Artificial Intelligence

   

Evidence Combination from an Evolutionary Game Theory Perspective

Authors: Xinyang Deng, Deqiang Han, Jean Dezert, Yong Deng, Yu Shyr

Dempster-Shafer evidence theory is a primary methodology for multi-source information fusion since it allows to deal with uncertain information. This theory is based on Dempster’s rule of combination to synthesize multiple evidences from various information sources. However, in some cases, counter-intuitive results may be obtained based on Dempster’s rule of combination. Lots of improved or new methods have been proposed to suppress the counter-intuitive results based on a physical perspective that minimizes the lost or deviation of original information. In this paper, inspired by evolutionary game theory, a biological and evolutionary perspective is considered to study the combination of evidences. An evolutionary combination rule (ECR) is proposed to mimick the evolution of propositions in a given population and finally find the biologically most supported proposition which is called as evolutionarily stable proposition (ESP) in this paper. Our proposed ECR provides new insight for the combination of multi-source information. Experimental results show that the proposed method is rational and effective.

Comments: 31 pages, 8 figures

Download: PDF

Submission history

[v1] 2015-03-10 17:21:38

Unique-IP document downloads: 52 times

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus