An AI and Data Engineering Perspective
DOI:
https://doi.org/10.5281/zenodo.21509045Keywords:
Intelligent Transportation Systems, AI-Powered ITS, Transportation Data Integration, AI-Based Data Engineering, Transportation Safety And Efficiency, Mobility And Sustainability, Multi-Source Transportation Data, ITS Infrastructure Provisioning, Real-Time Transportation Analytics, Data Acquisition And Ingestion, Transportation Data Interoperability, ITS Data Architectures, Predictive Traffic Modeling, Demand And Congestion Forecasting, Route Planning Optimization, Incident Detection And Mitigation, Transportation System Operations, ITS Data Governance And Security, AI-Driven Transportation Solutions, Scalable ITS Data Pipelines.Abstract
The mission of intelligent transportation systems (ITS) is to enhance transportation safety, efficiency, mobility, and sustainability through the integration of data from multiple sources. Despite the celebrated success of artificial intelligence (AI) in development and commercialization, its growing capacities, accessibility, and affordability have not been capitalized on in ITS. This is due partly to the lack of comprehensive and clearly delineated means for infrastructure provision, timeliness, and system continuity—especially in maintenance, operations, and expansion—and partly to the underlying data fundamentals. AI engenders unprecedented opportunities for transportation solutions by providing its own data engineering. Examination of AI-Powered Data Engineering methods reveals the enabling means of AI-based data engineering for ITS.
Data engineering encompasses the core functions for the acquisition, preparation, and deployment of data suitable for analysis and modeling. Like the broader IT domain, AI-Powered Data Engineering for ITS operates on a foundation of data acquisition and ingestion; integration and interoperability; architecture; optimization; security; governance; agency; and deployment. The function for data acquisition and ingestion serves the dual purpose of ingesting system-based information—such as from traffic signals and detection cameras used for system administration—as well as supporting predictive models for demand and congestion forecasting conversation systems for route planning and incident mitigation.
References
[1] Abdel-Aty, M., Cai, Q., & Yue, L. (2023). Deep learning applications for road safety analysis and crash prediction: A review. Accident Analysis & Prevention, 188, 107090.
[2] Abdulkareem, K. H., Mohammed, M. A., Salim, A., Arif, M., Geman, O., Gupta, D., & Khanna, A. (2021). Real-time big data analytics for intelligent transportation systems: A review. IEEE Access, 9, 10155–10178.
[3] Alghamdi, A., AlOtaibi, R., Alzahrani, A., & Alsubhi, K. (2023). Edge intelligence for connected autonomous vehicles: Architecture, challenges, and future directions. Future Generation Computer Systems, 145, 102–118.
[4] Al-Turjman, F., Ever, E., & Zahmatkesh, H. (2024). AI-driven vehicular edge computing for intelligent transportation: Concepts, taxonomy, and open research problems. IEEE Communications Surveys & Tutorials, 26(1), 1–34.
[5] Anwar, S., Qin, J., & Khan, S. (2023). Vision-based traffic surveillance: Deep learning methods, challenges, and applications. IEEE Transactions on Intelligent Transportation Systems, 24(6), 5801–5821.
[6] Badue, C., Guidolini, R., Carneiro, R. V., et al. (2022). Self-driving cars: A survey. Expert Systems with Applications, 165, 113816.
[7] Bai, L., Yao, L., Li, C., Wang, X., & Wang, C. (2023). Adaptive spatiotemporal graph neural networks for traffic flow forecasting: A survey. IEEE Transactions on Intelligent Transportation Systems, 24(7), 7011–7030.
[8] Barua, S., & Zou, J. (2024). Federated learning for intelligent transportation systems: A comprehensive survey. IEEE Transactions on Intelligent Transportation Systems, 25(2), 1320–1344.
[9] Bhatia, M., Mishra, S., & Sangaiah, A. K. (2023). Explainable AI for intelligent transportation systems: A systematic review. Information Fusion, 94, 1–20.
[10] Bojarski, M., Del Testa, D., Dworakowski, D., et al. (2016). End to end learning for self-driving cars. arXiv, 1–9.
[11] Cao, Z., Yao, Y., Xu, Z., & Wang, T. (2024). Large-scale trajectory data mining for urban mobility analytics: A review. ACM Computing Surveys, 56(6), 1–39.
[12] Chen, C., Liu, Y., Wan, J., Luan, J., & Cui, Q. (2019). Traffic flow prediction with big data: A deep learning approach. IEEE Transactions on Intelligent Transportation Systems, 20(10), 3726–3737.
[13] Chen, M., Mao, S., & Liu, Y. (2014). Big data: A survey. Mobile Networks and Applications, 19(2), 171–209.
