AI-Enabled IoT Data Fusion for Digital Transformation
DOI:
https://doi.org/10.5281/zenodo.20828459Keywords:
AI-Enabled Streaming Pipelines, Automated Digital Transformation, Internet of Things (IoT) Data Fusion, Event-Driven Data Architectures, End-to-End AI Orchestration, Dynamic Model Deployment in Streaming Systems, Data Governance Automation, Real-Time Data Quality Assurance, Privacy-Preserving Streaming Analytics, Intelligent Pipeline Automation, Cloud-Native AI Services, Scalable IoT Analytics Platforms, Feedback-Loop Optimization, Industry 4.0 Data Integration, Cross-Industry AI Service Enablement.Abstract
Automated digital transformation via AI-enabled streaming pipelines with IoT data fusion is a viable concept that fulfills companies' aspirations to innovate services and business lines. It eliminates substantial hurdles by automating the setup of data pipelines, orchestrating end-to-end solutions, accelerating data governance and quality improvement, and establishing closing feedback loops. Automation relies on creating pipelines for Internet of Things (IoT) data, driven by data sources and offering AI-backed services. Orchestration dynamically deploys AI models in the streaming layer, while data governance is facilitated by an integrating framework for data quality and data privacy and security assurance in streaming contexts. Real-life examples in industries such as manufacturing, energy, transportation and logistics, smart cities, and agriculture illustrate these points.
Companies are investing heavily in technology to realize new services and business lines. However, the aspiration for digital transformation still depends on manually developing complex custom data pipelines, integrating AI-driven models, and ensuring data privacy and quality. Automated digital transformation through data fusions is an appealing concept. Automating all the content and process in the topic enables a company to adapt data pipelines required to provide these services dynamically, onboarding the new use cases at high speed and reducing costs. AI modelling, therefore, is required to be produced only once in the data sources, providing services in the pipelines without involving teams in developing reports and dashboards.
References
1. Chen, J., Li, S., & He, H. (2026). Reinforcement learning for adaptive streaming analytics in cyber-physical systems. IEEE Transactions on Neural Networks and Learning Systems, 37(4), 812–826.
2. Zhang, Y., Wang, L., & Tao, F. (2026). Digital twin-driven IoT data fusion for Industry 4.0 transformation. IEEE Transactions on Industrial Informatics, 22(1), 55–68.
3. Ghassemi, M., Oakden-Rayner, L., & Beam, A. L. (2024). Reassessing explainability in high-stakes AI systems. The Lancet Digital Health, 6(1), e14–e22.
4. Armbrust, M., Ghodsi, A., Xin, R., Zaharia, M., & Stoica, I. (2025). Lakehouse architectures for AI-driven data platforms. Communications of the ACM, 68(4), 52–61.
5. Pahl, C., Jamshidi, P., & Soldani, J. (2024). Cloud-native software engineering: Emerging DevOps and DataOps patterns. IEEE Software, 41(2), 28–36.
6. Sutton, R. S., & Barto, A. G. (2025). Reinforcement learning: An introduction (3rd ed.). MIT Press.
7. Goodfellow, I., Bengio, Y., & Courville, A. (2024). Deep learning (2nd ed.). MIT Press.
8. Newman, S. (2021). Building microservices (2nd ed.). O’Reilly Media.
9. Kleppmann, M. (2017). Designing data-intensive applications. O’Reilly Media.
10. Kim, G., Debois, P., Willis, J., Humble, J., & Forsgren, N. (2021). The DevOps handbook (2nd ed.). IT Revolution Press.
11. Akidau, T., Chernyak, S., & Lax, R. (2018). Streaming systems: The what, where, when, and how of large-scale data processing. O’Reilly Media.
12. Zaharia, M., et al. (2016). Apache Spark: A unified engine for big data processing. Communications of the ACM, 59(11), 56–65.
13. Kreps, J., Narkhede, N., & Rao, J. (2011). Kafka: A distributed messaging system for log processing. NetDB Workshop.
14. Paszke, A., et al. (2019). PyTorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, 8024–8035.
15. Abadi, M., et al. (2016). TensorFlow: A system for large-scale machine learning. OSDI, 265–283.
16. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). Why should I trust you? KDD, 1135–1144.
17. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 4765–4774.
18. Rudin, C. (2019). Stop explaining black box machine learning models for high-stakes decisions. Nature Machine Intelligence, 1, 206–215.
19. Basel Committee on Banking Supervision. (2026). Principles for operational resilience (revised edition). Bank for International Settlements.
20. NIST. (2026). Artificial intelligence risk management framework: Streaming systems profile. National Institute of Standards and Technology.
21. OECD. (2025). AI, data governance, and digital transformation strategies. OECD Publishing.
22. ISO/IEC. (2024). ISO/IEC 27001: Information security management systems (4th ed.). International Organization for Standardization.
23. ISO/IEC. (2025). ISO/IEC 42001: Artificial intelligence management systems. International Organization for Standardization.
24. Tao, F., Qi, Q., Wang, L., & Nee, A. Y. C. (2019). Digital twins and cyber–physical systems for Industry 4.0. Engineering, 5(4), 653–661.
25. Zhou, K., Liu, T., & Zhou, L. (2015). Industry 4.0: Towards future industrial opportunities and challenges. IEEE International Conference on Fuzzy Systems, 2147–2152.
26. Sirignano, J., & Cont, R. (2019). Universal features of price formation in limit order books. Quantitative Finance, 19(9), 1449–1467.
27. Heaton, J., Polson, N., & Witte, J. (2017). Deep learning for finance and time-series systems. Applied Stochastic Models in Business and Industry, 33(1), 3–12.
28. Fox, A., & Patterson, D. (2012). Engineering long-lived software systems. Communications of the ACM, 55(5), 71–79.
Additional Files
Published
Issue
Section
License
Articles published in the European Advanced Journal for Science & Engineering (EAJSE) are made freely available online immediately upon publication under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license permits unrestricted use, distribution, and reproduction in any medium or format, provided the original work is properly cited. Authors retain copyright of their work. By submitting to EAJSE, authors grant the journal the right of first publication. For details, visit: https://creativecommons.org/licenses/by/4.0/
