Deadline for manuscript submissions: 31 December 2026

 

Special Issue Editors

 

Gang Wang Website  E-Mail: gangw@xaufe.edu.cn
Xi’an University of Finance and Economics, China
Interests: Artificial Intelligence, Cloud Computing, Big Data, IoTs, Trust security and Service computing.

  

Jinhu Wang Website  E-Mail: goldtigerwang@nuist.edu.cn
Nanjing University of Information Science & Technology (NUIST), China
Interests: Meteorological disaster monitoring and early warning; Low-altitude technology and engineering; Disaster prevention and mitigation system design

  

Tiejun Cui Website  E-Mail: ctj.159@163.com(Guest Editor)
Shenyang Ligong University, China
Interests: Fundamentals of Artificial Intelligence, Safety of Intelligent Systems

Special Issue Information

 

Modern industrial systems generate vast amounts of heterogeneous data—from sensors, operational logs, and environmental signals—that collectively offer rich insights into system behavior. The effective fusion of such multi-source information is critical for enhancing the accuracy and reliability of system safety prediction. With the complexity of modern industrial systems and the growth of multi-dimensional data, traditional fusion methods struggle to address issues such as data inconsistency, noise interference, and dynamic state changes. Consequently, this special issue focuses on the latest progress in multi-source information fusion methods and system safety prediction, highlighting innovative fusion theories, advanced technical frameworks, and practical safety prediction applications. To enhance the connection between theoretical research and industrial practice, original studies with detailed validation and engineering cases are highly encouraged. Therefore, we establish this special issue to provide a high-quality platform for scholars and engineers to exchange cutting-edge insights and technical achievements.

The primary topics are as follows (not limited to those listed):

• Heterogeneous data fusion algorithms for system safety assessment
• Deep learning-based multi-source information fusion frameworks
• Uncertainty quantification in multi-source data fusion processes
• Real-time fusion methods for dynamic system safety prediction
• Cross-domain information fusion for complex industrial system safety
• Digital twin-enabled multi-source data fusion and safety early warning

Collection Editor(s): Gang Wang, Jinhu Wang, Tiejun Cui

 

Keywords:multi-source information fusion; system safety prediction; heterogeneous data; deep learning; uncertainty quantification; safety early warning