Probe into Improved D-S Evidence Inference Algorithm Based on Weighted Method in Traffic Information Recognition

Yue Jing Lv; Xu Fei Xie; Xiang Bo Song; Xing Lin Zhou; Ming Liu

doi:10.4028/www.scientific.net/AMM.94-96.2138

Paper Titles

Numerical Simulation Analysis of the Ultimate Bearing Capacity of the Circular Steel Tube K-Joints Reinforced with the Concrete
p.2118

Research on Numerical Simulation of Flow-Field around the Building Based on FLUENT
p.2123

Numerical Analysis of Fluid-Structure Interaction of Frame Structure Considering the Impact of Turbulent Wind Load
p.2130

Building Component Maintenance/Repair Management: an Economic Analysis Simulation
p.2134

Probe into Improved D-S Evidence Inference Algorithm Based on Weighted Method in Traffic Information Recognition
p.2138

A Conceptual Framework for a BIM-Based Collaboration Platform Supported by Mobile Computing
p.2144

Secondary Development of Marc Software Based on Shield Tunnel Load Structure Method and its Verification
p.2149

The Finite Element Analysis on the Mainframe of High-Pressure Grouting Machine
p.2153

Research on the Road Concrete Mixing Uniformity Control Technology
p.2157

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 94-96Probe into Improved D-S Evidence Inference...

Probe into Improved D-S Evidence Inference Algorithm Based on Weighted Method in Traffic Information Recognition

Abstract:

Data recognition is the most important problem of traffic information recognition to be resolved, evidence inference method for such uncertainty problems have a strong advantage, but it can’t deal with contradictions of evidence, that largely limits the practical application of it. This paper improves D-S evidence inference algorithm. The improved algorithm can effectively deal with contradictions of evidence, and obtain more satisfactory and reasonable fusion results. Finally, the algorithm is verified by traffic information simulation experiment.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 94-96)

Pages:

2138-2143

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.94-96.2138

Citation:

Cite this paper

Online since:

September 2011

Authors:

Yue Jing Lv, Xu Fei Xie, Xiang Bo Song, Xing Lin Zhou, Ming Liu

Keywords:

D-S Evidence Theory, Information Fusion, Traffic Information Recognition

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Tongming Liu. Multi-sensor data fusion and applications. Beijing: National Defence Industry Press, (1998).

Google Scholar

[2] Hong Li.Study of Information Fusion Method Based on the Combination of ANN and Evidence Theory to Recognize Point Targets, Information and Control, vol.26(2) (1997), pp.151-155.

Google Scholar

[3] Xinsheng Duan. Evidence decision. Beijing:Economic Science Press,(1996).

Google Scholar

[4] Huadong Wu, Mel Siegel, Rainer Stiefe-lhagen, Jie Yang. Sensor Fusion Using Dempster-Shafer Theory. IEEE Instrume-ntation and Measurement Technology Confe- rence.Anchorage, AK, USA, May 2002, pp.21-23.

DOI: 10.1109/imtc.2002.1006807

Google Scholar

[5] Thierry Denceux. A Neural Network Class-ifier Based on Dempster-Shafer Theory. IEEE Transactions on systems, man, and cybernrtis-part a: systems and humans. March, vol.30(2) (2000), pp.131-150.

DOI: 10.1109/3468.833094

Google Scholar

[6] Huaijiang Sun,Zhongshan Hu,Jingyu Yang.Learning Dependent Original Evidences. Jounal of Nanjing University(Natural Sciences), vol.36(2)( 2001), pp.154-158.

Google Scholar

[7] Lei Qin,Wenbin Liu,kang Zhou. An Information Fusion Based on Group of Neural Network to Recognize Spatial Targets. Microelectronics and Computer, vol. 25(8)( 2008), pp.117-120.

Google Scholar