Data Fusion of Maritime Incident Databases Based on Dempster–Shafer Theory

摘要

Although there is a huge amount of information in all kinds of marine safety databases, only a small part can be used directly. The disorganized information from different sources leads to a mixture of format and definition. This paper applies Dempster-Shafer theory of evidence (DST) to combine evidence (a piece of information that supports a claim) from different sources. The method is regarded as a generalization of the Bayesian theory, and it can avoid two difficulties in classical probability theory: handling the conflicting information and assigning prior probabilities. The work of data fusion is firstly demonstrated by a decision fusion problem of expert system. DST can provide a comprehensive result to the decision maker by combining different experts’ opinion. Secondly, the fusion of two representative maritime incident databases: GISIS (Global Integrated Shipping Information System) and ICC (International Chamber of Commerce) is conducted. Although the records of the databases have some defects such as disorder, error and contradiction, DST is still able to work effectively and calculate an uncertainty interval of incident.