A multi-attribute fusion approach extending Dempster–Shafer theory for combinatorial-type evidences

• Published in: Expert systems with applications 2018-04, Vol.96, p.218-229
• Main Authors: Sun, Lin, Wang, Yanzhang
• Format: Article
• Language: English
• Subjects: Algorithms; Big Data; Cognition; Combinatorial analysis; Data management; Data mining; Dempster-Shafer Method; Dempster–Shafer theory; Emergency management; Empirical analysis; Expert systems; Knowledge element; Knowledge fusion; Machine learning; Multi-attribute perception; Preprocessing; Risk analysis
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2017.12.005

•A fusion method extends to integrate combinatorial type evidences.•A combining mechanism uses a number to measure the degree of confidence.•New uncertainty measures ensure the validity of the multi-attribute fusion.•A knowledge element model is applied for unified representation of objects. Human cognition of the world generally begins with attribute perception of things. Knowledge element, which is able to reveal microscopic regularities by attribute network, provides an intelligent support for attribute-based cognition. In the field of emergency management, knowledge element has been widely used in evolution rules, risk analysis and machine learning based on emergency cases. However, since the knowledge of emergency management is multidisciplinary and in addition, limited by diverse cognitive perspectives and language expressions, integrating heterogeneous knowledge from domain experts and data sources for depth mining and decision support seems to be difficult. Especially, with the advent of big data, the problem of developing an efficient multi-attribute fusion method to reorganize complex and massive data in a consensual knowledge framework must be addressed. In this paper, a novel mathematical approach, which extends Dempster–Shafer theory to fuse combinatorial-type evidences, is elaborated to handle multi-attribute integration through the use of knowledge element model. This methodology makes it possible to establish a complete knowledge structure for attribute description of things by implementing new uncertainty measures to determine a degree of belief when combining evidences. It is meaningful to optimize the fusion algorithm in view of reliability and expansibility to some extent. Furthermore, the processing also has the advantage of being effective without any semantic preprocessing. The application of the proposed model is shown in marine disaster monitoring for emergency management. We make an empirical analysis in the attribute fusion of knowledge element “sea”.