Marine accident learning with fuzzy cognitive maps (MALFCMs) and Bayesian networks: a case study on maritime accidents

Research output: Contribution to conferencePaper

Abstract

Aiming to improve maritime safety, there is a need for a practical method that is capable of identifying the importance weightings for each contributing factor involved in accidents. Hence, Marine Accident Learning with Fuzzy Cognitive Maps (MALFCM) incorporated with Bayesian networks is suggested and applied in this study. MALFCM approach is based on the concept and principles of Fuzzy Cognitive Maps (FCMs) to represent the interrelations amongst accident contributor factors. Hence, in this study, grounding/stranding accidents were investigated with the proposed MALFCM approach. As a result, inadequate leadership and supervision, lack of training and unprofessional behavior were identified as the most probable causes of grounding accident. In addition, in the accident scenario analysis, it was observed that the lack of safety culture contributed most to the system failure based on the posterior to prior failures ratio.

Conference

Conference4th Workshop and Symposium on Safety and Integrity Management of Operations in Harsh Environments
Abbreviated titleCRISE4
CountryCanada
CitySt John's
Period15/07/1917/07/19

Fingerprint

Bayesian networks
Accidents
Electric grounding

Keywords

  • maritime accidents
  • maritime safety
  • Maritime Accident Learning with Fuzzy Cognitive Maps (MALFCMs)
  • human factors
  • Bayesian networks

Cite this

Navas de Maya, B., Babaleye, A., & Kurt, R. E. (2019). Marine accident learning with fuzzy cognitive maps (MALFCMs) and Bayesian networks: a case study on maritime accidents. Paper presented at 4th Workshop and Symposium on Safety and Integrity Management of Operations in Harsh Environments, St John's, Canada.
Navas de Maya, Beatriz ; Babaleye, Ahmed ; Kurt, Rafet Emek. / Marine accident learning with fuzzy cognitive maps (MALFCMs) and Bayesian networks : a case study on maritime accidents. Paper presented at 4th Workshop and Symposium on Safety and Integrity Management of Operations in Harsh Environments, St John's, Canada.9 p.
@conference{02a69f8edee24cf99dcfcd171bc7e98d,
title = "Marine accident learning with fuzzy cognitive maps (MALFCMs) and Bayesian networks: a case study on maritime accidents",
abstract = "Aiming to improve maritime safety, there is a need for a practical method that is capable of identifying the importance weightings for each contributing factor involved in accidents. Hence, Marine Accident Learning with Fuzzy Cognitive Maps (MALFCM) incorporated with Bayesian networks is suggested and applied in this study. MALFCM approach is based on the concept and principles of Fuzzy Cognitive Maps (FCMs) to represent the interrelations amongst accident contributor factors. Hence, in this study, grounding/stranding accidents were investigated with the proposed MALFCM approach. As a result, inadequate leadership and supervision, lack of training and unprofessional behavior were identified as the most probable causes of grounding accident. In addition, in the accident scenario analysis, it was observed that the lack of safety culture contributed most to the system failure based on the posterior to prior failures ratio.",
keywords = "maritime accidents, maritime safety, Maritime Accident Learning with Fuzzy Cognitive Maps (MALFCMs), human factors, Bayesian networks",
author = "{Navas de Maya}, Beatriz and Ahmed Babaleye and Kurt, {Rafet Emek}",
year = "2019",
month = "7",
day = "15",
language = "English",
note = "4th Workshop and Symposium on Safety and Integrity Management of Operations in Harsh Environments, CRISE4 ; Conference date: 15-07-2019 Through 17-07-2019",

}

Navas de Maya, B, Babaleye, A & Kurt, RE 2019, 'Marine accident learning with fuzzy cognitive maps (MALFCMs) and Bayesian networks: a case study on maritime accidents' Paper presented at 4th Workshop and Symposium on Safety and Integrity Management of Operations in Harsh Environments, St John's, Canada, 15/07/19 - 17/07/19, .

Marine accident learning with fuzzy cognitive maps (MALFCMs) and Bayesian networks : a case study on maritime accidents. / Navas de Maya, Beatriz; Babaleye, Ahmed; Kurt, Rafet Emek.

2019. Paper presented at 4th Workshop and Symposium on Safety and Integrity Management of Operations in Harsh Environments, St John's, Canada.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Marine accident learning with fuzzy cognitive maps (MALFCMs) and Bayesian networks

T2 - a case study on maritime accidents

AU - Navas de Maya, Beatriz

AU - Babaleye, Ahmed

AU - Kurt, Rafet Emek

PY - 2019/7/15

Y1 - 2019/7/15

N2 - Aiming to improve maritime safety, there is a need for a practical method that is capable of identifying the importance weightings for each contributing factor involved in accidents. Hence, Marine Accident Learning with Fuzzy Cognitive Maps (MALFCM) incorporated with Bayesian networks is suggested and applied in this study. MALFCM approach is based on the concept and principles of Fuzzy Cognitive Maps (FCMs) to represent the interrelations amongst accident contributor factors. Hence, in this study, grounding/stranding accidents were investigated with the proposed MALFCM approach. As a result, inadequate leadership and supervision, lack of training and unprofessional behavior were identified as the most probable causes of grounding accident. In addition, in the accident scenario analysis, it was observed that the lack of safety culture contributed most to the system failure based on the posterior to prior failures ratio.

AB - Aiming to improve maritime safety, there is a need for a practical method that is capable of identifying the importance weightings for each contributing factor involved in accidents. Hence, Marine Accident Learning with Fuzzy Cognitive Maps (MALFCM) incorporated with Bayesian networks is suggested and applied in this study. MALFCM approach is based on the concept and principles of Fuzzy Cognitive Maps (FCMs) to represent the interrelations amongst accident contributor factors. Hence, in this study, grounding/stranding accidents were investigated with the proposed MALFCM approach. As a result, inadequate leadership and supervision, lack of training and unprofessional behavior were identified as the most probable causes of grounding accident. In addition, in the accident scenario analysis, it was observed that the lack of safety culture contributed most to the system failure based on the posterior to prior failures ratio.

KW - maritime accidents

KW - maritime safety

KW - Maritime Accident Learning with Fuzzy Cognitive Maps (MALFCMs)

KW - human factors

KW - Bayesian networks

UR - https://www.mun.ca/engineering/crise/workshops/crise4.php

M3 - Paper

ER -

Navas de Maya B, Babaleye A, Kurt RE. Marine accident learning with fuzzy cognitive maps (MALFCMs) and Bayesian networks: a case study on maritime accidents. 2019. Paper presented at 4th Workshop and Symposium on Safety and Integrity Management of Operations in Harsh Environments, St John's, Canada.