Extended PCR Rules for Dynamic Frames

Florentin Smarandache (1) , Jean Dezert (2)

1 Department of Mathematics and Statistics [Albuquerque]
2 ONERA - The French Aerospace Lab [Palaiseau]

In most of classical fusion problems modeled from belief functions, the frame of discernment is considered as static. This means that the set of elements in the frame and the underlying integrity constraints of the frame are fixed forever and they do not change with time. In some applications, like in target tracking for example, the use of such invariant frame is not very appropriate because it can truly change with time. So it is necessary to adapt the Proportional Conflict Redistribution fusion rules (PCR5 and PCR6) for working with dynamical frames. In this paper, we propose an extension of PCR5 and PCR6 rules for working in a frame having some non-existential integrity constraints. Such constraints on the frame can arise in tracking applications by the destruction of targets for example. We show through very simple examples how these new rules can be used for the belief revision process.

Mots clés: Information fusion; DSmT; integrity constraints; belief functions

Domaines: Intelligence artificielle [cs.AI]

Florentin Smarandache, Jean Dezert. Extended PCR Rules for Dynamic Frames. Fusion 2012 - 15th International Conference on Information Fusion, Jul 2012, Singapour, Singapore. ⟨hal-00720417⟩