This paper describes a generic decision support architecture (DSA) for supporting maritime operations. The system’s core is a decision support tool (DST), consisting of a risk assessment framework aimed at computing risks related to each action that can be performed on the maritime operation under consideration. In particular, the risks are computed for each action and for each class describing the forecasted condition of the environment (favourable, marginal, and unfavourable), according to their posterior probabilities. A fuzzy classifier is used to estimate such probabilities, starting from the forecast of the environmental variables affecting the operation. A distinctive feature of the implemented DSA is its flexibility: many different types of operations can be handled (amphibious landing, autonomous underwater vehicle (AUV) recovery, etc.) with no architectural change. The architecture has been tested both on synthetic data and on real data, the latter collected during two cruises carried out in Adriatic Sea and Ligurian Sea.
A Generic Decision Support Architecture for Maritime Operations
COCOCCIONI, MARCO;
2010-01-01
Abstract
This paper describes a generic decision support architecture (DSA) for supporting maritime operations. The system’s core is a decision support tool (DST), consisting of a risk assessment framework aimed at computing risks related to each action that can be performed on the maritime operation under consideration. In particular, the risks are computed for each action and for each class describing the forecasted condition of the environment (favourable, marginal, and unfavourable), according to their posterior probabilities. A fuzzy classifier is used to estimate such probabilities, starting from the forecast of the environmental variables affecting the operation. A distinctive feature of the implemented DSA is its flexibility: many different types of operations can be handled (amphibious landing, autonomous underwater vehicle (AUV) recovery, etc.) with no architectural change. The architecture has been tested both on synthetic data and on real data, the latter collected during two cruises carried out in Adriatic Sea and Ligurian Sea.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.