AN ALGORITHMIC APPROACH TO COMBINING BELIEF FUNCTIONS

Methods of combination are used to synthesize pieces of evidence of eq ual standing that represent different aspects of a specific system abo ut which a diagnosis is to be made. Combination is distinct from conse nsus, when complete diagnoses rendered by different knowledge sources require synthesis, and conditionalization, where pieces of evidence to be synthesized have dissymmetric relationships to each other. The Dem pster-Shafer Rule is the quintessential combination method. However, i t has been criticized for its inability to handle inconsistent pieces of evidence and for the way it focuses the weight of evidence. This ar ticle presents an alternative combination method that is capable of ha ndling inconsistent evidence and relates evidence focusing to the amou nt of information resident in pieces of evidence. The method is capabl e of combining belief functions. Future research should address extend ing the method to the combination of a broad class of imprecise probab ility functions. (C) 1996 John Wiley & Sons, Inc.