DocumentCode :
2298391
Title :
D-S Evidence Theory Fusion Method Based on Forecast Reliability
Author :
Zhang, Jianpei ; Wang, Li ; Zhang, Lejun ; Yang, Jing
Author_Institution :
Coll. of Comput. Sci. & Technol., Harbin Eng. Univ., Harbin, China
fYear :
2010
fDate :
1-2 Nov. 2010
Firstpage :
14
Lastpage :
19
Abstract :
D-S evidence theory is one of the most widely used methods in data fusion, and the problems including evidence conflict and low fusion efficiency are also the focus subject that many scholars are studying. The idea of forecast reliability is introduced into this paper for the problems. First, an improved method based on forecast reliability coefficient is presented. Secondly, on the basis of maintaining all the characters of original combination rule, forecast reliability coefficient is introduced into combination rule to improve data fusion speed and resolve evidence conflict problem. Finally, the simulation experiment proved the effectiveness of the proposed algorithm.
Keywords :
forecasting theory; inference mechanisms; reliability theory; sensor fusion; D-S evidence theory fusion method; data fusion; evidence conflict problem; forecast reliability coefficient; Distributed databases; Reliability theory; Temperature sensors; Training; Uncertainty; D-S evidence theory; data fusion; forecast reliability; fusion efficiency;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Internet Computing for Science and Engineering (ICICSE), 2010 Fifth International Conference on
Conference_Location :
Heilongjiang
Print_ISBN :
978-1-4244-9954-0
Type :
conf
DOI :
10.1109/ICICSE.2010.23
Filename :
6076533
Link To Document :
بازگشت