univariate Gaussian Mixtures for Grouped Data and Behaviour of the EM Algorithm. Journal of Scandinavian Statistics, 34, 569-586. (postscript file)
J. Jacques and C. Biernacki (2007). Analyse discriminante sur données binaires lorsque les populations d’apprentissage et de test sont différentes. Revue des Nouvelles Technologies de l'Information, Data Mining et apprentissage statistique : application en assurance, banque et marketing, A1, 109-125. (PDF file)
F. Beninel and C. Biernacki (2007). Modèles d’extension de la régression logistique. Revue des Nouvelles Technologies de l'Information, Data Mining et apprentissage statistique : application en assurance, banque et marketing, A1, 207-218. (PDF file)
C. Biernacki (2006). Simultaneous model-based clustering of data arising from different populations. 10th conference of the International Federation of Classification Societies (IFCS), Ljubljana, Slovenia, July 25-29 (invited speaker). (PDF files: abstract, slides)
C. Biernacki, G. Celeux, A. Anwuli, G. Govaert and F. Langrognet (2006).Le logiciel MIXMOD d'analyse de mélange pour la classification et l'analyse discriminante. La Revue de Modulad, 35, 25-44. (PDF file)
C. Biernacki, G. Celeux, G. Govaert and F. Langrognet (2006). Model-Based Cluster and Discriminant Analysis with the MIXMOD Software. Computational Statistics and Data Analysis, 51, 2, 587-600. (postscript file)
C. Biernacki (2005). Testing for a Global Maximum of the Likelihood . Journal of Computational and Graphical Statistics, 14, 3, 657-674. (PDF files: paper , appendix)
C. Biernacki (2005). An Asymptotic Upper Bound of the Likelihood to Prevent Gaussian Mixtures from Degenerating. Preprint. (postcript file)
C. Biernacki (2004). Influence of the Bin Dimension on Selecting a Model by the BIC Criterion in Gaussian Mixtures with Grouped Data. Preprint. (postscript file)
C. Biernacki (2004). Contribution à l'étude des mélanges de lois et à leurs applications. Mémoire d'Habilitation à Diriger des Recherches. (postscript file)
C. Biernacki (2004). Initializing EM Using the Properties of its Trajectories in Gaussian Mixtures. Statistics and Computing, 14 , 3, 267-279. (postscript file)
C. Biernacki and S. Chrétien (2003). Degeneracy in the Maximum Likelihood Estimation of Univariate Gaussian Mixtures with EM. Statistics & Probability Letters, 61, 373-382. (postcript file)
C. Biernacki, G. Celeux and G. Govaert (2003). Choosing Starting Values for the EM Algorithm for Getting theHighest Likelihood in Multivariate Gaussian Mixture Models. Computational Statistics and Data Analysis, 41, 561-575. (postcript file)
C. Biernacki, F. Beninel and V. Bretagnolle (2002). A Generalized Discriminant Rule when Training Population and Test Population Differ on their Descriptive Parameters. Biometrics, 58, 2, 387-397. (postcript file)
C. Biernacki, G. Celeux and G. Govaert (2000). Assessing a Mixture Model for Clustering with the IntegratedCompleted Likelihood. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22 (7), 719-725. (postcript file)
C. Biernacki, G. Celeux and G. Govaert (1999). An Improvement of the NEC Criterion for Assessing the Number of Clusters in a Mixture Model. Pattern Recognition Letters, 20 (3), 267-272. (postcript file)
C. Biernacki and G. Govaert (1999). Choosing Models in Model-based Clustering and Discriminant Analysis. Journal of Statistical Computation and Simulation, 64, 49-71. (technical report postcript file)
C. Biernacki (1999). Précision sur les données et coude de la vraisemblance pour trouver le nombre de classes dans un mélange. Revue de Statistique Appliquée, 47 (1), 47-62. (postcript file)
C. Biernacki (1997). Choix de modèles en classification. Ph.D. Thesis, Université de Technologie de Compiègne. (postcript file)
C. Biernacki and G. Govaert (1997). Using the Classification Likelihood to Choose the Number of Clusters. Computing Science and Statistics, 29 (2), 451-457. (postcript file)
A. Guérin-Dugué, C. Biernacki and J. Hérault (2001). Statistical Modelling for Image Retrieval using a Biological Model of the Perceptive Colour Space. ICIP'2001, IEEE International Conference on Image Processing, Thessaloniki, Greece, 7-10 October. (Word file)
R. Hammoud, R. Mohr and C. Biernacki (1999). Robustification des signatures de couleurs par modélisation de leurs variabilités. GRETSI'99, 17ème colloque GRETSI sur le traitement du signal et des images, Vannes, France, 13-17 September. (postcript file)
C. Biernacki and R. Mohr (1999). Indexation et appariement d'images par modèle de mélange gaussien des couleurs . GRETSI'99, 17ème colloque GRETSI sur le traitement du signal et des images, Vannes, 13-17 September. (technical report postcript file)
B. Villain, B. Vérité, C. Biernacki and G. Celeux (1999). A Practical Approach of Expert Elicitation for Bayesian Reliability Analysis of Ageing. ESREL'99 (European Safety and Reliability Conference), TUM Munich - Garching, Germany, 13-17 September. (Word file)
C. Biernacki, G. Celeux, B. Villain et B. Vérité (1998). Utilisation des opinions d'experts pour l'analyse de la dégradation des structures passives. Technical report of the contract Inria-EDF
M. Bricler et C. Biernacki (2001). Projet d'élaboration d'une méthode aidant les collectivités locales et les établissements hospitaliers à réduire l'absentéisme. Technical report of the contract DEXIA-SOFAXIS/IRDQ.
Back to the Laboratoire de Mathématiques Painlevé Home Page.
Last update: 14th October 2009