Adding decision rule to the Shafer-Logan algorithm for hierarchical identity information fusion

The Dempster-Shafer evidential theory is used in the form of the Shafer-Logan algorithm for fast computation of information that is hierarchically structured. A Shafer-Logan algorithm is suitable for implementation because of the hierarchical nature of the evidence which reduces the calculations from exponential to linear time in proportion to the number of nodes in the tree. We present the main equations of the Shafer-Logan algorithm and give the flowchart for its implementation. We then add a decision rule based on the theory of utility. This decision rule offers a good way to take into account the hierarchical structure of the data, giving variable costs to nodes (propositions) depending on their level in the tree. Moreover, because of the form of the present quantities, a recursive computation is allowed which can be integrated as a last stage of the Shafer-Logan algorithm.