Identification of risk influential factors for fishing vessel accidents using claims data from fishery mutual insurance association

This research aims to identify and analyze the significant risk factors contributing to accidents involving fishing vessels, a crucial step towards enhancing safety and promoting sustainable practices in the fishing industry. Using a data-driven Bayesian network (BN) model that incorporates feature...

Descripción completa

Detalles Bibliográficos
Autores: Wang, Fang, Du, Weijie, Feng, Hongxiang, Ye, Yun, Grifoll Colls, Manel|||0000-0003-4260-6732, Liu, Guiyun, Zheng, Pengjun
Tipo de recurso: artículo
Fecha de publicación:2023
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:2117/405158
Acceso en línea:https://hdl.handle.net/2117/405158
https://dx.doi.org/10.3390/su151813427
Access Level:acceso abierto
Palabra clave:Fishing boats--Accidents
Fishers--Accidents
Employers’ liability insurance
Fishing vessel
Accident analysis
Random forest
Bayesian network
Feature selection
Embarcacions de pesca--Accidents
Pescadors--Accidents
Assegurances d'accidents de treball
Àrees temàtiques de la UPC::Nàutica::Seguretat marítima::Accidents marítims
Àrees temàtiques de la UPC::Enginyeria agroalimentària::Pesca::Pesca marina
Descripción
Sumario:This research aims to identify and analyze the significant risk factors contributing to accidents involving fishing vessels, a crucial step towards enhancing safety and promoting sustainable practices in the fishing industry. Using a data-driven Bayesian network (BN) model that incorporates feature selection through the random forest (RF) method, we explore these key factors and their interconnected relationships. A review of past academic studies and accident investigation reports from the Fishery Mutual Insurance Association (FMIA) revealed 17 such factors. We then used the random forest model to rank these factors by importance, selecting 11 critical ones to build the Bayesian network model. The data-driven Bayesian network (BN) model is further utilized to delve deeper into the central factors influencing fishing vessel accidents. Upon validation, the study results show that incorporating the random forest feature selection method enhances the simplicity, reliability, and precision of the BN model. This finding is supported by a thorough performance evaluation and scenario analysis.