Affiliations: [a] College of Computer Science and Technology, Jilin University, Changchun, China
| [b] State Key Laboratory of Applied Optics, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China
| [c] Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China
| [d] Institute of Computer Engineering, Vienna University of Technology, Vienna, Austria
Correspondence:
[*]
Corresponding author. Yungang Zhu, College of Computer, Science and Technology, Jilin University, Changchun, China. Tel.: +86 43185166479; E-mail: zhuyungang@jlu.edu.cn.
Abstract: Convex evidence theory is the only way to handle ordered and fuzzy evidence fusion, however, conventional convex evidence theory has some drawbacks that make the fusion results are unreasonable in some cases, and not efficient in the scenario of massive data. To overcome above issues, in this article we proposed a novel convex evidence theory based on Gaussian function, we modified Gaussian function and use it to combine mass function of ordered propositions, we designed the formula of the parameters of Gaussian function, and proposed a more accurate method to find the most likely true proposition. We also proved the effectiveness of the proposed method. Theoretical analysis and experimental results demonstrate that the proposed method has lower time complexity and higher accuracy than state-of-the-art method.
Keywords: Evidence theory, data fusion, gaussian function, convex function
