DocumentCode :
3217320
Title :
The fusion method of conflicting evidence based on the cosine similarity of evidence vectors
Author :
Wang, Yucheng ; Xu, Xiaobin ; Lu, Yanwen ; Wen, Chenglin
Author_Institution :
Autom., Hangzhou Dianzi Univ., Hangzhou, China
fYear :
2010
fDate :
9-11 June 2010
Firstpage :
1279
Lastpage :
1283
Abstract :
A new method of the conflicting evidence fusion is proposed based on the similarity measure of evidence. Firstly, the body of evidence is transformed to pignistic evidence vector (PEV) in a constructed pignistic similarity space. The vector cosine is used to measure similarity between two PEVs. Secondly, the weight of each original body of evidence is obtained from the vector cosine. The modified average method of the weighted evidence fusion is given. Finally, numerical examples illustrate the effectivity of the proposed method.
Keywords :
Automatic control; Automation; Convergence; Fault diagnosis; Human factors; Information resources; Pattern recognition; Sensor fusion; Sensor systems; Uncertainty; Evidence theory; conflicting evidence; pignistic evidence vector; pignistic similarity space;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control and Automation (ICCA), 2010 8th IEEE International Conference on
Conference_Location :
Xiamen, China
ISSN :
1948-3449
Print_ISBN :
978-1-4244-5195-1
Electronic_ISBN :
1948-3449
Type :
conf
DOI :
10.1109/ICCA.2010.5524200
Filename :
5524200
Link To Document :
بازگشت