Show simple item record

dc.contributoren-US
dc.creatorMartín, José Enrique; Departamento de Ingeniería de los Recursos Naturales y Medio Ambiente Universidad de Vigo, Lagoas Marcosende, 36310 Vigo
dc.creatorTaboada-García, Javier; Departamento de Ingeniería de los Recursos Naturales y Medio Ambiente Universidad de Vigo Lagoas Marcosende, 36310 Vigo
dc.creatorGerassis, Saki; Departamento de Ingeniería de los Recursos Naturales y Medio Ambiente Universidad de Vigo Lagoas Marcosende, 36310 Vigo
dc.creatorSaavedra, Ángeles; Departamento de Estadística e Investigación Operativa, Universidad de Vigo Lagoas Marcosende, 36310 Vigo
dc.creatorMartínez-Alegría, Roberto; Departamento de Enseñanzas Técnicas, Universidad Europea Miguel de Cervantes C/Padre Julio Chevalier, nº 2, 47012 Valladolid
dc.date2017-09-01
dc.date.accessioned2019-05-03T12:20:05Z
dc.date.available2019-05-03T12:20:05Z
dc.identifierhttp://revistadelaconstruccion.uc.cl/index.php/rdlc/article/view/1041
dc.identifier.urihttp://revistaschilenas.uchile.cl/handle/2250/84071
dc.descriptionDOI: 10.7764/RDLC.16.3.439AbstractAnalysis of accidents using Bayesian networks links certain predictor factors with other target factors representing types of accidents under study. Databases of real accident reports are typically used for both designing and training networks, which inevitably skews future inferences. Inferences are also limited because such databases do not usually include data on situations where accidents have not occurred. Inferences can thus be made about the occurrence of an accident, but not about specific types of accident. We describe a novel Bayesian network strategy for the field of occupational risk prevention which, extracting data from a database that includes situations where no accident has occurred, quantifies the influence and interactions of factors. It also allows particular accident types to be studied individually, thereby highlighting not only the correlation but also the causal relationship between work setting and accident risk.  en-US
dc.formatapplication/pdf
dc.languageeng
dc.publisherPONTIFICIA UNIVERSIDAD CATOLICA DE CHILEen-US
dc.relationhttp://revistadelaconstruccion.uc.cl/index.php/rdlc/article/view/1041/216
dc.sourceRevista de la Construcción. Journal of Construction; Vol 16, No 3 (2017): Revista de la Construcción. Journal of Construction; 439-446en-US
dc.source0718-915X
dc.source0717-7925
dc.subjecten-US
dc.subjectCivil engineering, information deficit, Bayesian networks, workplace accident, model reduction.en-US
dc.titleBayesian network analysis of accident risk in information-deficient scenariosen-US
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion
dc.typePeer-reviewed Articleen-US


This item appears in the following Collection(s)

Show simple item record