Ana Kuzmanić Skelin, Lea Vojković, Dani Mohović, D. Zec
{"title":"Weight of Evidence Approach to Maritime Accident Risk Assessment Based on Bayesian Network Classifier","authors":"Ana Kuzmanić Skelin, Lea Vojković, Dani Mohović, D. Zec","doi":"10.7225/toms.v10.n02.w07","DOIUrl":null,"url":null,"abstract":"Probabilistic maritime accident models based on Bayesian Networks are typically built upon the data available in accident records and the data obtained from human experts knowledge on accident. The drawback of such models is that they do not take explicitly into the account the knowledge on non-accidents as would be required in the probabilistic modelling of rare events. Consequently, these models have difficulties with delivering interpretation of influence of risk factors and providing sufficient confidence in the risk assessment scores. In this work, modelling and risk score interpretation, as two aspects of the probabilistic approach to complex maritime system risk assessment, are addressed. First, the maritime accident modelling is posed as a classification problem and the Bayesian network classifier that discriminates between accident and non-accident is developed which assesses state spaces of influence factors as the input features of the classifier. Maritime accident risk are identified as adversely influencing factors that contribute to the accident. Next, the weight of evidence approach to reasoning with Bayesian network classifier is developed for an objective quantitative estimation of the strength of factor influence, and a weighted strength of evidence is introduced. Qualitative interpretation of strength of evidence for individual accident influencing factor, inspired by Bayes factor, is defined. The efficiency of the developed approach is demonstrated within the context of collision of small passenger vessels and the results of collision risk assessments are given for the environmental settings typical in Croatian nautical tourism. According to the results obtained, recommendations for navigation safety during high density traffic have been distilled.","PeriodicalId":42576,"journal":{"name":"Transactions on Maritime Science-ToMS","volume":"23 1","pages":""},"PeriodicalIF":0.8000,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transactions on Maritime Science-ToMS","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.7225/toms.v10.n02.w07","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MARINE","Score":null,"Total":0}
引用次数: 1
Abstract
Probabilistic maritime accident models based on Bayesian Networks are typically built upon the data available in accident records and the data obtained from human experts knowledge on accident. The drawback of such models is that they do not take explicitly into the account the knowledge on non-accidents as would be required in the probabilistic modelling of rare events. Consequently, these models have difficulties with delivering interpretation of influence of risk factors and providing sufficient confidence in the risk assessment scores. In this work, modelling and risk score interpretation, as two aspects of the probabilistic approach to complex maritime system risk assessment, are addressed. First, the maritime accident modelling is posed as a classification problem and the Bayesian network classifier that discriminates between accident and non-accident is developed which assesses state spaces of influence factors as the input features of the classifier. Maritime accident risk are identified as adversely influencing factors that contribute to the accident. Next, the weight of evidence approach to reasoning with Bayesian network classifier is developed for an objective quantitative estimation of the strength of factor influence, and a weighted strength of evidence is introduced. Qualitative interpretation of strength of evidence for individual accident influencing factor, inspired by Bayes factor, is defined. The efficiency of the developed approach is demonstrated within the context of collision of small passenger vessels and the results of collision risk assessments are given for the environmental settings typical in Croatian nautical tourism. According to the results obtained, recommendations for navigation safety during high density traffic have been distilled.
期刊介绍:
ToMS is a scientific journal with international peer review which publishes papers in the following areas: ~ Marine Engineering, ~ Navigation, ~ Safety Systems, ~ Marine Ecology, ~ Marine Fisheries, ~ Hydrography, ~ Marine Automation and Electronics, ~ Transportation and Modes of Transport, ~ Marine Information Systems, ~ Maritime Law, ~ Management of Marine Systems, ~ Marine Finance, ~ Bleeding-Edge Technologies, ~ Multimodal Transport, ~ Psycho-social and Legal Aspects of Long-term Working Aboard. The journal is published in English as an open access journal, and as a classic paper journal (in limited editions). ToMS aims to present best maritime research from South East Europe, particularly the Mediterranean area. Articles will be double-blind reviewed by three reviewers. With the intention of providing an international perspective at least one of the reviewers will be from abroad. ToMS also promotes scientific collaboration with students and has a section titled Students’ ToMS. These papers also undergo strict peer reviews. Furthermore, the Journal publishes short reviews on significant papers, books and workshops in the fields of maritime science.