Information fusion for natural hazards in mountains

Jean-Marc Tacnet, Mireille Batton-Hubert, Jean Dezert
2009 Advances and Applications of DSmT for Information Fusion (Collected works)   unpublished
From a real case application based on snow-avalanche risk management, an integrated framework mixing evidential reasoning and multi-criteria decision analysis (ER-MCDA) is proposed. This methodology considers a simplified decision sorting problem based on qualitative and quantitative criteria on which more or less reliable sources provide uncertain and imprecise evaluations. The Analytical Hierarchy Process (AHP) is used both to model the problem in a conceptual way and to elicit preferences
more » ... icit preferences between key criteria. Fuzzy Sets and Possibilities theories are used to transform quantitative and qualitative criteria into a common frame for Dempster-Shafer Theory (DST) and Dezert-Smarandache Theory (DSmT). It is shown that DSmT offers an interesting framework to take incomplete information into account and we use it for decision-making. Evidential reasoning allows merging different uncertain and incomplete pieces of information to identify the sensitivity of an avalanche prone area and to determine an avalanche hazard map. This approach emphasizes some implementation guidelines based on a Unified Modeling Language (UML) of the problem. We point out also some important issues of information fusion such as basic belief assignment elicitation, conflict identification, fusion rules choice and results validation. An UML class diagram using a composite pattern diagram [Gamma et al. 1995] can represent this hierarchical structure as described in (see Fig. 23 .21).