Combining evidences by means of the entropy maximization principle

Works have investigated the problem of the conflict redistribution in the fusion rules of evidence theories. As a consequence of these works, many new rules have been proposed. Now, there is not a clear theoretical criterion for a choice of a rule instead another. The present paper proposes a new theoretically grounded rule, based on a new concept of sensor independence. This new rule avoids the conflict redistribution, by an adaptive combination of the beliefs. Both the logical grounds and the algorithmic implementation are considered.