Title :
On the robustness of Dempster´s rule of combination
Author :
Hau, Hai-Yen ; Kashyap, R.L.
Author_Institution :
Grumman Data Syst., Woodbury, NY, USA
Abstract :
It is demonstrated by example that Dempster´s rule of combination is not robust when combining highly conflicting belief functions. It is shown that Shafer´s (1983) discounted belief functions also suffer from this lack of robustness with respect to small perturbations in the discount factor. A modified version of Dempster´s rule is proposed to remedy this difficulty
Keywords :
artificial intelligence; fuzzy logic; Dempster´s rule of combination; discount factor; discounted belief functions; highly conflicting belief functions; perturbations; robustness; Artificial intelligence; Bayesian methods; Data systems; Expert systems; Knowledge management; Robustness; Uncertainty;
Conference_Titel :
Tools for Artificial Intelligence, 1989. Architectures, Languages and Algorithms, IEEE International Workshop on
Conference_Location :
Fairfax, VA
Print_ISBN :
0-8186-1984-8
DOI :
10.1109/TAI.1989.65370
