Cautious Conjunctive Merging of Belief Functions

Authors:
Sebastien Destercke;Didier Dubois;Eric Chojnacki
Affiliations:
Institut de Radioprotection et de Sûreté Nucléaire, DPAM, SEMIC, LIMSI, Cadarache, France and Toulouse Institute of Research in Computer Science (IRIT), Toulouse, France;Toulouse Institute of Research in Computer Science (IRIT), Toulouse, France;Institut de Radioprotection et de Sûreté Nucléaire, DPAM, SEMIC, LIMSI, Cadarache, France
Venue:
ECSQARU '07 Proceedings of the 9th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty
Year:
2007

Citing 6
Cited 2

Fuzzy set connectives as combinations of belief structures

Information Sciences: an International Journal
The transferable belief model

Artificial Intelligence
Combination of compatible belief functions and relation of specificity

Advances in the Dempster-Shafer theory of evidence
Analyzing the combination of conflicting belief functions

Information Fusion
The canonical decomposition of a weighted belief

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Practical representations of incomplete probabilistic knowledge

Computational Statistics & Data Analysis

Can the Minimum Rule of Possibility Theory Be Extended to Belief Functions?

ECSQARU '09 Proceedings of the 10th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty
Belief functions combination without the assumption of independence of the information sources

International Journal of Approximate Reasoning

Quantified Score

Hi-index	0.01

Visualization

Abstract

When merging belief functions, Dempster rule of combination is justified only when information sources can be considered as independent. When this is not the case, one must find out a cautious merging rule that adds a minimal amount of information to the inputs. Such a rule is said to follow the principle of minimal commitment. Some conditions it should comply with are studied. A cautious merging rule based on maximizing expected cardinality of the resulting belief function is proposed. It recovers the minimum operation when specialized to possibility distributions. This form of the minimal commitment principle is discussed, in particular its discriminating power and its justification when some conflict is present between the belief functions.