Multiple level parallel decision fusion model with distributed sensors based on Dempster-Shafer evidence theory

Author

Yu, Neng-hai ; Yin, Yong

Author_Institution

Dept. of Electron. Eng. & Inf. Sci., Univ. of Sci. & Technol. of China, Hefei, China

Volume

5

fYear

2003

fDate

2-5 Nov. 2003

Firstpage

3104

Abstract

The application of Dempster-Shafer evidence theory to decision fusion with multi-sensors is discussed in this paper, and whose analysis focuses on comparing and contrasting Dempster´s rule of combination and its improved model. Considering such defects of the Dempster combination rule as failing to support the totally inconsistent evidences and being insensitive to the base of aggregate, and also due to the lower border of belief interval in the improved model of Dempster´s rule being too low, we put forward a new multiple level parallel decision fusion model with distributed sensors based on Dempster-Shafer evidence theory, accordingly. The results of simulation experiments demonstrate that the model we present is more feasible and effective, and will be of great significance to solve the problem of military target identification.

Keywords

distributed sensors; inference mechanisms; probability; sensor fusion; uncertainty handling; Dempster combination rule; Dempster-Shafer evidence theory; distributed sensors; military target identification; multiple level parallel decision fusion model; multisensors; probability; Aggregates; Bayesian methods; Cybernetics; Electronic mail; Information analysis; Information science; Machine learning; Sensor fusion;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2003 International Conference on

Print_ISBN

0-7803-8131-9

Type

conf

DOI

10.1109/ICMLC.2003.1260112

Filename

1260112