Aggregations of Subjective Probabilities Based on Logical Information Source Model and of Possibilistic CFs Using Dempster's Rule

The paper reviews an aggregation of multiple possibilities for a hypothesis based on a logical information source model proposed recently, and applies the approach to a new aggregation of subjective probabilities. It also recalls an old and controversial uncertainty representation called Certainty Factors (CFs), and reinterprets them as another representation of possibilities. Then, a new aggregation rule of CFs, or equivalently a new combination rule of possibilities is proposed, which employs Dempster's rule of combination as well as uncertainty transformation and approximation between possibility distributions and mass functions.