2003/05/16 by Johan Schubert
Computer Science · #cs.AI #cs.NE
published as in Proceedings of the Ninth International Conference on Information Processing and Management of Uncertainty in Knowledge-based Systems (IPMU'02), pp. 571-578, Annecy, France, 1-5 July 2002 · 8 pages, 3 figures
arxiv created 2003/05/16 · arxiv updated 2009/11/30
In this paper we develop a method for clustering belief functions based on attracting and conflicting metalevel evidence. Such clustering is done when the belief functions concern multiple events, and all belief functions are mixed up. The clustering process is used as the means for separating the belief functions into subsets that should be handled independently. While the conflicting metalevel evidence is generated internally from pairwise conflicts of all belief functions, the attracting metalevel evidence is assumed given by some external source.