Learning from near misses has a large potential for improving operations especially in high-risk sectors, such as Seveso industries. A comprehensive analysis of near miss reports requires processing a large volume of data from various sources, which are not standardized and seemingly disconnected from each other. A knowledge graph is here used to provide a comprehensive safety perspective to near miss data. In particular, this paper presents an analysis of a knowledge graph for near miss reports with the objective to measure systematically their completeness based on an integrated multi-criteria decision-making technique. The reports completeness fosters a meta-analysis of available data, highlighting systems’ strengths and vulnerabilities, as well as disseminating best practices for industry stakeholders.
Knowledge in graphs. Investigating the completeness of industrial near miss reports / Simone, F.; Ansaldi, S. M.; Agnello, P.; Di Gravio, G.; Patriarca, R.. - In: SAFETY SCIENCE. - ISSN 1879-1042. - 168:(2023). [10.1016/j.ssci.2023.106305]
Knowledge in graphs. Investigating the completeness of industrial near miss reports
Simone F.
Primo
;Di Gravio G.;Patriarca R.Ultimo
2023
Abstract
Learning from near misses has a large potential for improving operations especially in high-risk sectors, such as Seveso industries. A comprehensive analysis of near miss reports requires processing a large volume of data from various sources, which are not standardized and seemingly disconnected from each other. A knowledge graph is here used to provide a comprehensive safety perspective to near miss data. In particular, this paper presents an analysis of a knowledge graph for near miss reports with the objective to measure systematically their completeness based on an integrated multi-criteria decision-making technique. The reports completeness fosters a meta-analysis of available data, highlighting systems’ strengths and vulnerabilities, as well as disseminating best practices for industry stakeholders.| File | Dimensione | Formato | |
|---|---|---|---|
|
Simone_Knowledge2023.pdf
accesso aperto
Note: https://doi.org/10.1016/j.ssci.2023.106305
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Creative commons
Dimensione
4.47 MB
Formato
Adobe PDF
|
4.47 MB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
