Bayesian network analysis of accident risk in information-deficient scenarios

Abstract: Analysis 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. Inf...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Martín,José Enrique, Taboada-García,Javier, Gerassis,Saki, Saavedra,Ángeles, Martínez-Alegría,Roberto
Lenguaje:	English
Publicado:	Escuela de Construcción Civil, Pontificia Universidad Católica de Chile 2017
Materias:	Civil engineering information deficit Bayesian networks workplace accident model reduction.
Acceso en línea:	http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-915X2017000300439
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:scielo:S0718-915X2017000300439
record_format	dspace
spelling	oai:scielo:S0718-915X20170003004392018-03-05Bayesian network analysis of accident risk in information-deficient scenariosMartín,José EnriqueTaboada-García,JavierGerassis,SakiSaavedra,ÁngelesMartínez-Alegría,Roberto Civil engineering information deficit Bayesian networks workplace accident model reduction. Abstract: Analysis 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.info:eu-repo/semantics/openAccessEscuela de Construcción Civil, Pontificia Universidad Católica de ChileRevista de la construcción v.16 n.3 20172017-09-01text/htmlhttp://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-915X2017000300439en10.7764/rdlc.16.3.439
institution	Scielo Chile
collection	Scielo Chile
language	English
topic	Civil engineering information deficit Bayesian networks workplace accident model reduction.
spellingShingle	Civil engineering information deficit Bayesian networks workplace accident model reduction. Martín,José Enrique Taboada-García,Javier Gerassis,Saki Saavedra,Ángeles Martínez-Alegría,Roberto Bayesian network analysis of accident risk in information-deficient scenarios
description	Abstract: Analysis 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.
author	Martín,José Enrique Taboada-García,Javier Gerassis,Saki Saavedra,Ángeles Martínez-Alegría,Roberto
author_facet	Martín,José Enrique Taboada-García,Javier Gerassis,Saki Saavedra,Ángeles Martínez-Alegría,Roberto
author_sort	Martín,José Enrique
title	Bayesian network analysis of accident risk in information-deficient scenarios
title_short	Bayesian network analysis of accident risk in information-deficient scenarios
title_full	Bayesian network analysis of accident risk in information-deficient scenarios
title_fullStr	Bayesian network analysis of accident risk in information-deficient scenarios
title_full_unstemmed	Bayesian network analysis of accident risk in information-deficient scenarios
title_sort	bayesian network analysis of accident risk in information-deficient scenarios
publisher	Escuela de Construcción Civil, Pontificia Universidad Católica de Chile
publishDate	2017
url	http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-915X2017000300439
work_keys_str_mv	AT martinjoseenrique bayesiannetworkanalysisofaccidentriskininformationdeficientscenarios AT taboadagarciajavier bayesiannetworkanalysisofaccidentriskininformationdeficientscenarios AT gerassissaki bayesiannetworkanalysisofaccidentriskininformationdeficientscenarios AT saavedraangeles bayesiannetworkanalysisofaccidentriskininformationdeficientscenarios AT martinezalegriaroberto bayesiannetworkanalysisofaccidentriskininformationdeficientscenarios
_version_	1714206286368735232

Bayesian network analysis of accident risk in information-deficient scenarios

Ejemplares similares