Navigation safety is a priority both at European and global level. Despite the important progress made over the years, sea accidents remain a major concern and much work is still needed to enhance maritime safety. Knowing the causes and precursors of past accidents is essential to identify the elements on which to intervene to improve safety and reduce the possibility of an accident to occur again. In this study, 1.079 sea accidents from the International Maritime Organization (IMO) database are analyzed using Semi-supervised Recursively Partitioned Mixture Models in an attempt to identify and categorize causal themes from accident data. Special attention is devoted to the human element, which is widely recognized as a primary or precursory cause in most accidents.

Investigating the Role of the Human Element in Maritime Accidents using Semi-Supervised Hierarchical Methods

Fadda Paolo;Fancello Gianfranco;Frigau Luca;Mandas Marco;Medda Andrea;Mola Francesco;Pelligra Vittorio;Porta Mattia;Serra Patrizia
2021-01-01

Abstract

Navigation safety is a priority both at European and global level. Despite the important progress made over the years, sea accidents remain a major concern and much work is still needed to enhance maritime safety. Knowing the causes and precursors of past accidents is essential to identify the elements on which to intervene to improve safety and reduce the possibility of an accident to occur again. In this study, 1.079 sea accidents from the International Maritime Organization (IMO) database are analyzed using Semi-supervised Recursively Partitioned Mixture Models in an attempt to identify and categorize causal themes from accident data. Special attention is devoted to the human element, which is widely recognized as a primary or precursory cause in most accidents.
2021
Sea Accidents; Clustering; Sea Safety; Human Factors; Hierarchical Methods
File in questo prodotto:
File Dimensione Formato  
Paolo Fadda et al_Transportation Research Procedia.pdf

accesso aperto

Descrizione: articolo online
Tipologia: versione editoriale
Dimensione 665.35 kB
Formato Adobe PDF
665.35 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/307510
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 17
  • ???jsp.display-item.citation.isi??? ND
social impact