Study of Spanish mining accidents using data mining techniques
Mining is an economic sector with a high number of accidents. Mines are hazardous places and workers can suffer a wide variety of injuries. Utilizing a database composed of almost 70,000 occupational accidents and fatality reports corresponding to the decade 2003–2012 in the Spanish mining sector, t...
| Autores: | , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2015 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/26427 |
| Acceso en línea: | https://hdl.handle.net/2117/26427 https://dx.doi.org/10.1016/j.ssci.2015.01.016 |
| Access Level: | acceso abierto |
| Palabra clave: | Mine safety Data mining Mine accidents Mining accidents Bayesian network Classification methods Mines -- Mesures de seguretat Mineria de dades Mines -- Accidents Àrees temàtiques de la UPC::Enginyeria civil::Enginyeria de mines Àrees temàtiques de la UPC::Economia i organització d'empreses::Seguretat industrial::Prevenció de riscos laborals |
| Sumario: | Mining is an economic sector with a high number of accidents. Mines are hazardous places and workers can suffer a wide variety of injuries. Utilizing a database composed of almost 70,000 occupational accidents and fatality reports corresponding to the decade 2003–2012 in the Spanish mining sector, the paper analyzes the main causes of those accidents. To carry out the study, powerful statistical tools have been applied, such as Bayesian classi¿ers, decision trees or contingency tables, among other data mining techniques. Statistical analyses have been performed using Weka software and behavioral patterns based on certain rules have been obtained. From these rules, some conclusions are extracted which can help to develop suitable prevention policies to reduce injuries and fatalities. |
|---|