Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 9, Issue 4, 2025

Deep Bayesian Modeling for Maritime Situational Awareness with Multisource and Heterogeneous Information

Download as PDF

DOI: 10.23977/acss.2025.090409 | Downloads: 0 | Views: 51

Author(s)

Yao Haiyang 1, Zhang Shuchen 1, Chen Xiao 1, Wang Haiyan 1,2

Affiliation(s)

1 School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi'an, 710016, China
2 School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, 710072, China

Corresponding Author

Yao Haiyang

ABSTRACT

Maritime situational awareness is a core research field in marine science, whose intrinsic complexity stems from the inherent nature of the ocean as an open, complex giant system and the technical challenges of cross-domain multi-platform coordination and multi-source heterogeneous data processing. To address this challenge, this paper proposes an intelligent prediction framework based on multi-source data fusion via a deep Bayesian network. The model integrates deep learning architectures with probabilistic graphical modeling, effectively leveraging the powerful representational capacity of neural networks together with the strengths of Bayesian inference in uncertainty modeling and causal reasoning. A central contribution of this framework is its multimodal fusion mechanism, which captures the complex, nonlinear, and non-stationary evolution of maritime situations. By moving beyond the limitations of conventional methods, our approach extracts latent situational elements from multimodal inputs and performs probabilistic density estimation of future states through variational inference. Experimental results demonstrate that the predictions generated by our model align closely with actual situational developments, with all key evaluation metrics showing significant improvements over existing forecasting techniques.

KEYWORDS

Deep Bayesian Network, Multi-source Data Fusion, Maritime Situation Prediction, Uncertainty Quantification

CITE THIS PAPER

Yao Haiyang, Zhang Shuchen, Chen Xiao, Wang Haiyan, Deep Bayesian Modeling for Maritime Situational Awareness with Multisource and Heterogeneous Information. Advances in Computer, Signals and Systems (2025) Vol. 9: 69-82. DOI: http://dx.doi.org/10.23977/acss.2025.090409.

REFERENCES

[1] LI Ming , ZHANG Ren , CHEN Xi , LIU Yuhang , WANG Bo. Review of assessment methods for impact of marine battlefield environment. Command Control and Simulation. 2024, 46(5): 155-160 https://doi.org/10.3969/j.issn.1673-3819.2024.05.021
[2] DUAN Y X, LIU C Y, WEI W F. Review of key technologies for battlefield situational awareness[J]. Fire Control& Command Control, 2021, 46(11): 1-11.
[3] Biddle S, Severini J. Military Effectiveness and Naval Warfare[J]. Security Studies, 2024, 33(3): 325-347.
[4] Wu S , Li X , Dong W ,et al.Multi-source and heterogeneous marine hydrometeorology spatio-temporal data analysis with machine learning: a survey[J].World Wide Web, 2022:1-42.DOI:10.1007/s11280-022-01069-4.
[5] Ke L. Application of cognitive technology in battlefield situation awareness[J]. command information system and technology, 2021, 12: 63-66.
[6] Lee C, Baek J, Do S, et al. Multi-Agent Based Collaborative Agent Architecture for Battlefield Situation Awareness[C]//2024 IEEE International Conference on Big Data and Smart Computing (BigComp). IEEE, 2024: 395-396.
[7] Wang H, Li T, Rao J. New Interpretation of Battlefield Situation Awareness in the Era of Artificial Intelligence[C]//China Conference on Command and Control. Singapore: Springer Nature Singapore, 2022: 701-711.
[8] Li D, Liu M, Zhang S. Underwater target threat assessment method based on Bayesian network[C]//2021 40th Chinese Control Conference (CCC). IEEE, 2021: 3363-3367.
[9] Zhang X, Li W, Wang Z. Bayesian Network-Based Threat Assessment and TARAPSO Algorithm for UUV Path Planning in Complex Environments[J]. Journal of Intelligent & Robotic Systems, 2025, 111(1): 1-17.
[10] Kong D, Lin Z, Li W, et al. Development of an improved Bayesian network method for maritime accident safety assessment based on multiscale scenario analysis theory[J]. Reliability Engineering & System Safety, 2024, 251: 110344.
[11] Zhang Q, Chen J, Sun J, et al. Soldier threat assessment method based on Bayesian Network[C]//2021 China Automation Congress (CAC). IEEE, 2021: 1750-1755.
[12] Fan H, Jia H, He X, et al. Navigating uncertainty: A dynamic Bayesian network-based risk assessment framework for maritime trade routes[J]. Reliability Engineering & System Safety, 2024, 250: 110311.
[13] Chen X, Zhang B, Liu W, et al. Threat assessment of the maritime targets based on dynamic bayesian networks[C]//2022 34th Chinese Control and Decision Conference (CCDC). IEEE, 2022: 4841-4846.
[14] Fan Z H, Shi B H, Chen J Y, et al. A novel dynamic Bayesian network based threat assessment algorithm[C]//2017 4th International Conference on Systems and Informatics (ICSAI). IEEE, 2017: 611-615
[15] Sun H, Xie X, Sun T, et al. Dynamic Bayesian network threat assessment for warship formation: a data analysis method[J]. International Journal of High Performance Systems Architecture, 2018, 8(1-2): 71-81.
[16] Yongcui Z. Situation awareness and target recognition of marine big data battlefield based on deep learning[C]//2022 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA). IEEE, 2022: 430-435.
[17] Fan X, Shen T, Shi W, et al. Research on intelligent prediction of navigation situation based on ship operation data[C]//ISOPE International Ocean and Polar Engineering Conference. ISOPE, 2022: ISOPE-I-22-546.
[18] Li W, Li Y, Wang Q. Unified Representation Method for Multi-Source Information in Situation Awareness Knowledge Graph[C]//2024 14th Asian Control Conference (ASCC). IEEE, 2024: 25-30.
[19] Du X, Liang T, Qiu S, et al. Situation estimation method based on improved DS evidence theory[C]//CIBDA 2022; 3rd International Conference on Computer Information and Big Data Applications. VDE, 2022: 1-4.
[20] Gal Y, Ghahramani Z. Dropout as a bayesian approximation: Representing model uncertainty in deep learning[C]//international conference on machine learning. PMLR, 2016: 1050-1059.
[21] Kingma, Diederik P. et al. "Variational Dropout and the Local Reparameterization Trick." Neural Information Processing Systems (2015).
[22] Blundell, Charles et al. "Weight Uncertainty in Neural Network." International Conference on Machine Learning (2015).
[23] Sucar, L.E. (2021). Bayesian Networks: Representation and Inference. In: Probabilistic Graphical Models. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-030-61943-5_7.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 41603
Visits: 845615

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.