A Novel Weighted Evidence Combination Method Based on Reliability and Credibility degree with an Application in Decision Making Process

Palash Dutta and Sonom Shome ()
Additional contact information
Palash Dutta: Department of Mathematics, Dibrugarh University, Dibrugarh 786004, Assam, India
Sonom Shome: Department of Mathematics, Dibrugarh University, Dibrugarh 786004, Assam, India

New Mathematics and Natural Computation (NMNC), 2025, vol. 21, issue 02, 379-407

Abstract: The Dempster–Shafer theory (DST), also known as Belief function theory (BFT), finds extensive application across various domains involving data fusion. However, it is not uncommon to encounter counterintuitive results when combining highly conflicting pieces of evidence using the Dempster combination rule (DCR). While the literature offers several combination rules, only a few address these shortcomings effectively. To address these limitations and rectify the issue of counterintuitive outcomes, a novel weighted evidence fusion rule has been introduced. This fusion approach comprises four key steps: First, the reliability degree of each evidence set, also known as body of evidence (BOE) is determined based on its compatibility degree and total correlation. This step helps to mitigate conflicts arising from unreliable sources. Second, the degree of credibility of each BOE is computed, taking into account distance of evidence and uncertainty degree, further enhancing the accuracy of the fusion process. Third, the reliability and credibility degrees are combined to derive weights for each BOE, ensuring that more weight is assigned to trustworthy sources of evidence. Finally, these weights for each BOE are used to compute a modified Basic Probability Assignment (BPA) for each proposition, which are then fused using the Dempster combination rule. Numerous numerical examples, as well as artificial and real datasets, have been employed to emphasize the effectiveness and potential of this innovative approach. Furthermore, through comparative analysis, it becomes evident that the proposed rule consistently outruns other existing methods, ensuring more accurate and reliable outcomes.

Keywords: Credibility degree; reliability degree; compatibility; correlation; entropy (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S1793005725500176
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:nmncxx:v:21:y:2025:i:02:n:s1793005725500176

Ordering information: This journal article can be ordered from

DOI: 10.1142/S1793005725500176

Access Statistics for this article

New Mathematics and Natural Computation (NMNC) is currently edited by Paul P Wang

More articles in New Mathematics and Natural Computation (NMNC) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().