A semantic-based belief network construction approach in IoT

Yuji Dong*, Kaiyu Wan, Yong Yue

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)


Uncertainty is intrinsic in most of the complex systems, especially when the systems have to interact with the physical environment; therefore, handling uncertainty is critical in the Internet of Things (IoT). In this paper, we propose a semantic-based approach to build the belief network in IoT systems to handle the uncertainties. Semantics is the functionality description of any system component. Semantic Match mechanisms can construct the appropriate structures to compare the consistency between different sources of data based on the same functionality. In the approach, we define the belief property of every system component and develop the related algorithms to update the belief value. Furthermore, the related mechanisms and algorithms for data fusion and fault detection based on the belief property are described to explain how the approach works in the IoT systems. Several simulation experiments are used to evaluate the proposed approach, and the results indicate that the approach can work as expected. More accurate data are fused from the inaccurate devices and the fault in one node is automatically detected.

Original languageEnglish
Article number5747
Pages (from-to)1-22
Number of pages22
JournalSensors (Switzerland)
Issue number20
Publication statusPublished - 2 Oct 2020


  • Belief
  • Data fusion
  • Fault detection
  • Internet of things
  • Self adaptation
  • Uncertainty

Cite this