Skip to Main content Skip to Navigation
Conference papers

Découverte de règles contextuelles pour prédire la présence d’amiante dans les bâtiments

Abstract : The Scientific and Technical Center for Building (CSTB) was asked to develop a tool to help identify materials containing asbestos in buildings. In this context, we have developed an approach, named CRA-Miner, which uses inductive logic programming (ILP) techniques to discover logic rules from a data graph describing buildings and asbestos diagnostics. Since the reference of the specific products used during construction is never specified, CRAMiner considers the temporal data, the types of products and the contextual information to find the set of candidate rules which can then be used to deduce the presence of asbestos in construction elements. The experiments carried out on the knowledge graph provided by CSTB show that a promising F-Measure can be obtained.
Complete list of metadata

https://hal-emse.ccsd.cnrs.fr/emse-03260573
Contributor : Florent Breuil <>
Submitted on : Tuesday, June 15, 2021 - 9:53:37 AM
Last modification on : Friday, July 16, 2021 - 10:07:23 AM

File

actes_IC_CH_PFIA2021_81-88.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : emse-03260573, version 1

Citation

Thamer Mecharnia, Lydia Chibout Khelifa, Fayçal Hamdi, Nathalie Pernelle, Celine Rouveirol. Découverte de règles contextuelles pour prédire la présence d’amiante dans les bâtiments. Journées Francophones d'Ingénierie des Connaissances (IC) Plate-Forme Intelligence Artificielle (PFIA'21), Jun 2021, Bordeaux, France. pp 73-80. ⟨emse-03260573⟩

Share

Metrics

Record views

46

Files downloads

14