Title :
Combining the Conflicting Belief Functions
Author :
Liu Zhun-ga ; Cheng Yong-mei ; Pan Quan ; Miao Zhuang
Author_Institution :
Sch. of Autom., Northwestern Polytech. Univ., Xi´an, China
Abstract :
The classical Dempster-Shafer theory involves counter-intuitive behaviors when the evidence high conflict. In order to solve the problem, a new approach of weighted evidence combination is proposed. Both evidence distance and inconsistent information are considered to evaluate the conflict. Each piece of evidence is given weight coefficient according to its amount of conflict with others. Then two methods are used to modify the belief functions, and the modified functions are combined by DS rule. Numerical example shows the proposed approach can efficiently handle conflicting evidence with good convergence efficiency.
Keywords :
belief networks; case-based reasoning; inference mechanisms; Dempster-Shafer theory; belief functions; counter intuitive behavior; evidence distance; evidence theory; inconsistent information; Automation; Convergence of numerical methods; Information science;
Conference_Titel :
Information Science and Engineering (ICISE), 2009 1st International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-4909-5
DOI :
10.1109/ICISE.2009.403