Skip to Main content Skip to Navigation
Journal articles

Muskca : un système de fusion d'ontologies fondé sur le consensus et l'estimation de la confiance

Abstract : Today many datasets related to the same domain of interest are available on the web of Linked Data. These datasets can have variable quality, which makes them difficult to reuse. In this article, we present a novel approach for identifying knowledge shared by different datasets taking into account their quality. This approach is based on metrics used to evaluate the trust score of common elements extracted from various datasets. In this article we propose several metrics, one of them is based on the integral of Choquet. These metrics have been evaluated on a real case study with experts from the agriculture domain.
Document type :
Journal articles
Complete list of metadata

https://hal.inrae.fr/hal-02607693
Contributor : Migration Irstea Publications <>
Submitted on : Saturday, May 16, 2020 - 2:35:26 PM
Last modification on : Tuesday, September 14, 2021 - 10:20:08 AM

Identifiers

Citation

Fabien Amarger, Catherine Roussey, Ollivier Haemmerlé, Nathalie Hernandez, Olivier Guillaume. Muskca : un système de fusion d'ontologies fondé sur le consensus et l'estimation de la confiance. Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, Lavoisier, 2018, 32 (3), pp.313-344. ⟨10.3166/ria.32.313-344⟩. ⟨hal-02607693⟩

Share

Metrics

Record views

40