Department of Computer Engineering and IT,Tarbiat Modares University
Abstract
So far, most of the evidential distance and similarity measures proposed in the Dempster-
Shafer theory literature have been based on the basic belief assignment function, so as the belief and
plausibility functions as two main results of the theory are not directly used in this regard. In this paper,
a new evidential distance measure is proposed based on these functions according to nearest neighborhood
concept. After assigning basic belief values to propositions and constructing the belief and plausibility
functions or the belief interval, this evidential distance measure compares the similarity between the
unknown pattern and class belief intervals. For this purpose, we rst acquire the belief and plausibility
functions or the belief intervals and then the distance between the belief intervals of uncertain pattern
feature vectors and samples are calculated. We applied this novel distance measure to the bacillus colonies
recognition and coronary heart disease patients classi cation problems to examine the proposed measure
capability in contrast to other evidential measures. Our experiment illustrates that the belief interval
distance measure yields the accuracy rates of 91.66 and 92.45 percent for unknown bacillus patterns
recognition and coronary heart disease patients classi cation, respectively, which in contrast to other
evidential measures shows superior performance.
)