Extrapolation of fuzzy values from incomplete data bases |
| |
Authors: | Inaki Arrazola Agn s Plainfoss Henri Prade and Claudette Testemale |
| |
Affiliation: | Laboratoire L.S.I., Université Paul Sabatier, 31062, Toulouse Cédex, France |
| |
Abstract: | This paper presents different approaches which enable a data base management system to obtain a plausible fuzzy estimate for an attribute value of an item for which the information is not explicitly stored in the data base. This can be made either by a kind of analogical reasoning from information about particular items or by means of expert rules which specify the (fuzzy) sets of possible values of the attribute under consideration, for various classes of items. Another kind of expert rules enables the system to compute an estimate from the attribute value of another item provided that, in other respects, this latter item sufficiently resembles the item, the value of which we are interested in; then these expert rules are used either for controlling the analogical reasoning process or for enlarging the scope of application of the first kind of expert rules. The different approaches are discussed in the framework of possibility theory. |
| |
Keywords: | Data base incompleteness uncertainty fuzzy information analogical reasoning expert rule possibility theory |
本文献已被 ScienceDirect 等数据库收录! |