Concevoir un ensemble de nouvelles méthodes efficaces pour la fouille de motifs intéressants et pour l'extraction de bases de règles d'associations à partir de ceux-ci.
Laszlo Szathmary, Petko Valtchev, Napoli, Amedeo, Robert Godin, Boc, Alix and Makarenkov, Vladimir, "A fast compound algorithm for mining generators, closed itemsets, and computing links between equivalence classes," Annals of Mathematics and Artificial Intelligence, vol. 1(25), 2013.
Laszlo Szathmary, Petko Valtchev, A. Napoli and Robert Godin, "Finding Minimal Rare Itemsets in a Depth-Fist Manner," in FCA4AI Workshop, European Conference on Artificial Intelligence, Montpellier, France, 2012.
Laszlo Szathmary, Petko Valtchev, A. Napoli and Robert Godin, "Efficient Vertical Mining of Minimal Rare Itemsets," in International Conference on Concept Lattices and Applications (CLA), Fuengirola (Málaga), Spain, 2012.
Laszlo Szathmary, Petko Valtchev, Amedeo Napoli, Alix Boc and Robert Godin, "Fast mining of iceberg lattices: A modular approach using generators," in the 8th Intl. Conf. on Concept Lattices and Their Applications (CLA'11), Nancy, France, 2011.
Software development is a fairly complex activity, that is both labour-intensive and knowledge-rich, and systematically delivering high-quality software that addresses the users’ needs, on-time, and within budget, remains an elusive goal. This is even more true for internet applications presents additional challenges, including, 1) a predominance of the highly volatile interaction logic, and 2) stronger time-to-market pressures. Model-driven development purports to alleviate the problem by slicing the development process into a sequence of semantics-preserving transformations that start with a computation-independent model, through to an architecture-neutral platform independent model (PIM), all the way to platform-specific model or code at the other end. That is the idea(l). In general, however, the semantic gap between the CIM and PIM is such that the transition between them is hard to formalize. In this paper, we present a case study where we used an ontology to drive the development of an e-tourism portal. Our project showed that it is possible to drive the development of an internet application from a semantic description of the business entities, and illustrated the effectiveness of this approach during maintenance. It also highlighted the kinds of trade-offs we needed to make to reconcile somewhat lofty design principles with the imperative of producing a product with reasonable quality
Laszlo Szathmary, Petko Valtchev, Amedeo Napoli, Alix Boc, Robert Godin and Vladimir Makarenkov, "A fast vertical method for mining association rule bases.," Data Mining and Knowledge Discovery (submitted), 2011.
Laszlo Szathmary, Petko Valtchev and Amedeo Napoli, "Generating Rare Association Rules Using the Minimal Rare Itemsets Family," vol. 4, pp. 219--238, 2010.
Laszlo Szathmary, Petko Valtchev and Amedeo Napoli, "Generating highly confident rare association rules using the minimal rare itemsets family," International Journal of Software and Informatics, vol. 4(3), pp. 219-238, 2010.
Laszlo Szathmary, Petko Valtchev, A. Napoli and Robert Godin, "Efficient Vertical Mining of Frequent Closures and Generators," in The 8th International Symposium on Intelligent Data Analysis (IDA'2009), Lyon, France, 2009.
Laszlo Szathmary, Petko Valtchev, A. Napoli and Robert Godin, "Constructing Iceberg Lattices from Frequent Closures Using Generators," in Proceedings of the 11th International Conference on Discovery Sciences (DS’08), Budapest, Hongrie, 2008.
Laszlo Szathmary, Petko Valtchev, A. Napoli and Robert Godin, "An Efficient Hybrid Algorithm for Mining Frequent Closures and Generators," in Proceedings of the 6th Intl. Conf. Concept Lattices and Applications (CLA’08), Olomouc, République tchèque, 2008.
Laszlo Szathmary, A. Napoli and Petko Valtchev, "Towards Rare Itemset Mining," in Proceedings of the 19th IEEE International Conference on Tools with Artificial Intelligence (ICTAI ’07), Patras, Greece, 2007.