Mathematical theory of evidence in maritime traffic engineering

Nowadays operator at maritime traffic monitoring station is assumed to have access to a great amount of data. Information come from different sources and the data are generated by multiple of sensors. Multiple sources of data create challenge regarding data association. The challenge is met by data fusion. By means of fusion, different sources of information are combined to arrive at proper final decision. Ship's presence within a confined area defines a non-empty bounded closed interval. It can be denoted by the earliest and latest bounds of the closed time interval at a given possibility level. To assess situation within any confined region one should take into account total of safety factors of all ships present within forecast imprecise slots of time. Safety factors enable vessels' classification regarding potential consequences of an accident. In general approach environmentally dangerous freight and huge tonnage increase the factor. Safety factors are treated as fuzzy, imprecise values. Small ranges of values are assigned to small craft without dangerous cargo. The largest intervals are reserved for huge crude carriers. Associated data enable the VTS operator to approximate congestion for each restricted and considered as important areas. To forecast and assess situation within such areas all ships are to be identified and classified. The process usually involves uncertainty, ambiguity and partiality in available evidence. The new AIS technology itself causes ambiguity with respect to identification of crafts. Published statistics point at incorrect data transferred in the system. Therefore partial evidence is to be taken into account while identifying objects. Dempster-Shafer reasoning is helpful when combining evidence in order to refine objects. Situation in which one spotted new target and tries to find out what ship this could be is considered. Fuzzy evidence embraced within frame of discernment and related to this identification case will be assumed.