Skip to Main content Skip to Navigation
Theses

Intégration de connaissances expertes dans le processus de fouille de données pour l'extraction d'informations pertinentes

Laurent Brisson 1
1 Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Equipe KEIA
Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
Abstract : Knowledge discovery from data is a process that aims to extract potentially useful knowledge hidden in large databases. Current works, in order to evaluate extracted patterns use interestingness measures. Such measures of interestingness are divided into objective measures that depend only on the structure of a pattern and the underlying data used in the discovery process, and the
subjective measures that also depend on the class of users who examine the pattern. However, it remains difficult to select relevant models according domain expert knowledge and the lack of formalism in knowledge expression prevents to compare expert knowledge to extracted patterns. We present KEOPS approach based on a method which use expert knowledge during a data mining process. An ontology driven information system (ODIS) plays a central role in KEOPS, allowing efficient data selection, data preparation and models interpretation. Furthermore, KEOPS uses a part-way interestingness
measure between objective and subjective measure in order to evaluate models relevance according to expert knowledge. Finally, KEOPS helps to create and maintain strategies in order to improve data mining processes and to monitor models usage in day-to-day business. KEOPS was deployed in order to study relationships with
beneficiaries of allowances from the `family' branch of the French national health care system (CAF: Caisse Nationale d'Allocations Familiales). The objective of this study was to help executives with relevant and useful information.
Document type :
Theses
Complete list of metadatas

https://tel.archives-ouvertes.fr/tel-00211946
Contributor : Estelle Nivault <>
Submitted on : Tuesday, January 22, 2008 - 11:36:00 AM
Last modification on : Monday, October 19, 2020 - 11:00:19 AM
Long-term archiving on: : Thursday, April 15, 2010 - 1:58:12 AM

Identifiers

  • HAL Id : tel-00211946, version 1

Collections

Citation

Laurent Brisson. Intégration de connaissances expertes dans le processus de fouille de données pour l'extraction d'informations pertinentes. Interface homme-machine [cs.HC]. Université Nice Sophia Antipolis, 2006. Français. ⟨tel-00211946⟩

Share

Metrics

Record views

592

Files downloads

403