International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 38 - Number 4 |
Year of Publication: 2012 |
Authors: Tazid Ali, Palash Dutta |
10.5120/4680-6802 |
Tazid Ali, Palash Dutta . Methods to obtain basic Probability Assignment in Evidence Theory. International Journal of Computer Applications. 38, 4 ( January 2012), 46-51. DOI=10.5120/4680-6802
Dempster-Shafer Theory (DST) of Evidence is a powerful and flexible mathematical tool for handling uncertainty, impreciseness, and incomplete information. It can be used when both epistemic and aleatory uncertainties are present in the problem under consideration. The fundamental and important object of this theory of evidence is the primitive function called basic probability assignment (bpa). In the absence of empirical data, experts in related fields provide necessary information (bpa). However how to obtain BPA is still an open issue. In this paper, we propose methods to determine BPA when only the minimum, maximum and most likely values of the parameter are known. An example is illustrated to demonstrate and check the efficiency of the proposed methods. We have also developed an extended version of uncertainty measurement in evidence theory in order to calculated total uncertainty in the body of evidence obtained by the proposed methods.