ABSTRACT
Fundamental to supporting decision making in risky situations is a need to model the uncertainty associated with a course of action, an alternative’s uncertainty profile. In addition to this we need to be able to model the responsible agents’ decision function, their attitude with respect to different uncertain risky situations. In the real world, both these kinds of information are too complex, ill defined and imprecise to be able to be realistically modeled by conventional techniques. Here we look at new techniques arising from the modern technologies of computational intelligence and soft computing. The use of fuzzy rule-based formulations to model decision functions is investigated. We describe the role of perception-based granular probability distributions as a means of modeling the uncertainty profiles of the alternatives. Tools for evaluating rule-based decision functions in the face of perception-based uncertainty profiles are presented.