[14] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.
[15] Das, S., & Kwasinski, A. (2023). Data engineering pipelines for real-time smart mobility: Design patterns and deployment challenges. IEEE Access, 11, 77901–77920.
[16] Doshi, P., Ranjan, R., & Singh, A. (2022). Edge intelligence for smart transportation: A survey. Future Generation Computer Systems, 128, 390–410.
[17] Fang, Z., Zhang, Y., & Zhang, J. (2024). Privacy-preserving learning in connected transportation systems: Trends and open challenges. IEEE Network, 38(1), 78–86.
[18] Gao, J., Li, Y., & Zhang, X. (2023). Multi-source data fusion for urban traffic state estimation: A review. Transportation Research Part C: Emerging Technologies, 148, 104014.
[19] Guo, J., Huang, W., Williams, B. M., & Wei, Y. (2019). Deep learning for traffic prediction: A review. IEEE Transactions on Intelligent Transportation Systems, 20(12), 4550–4565.
[20] Han, K., Liu, J., Luo, J., & Wang, C. (2024). Real-time intelligent traffic signal control using deep reinforcement learning: A survey. IEEE Transactions on Intelligent Transportation Systems, 25(4), 3122–3143.
[21] He, Z., Zhao, J., & Zhang, L. (2023). MLOps for edge AI in intelligent transportation: Requirements, architectures, and deployment strategies. ACM Transactions on Internet Technology, 23(4), 1–27.
[22] Janai, J., Güney, F., Behl, A., & Geiger, A. (2020). Computer vision for autonomous vehicles: Problems, datasets and state of the art. Foundations and Trends in Computer Graphics and Vision, 12(1–3), 1–308.
[23] Jiang, W., & Zhang, J. (2023). Graph neural networks for traffic forecasting: A comprehensive review. IEEE Transactions on Intelligent Transportation Systems, 24(8), 8201–8223.
[24] Khorasani, A., Gupta, V., & Kannan, R. (2024). Secure data engineering for intelligent transportation: Threat models, defenses, and validation. Computers & Security, 136, 103470.
[25] Kreps, J., Narkhede, N., & Rao, J. (2011). Kafka: A distributed messaging system for log processing. Proceedings of the NetDB Workshop, 1–7.
[26] Li, X., Ma, Y., Zhang, Z., & Wang, J. (2023). Streaming analytics for connected vehicle systems: Architectures and performance evaluation. IEEE Internet of Things Journal, 10(8), 6900–6914.
[27] Liu, Y., Zheng, H., Feng, X., & Chen, Z. (2020). Short-term traffic flow prediction with graph neural networks: A review. IEEE Transactions on Intelligent Transportation Systems, 21(5), 1–14.
[28] Lv, Y., Duan, Y., Kang, W., Li, Z., & Wang, F. Y. (2015). Traffic flow prediction with big data: A deep learning approach. IEEE Transactions on Intelligent Transportation Systems, 16(2), 865–873.
[29] McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 1273–1282.
[30] NIST. (2023). Artificial intelligence risk management framework (AI RMF 1.0). National Institute of Standards and Technology.
[31] NIST. (2020). Security and privacy controls for information systems and organizations. NIST Special Publication 800-53 (Rev. 5).
[32] Paszke, A., Gross, S., Massa, F., et al. (2019). PyTorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, 32, 8024–8035.
[33] Roman, R., Lopez, J., & Mambo, M. (2018). Mobile edge computing, Fog et al.: A survey and analysis of security threats and challenges. Future Generation Computer Systems, 78, 680–698.
[34] Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1), 30–39.
[35] Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646.
[36] Wang, X., Li, Y., & Huang, C. (2024). Trustworthy AI for intelligent transportation systems: Fairness, robustness, and accountability. IEEE Transactions on Intelligent Transportation Systems, 25(1), 110–128.
[37] Xu, X., Weber, I., & Staples, M. (2019). Architecture for blockchain applications. Springer.
[38] Zaharia, M., Chowdhury, M., Franklin, M. J., Shenker, S., & Stoica, I. (2010). Spark: Cluster computing with working sets. Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing, 1–7.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
This work is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). Authors retain full copyright of their published work. Under this license, others are free to share, copy, distribute, transmit, remix, transform, and build upon the published work for any purpose, including commercial use, provided that appropriate credit is given to the original authors, a link to the license is provided, and any changes made are clearly indicated. No additional restrictions may be applied that limit others from doing anything the license permits. All published articles are freely and permanently accessible online to readers worldwide without any subscription or access fees.
License URL: https://creativecommons.org/licenses/by/4.0/
