Port security risk probability prediction by Bayesian network

In view of the difficulty of determining the probability of port security risk in current port security risk assessment, a Bayesian network based port security risk probability prediction model is proposed. Based on the analysis of 175 cases of port security incidents and expert opinions, the indicators affecting port security risk probability are analyzed from two aspects of threat and vulnerability, and mapped into Bayesian network structure. The prior probability is determined by the accident data generated by the conditional table and the fuzzy theory, and the conditional probability is determined by the Best Worst Method. Finally, this model is used to determine the risk probability of a potential security incident in a domestic passenger terminal, and is compared with the security risk probability determination method in the Basic Standard for Identification, Evaluation and Control of Safety Production Risk in Highway and Waterway Industry（Trial）. The results show that the model can effectively predict the risk probability of port security incidents and provide support for port security risk assessment.