A new base basic probability assignment approach for conflict data fusion in the evidence theory
- PDF / 1,957,123 Bytes
- 13 Pages / 595.224 x 790.955 pts Page_size
- 16 Downloads / 171 Views
A new base basic probability assignment approach for conflict data fusion in the evidence theory Ming Jing1 · Yongchuan Tang1
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Dempster-Shafer evidence theory (D-S theory) is applied to process uncertain information in different scenarios. However, traditional Dempster combination rule may produce counterintuitive results while dealing with highly conflicting data. Inspired by a perspective of constructing base belief function for conflicting data processing in D-S theory, a new base basic probability assignment (bBPA) method is proposed to process the potential conflict before data fusion. Instead of assigning initial belief on the whole power set space, the new method assigns the base belief to basic events in the frame of discernment. Consequently, the bBPA is consistent with the classical probability theory. Several numerical examples are adopted to verify the reliability and accuracy of the method in processing highly conflicting data. The data sets in the University of California Irvine (UCI) Machine Learning Repository are used to verity the availability of the new method in classification problem. Experimental result shows that the new method has some superiority in dealing with highly conflicting data. Keywords Dempster-Shafer evidencve theory · Basic probability assignment · Conflict management · Conflicting data fusion
1 Introduction Dempster-Shafer evidence theory (D-S theory) [1, 2] has been adopted to process uncertain information in many domains such as classification [3, 4], clustering [5–7], fault diagnosis [8, 9], knowledge-based system [10, 11], medical diagnosis [12], sensor data fusion [13], decision making [14, 15], risk analysis [16–19], and so on [20]. Many efforts have been given to address the open issues in DS theory. First of all, the generation of basic probability assignment (BPA) is the base of applying D-S theory [21]. Secondly, the fusion of conflicting data is a hot topic in both theory and practical domains [22, 23]. D-S theory may produce counterintuitive results while dealing with
The work is partially supported by National Key Research and Development Project of China (Grant No. 2019YFB2102602). Yongchuan Tang
[email protected] Ming Jing [email protected] 1
School of Big Data and Software Engineering, Chongqing University, Chongqing 401331, China
highly conflicting data. Thirdly, decision making based on mass function [24, 25]. The generated BPA cannot directly provide the probability of occurrences. How to transform the BPA to probability is a big problem [26]. Fourthly, the problem of high computational complexity [27, 28]. The computational complexity of Dempster combination rule is high. After the space is expanded, the number of the events in the power set increases exponentially and the computational complexity is high. Finally, the function for evidence evaluation [29], e.g. belief entropy-based methods for uncertainty measure [30–32]. This paper focuses on conflicting data fusi
Data Loading...
