A simplified technique for using necessity-possibility measures

A new technique o f uncertainty management in expert systems is proposed. It is suggested that the possibility theory-based treatment o f uncertainty (developed by D. Dubois and H. Prade) in inference engines be simplified by using a combination o f possibility and necessity measures, namely N + FI 1, rather than using the possibility measure 17 and the necessity measure N separately. This combination is denoted by V, and its range is [ 1, 1]. First it is explained how this measure V is derived f rom the original necessity-possibility measures through a one-to-one function, and the meaning o f V is shown precisely. Then the paper describes the adaptation o f the different uncertainty propagation and combination methods o f the Dubois-Prade model to the "'newly'" defined measure. In this conversion the implicit behavior o f each procedure is shown, along with its connection with other uncertainty resolution methods. Particularly important is the fact that none o f the advantages o f the Dubois-Prade model are lost, especially in the handling o f fuzzy facts. This is so because at any given moment it is possible to work with either V or the necessity-possibility pair. The proposed uncertainty resolution method offers distinct advantages over previous models, such as certainty factors o f MYCIN.