Skip to main content
European Commission logo
français français
CORDIS - Résultats de la recherche de l’UE
CORDIS
CORDIS Web 30th anniversary CORDIS Web 30th anniversary
Contenu archivé le 2024-05-24

consortium on discovering knowledge with Inductive Queries

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

A few tens of scientific papers have been dedicated to the studied pattern domains and the design of adequate solvers. It includes molecular fragment mining, item set mining, association rule mining, sequential pattern mining, equation discovery, etc. All these algorithms have been implemented by means of software prototypes, which have also been used for targeted applications in chemoinformatics, moleucular biology, environmental data analysis and telecommunication data analysis.
Again, the project members have published about ten scientific papers focussing on promising applications of the designed algorithms. It has concerned chemoinformatics and predictive toxicity (developement in Freiburg), telecommunication data analysis (developments in Torino and helsinki on log mining), gene expression data analysis and bioinformatics (developments in Lyon) and also potential applications within semi-structured data mining (say XML) in Torino and Milano.
Various conceptual and theoretical contributions to the inductive database framwork have been achieved. The consortium has produced a rather comprehensive study of inductive queries on the co-called local patterns. The key concept of condensed representations (with many applications in the context of frequent patterns) has been identified. Other key issues related to the most general type of inductive query studied so far have been considered. The results have been published in the main data mining conferences (ACM SIGKDD, IEEE IDCM, ECML/PKDD) and the best journals in the field (e.g., DMKD and IS journals).

Recherche de données OpenAIRE...

Une erreur s’est produite lors de la recherche de données OpenAIRE

Aucun résultat disponible