Mining Contextual Rules to Predict Asbestos in Buildings

In the context of work conducted at CSTB (French Scientific and Technical Center for Building), need a tool providing assistance in identification asbestos-containing materials buildings was identified. To this end, we have developed an approach, named CRA-Miner, that mines logical rules from knowledge graph describes asbestos diagnoses. Since specific product used is not defined, CRA-Miner considers temporal data, types, contextual information to find set candidate maximizes confidence. These can then be identify building elements may contain those are asbestos-free. The experiments on RDF provided by show proposed approach promising satisfactory accuracy obtained.