Loading [MathJax]/extensions/MathZoom.js
Is entropy enough to evaluate the probability transformation approach of belief function? | IEEE Conference Publication | IEEE Xplore

Is entropy enough to evaluate the probability transformation approach of belief function?


Abstract:

In Dempster-Shafer Theory (DST) of evidence and transferable belief model (TBM), the probability transformation is necessary and crucial for decision-making. The evaluati...Show More

Abstract:

In Dempster-Shafer Theory (DST) of evidence and transferable belief model (TBM), the probability transformation is necessary and crucial for decision-making. The evaluation of the quality of the probability transformation is usually based on the entropy or the probabilistic information content (PIC) measures, which are questioned in this paper. Another alternative of probability transformation approach is proposed based on the uncertainty minimization to verify the rationality of the entropy or PIC as the evaluation criteria for the probability transformation. According to the experimental results based on the comparisons among different probability transformation approaches, the rationality of using entropy or Probabilistic Information Content (PIC) measures to evaluate probability transformation approaches is analyzed and discussed.
Date of Conference: 26-29 July 2010
Date Added to IEEE Xplore: 10 February 2011
ISBN Information:
Conference Location: Edinburgh, UK