An Improve Information Fusion Algorithm Based on BP Neural Network and D-S Evidence Theory

Author

Yi, Chen ; Qing, Huang ; Yanlan, Chen

Author_Institution

Guilin Univ. of Electron. Sci. & Technol., Guilin, China

fYear

2012

fDate

July 31 2012-Aug. 2 2012

Firstpage

179

Lastpage

181

Abstract

BP neural network and DS evidence theory have gotten a wide range of applications in the field of information fusion. According to the BP neural network have low recognition rate and poor network stability, what is more, it is difficult to get D-S evidence theory of basic probability distribution function, This paper design a kind of improved algorithm, which combined group neural network and D-S evidence theory. The improved algorithm make full use of the advantages. The simulation results show that this algorithm have a better effect both in recognition rate and anti-noise capacity.

Keywords

backpropagation; inference mechanisms; neural nets; probability; sensor fusion; uncertainty handling; BP neural network; D-S evidence theory; Dempster-Shafer evidence theory; anti noise capacity; improved information fusion algorithm; probability distribution function; rate noise capacity; Algorithm design and analysis; Feature extraction; Gaussian noise; Neural networks; Signal processing algorithms; Simulation; Vectors; Bp Neural Network; Evidence Theory; Information Fusion; Multi-sesor;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Manufacturing and Automation (ICDMA), 2012 Third International Conference on

Conference_Location

GuiLin

Print_ISBN

978-1-4673-2217-1

Type

conf

DOI

10.1109/ICDMA.2012.43

Filename

6298283