Generative Adversarial Networks for High Fidelity Traffic Simulation and Prediction in Intelligent Transportation Systems

Generative Adversarial Networks for High Fidelity Traffic Simulation and Prediction in Intelligent Transportation Systems

Authors

  • Yuan Sun Rutgers University, New Brunswick, USA
  • Jorge Ortiz Rutgers University, New Brunswick, USA

DOI:

https://doi.org/10.53469/wjimt.2024.07(06).20

Keywords:

Generative Adversarial Networks (GANs), Intelligent Transportation Systems (ITS), Cross-Modal Data Generation, Traffic Scenario Simulation, Urban Traffic Management

Abstract

Intelligent transportation systems (ITS) face increasing challenges in coping with complex urban traffic scenarios, including congestion propagation, vehicle rerouting, and the combined impact of environmental factors. The study proposes a framework based on generative adversarial networks (GANs) combined with advanced cross-modal data generation techniques to reconstruct, simulate, and predict traffic scenarios with high fidelity. The framework improves traffic perception and prediction capabilities by generating synthetic traffic images, videos, and text-based event alerts, effectively filling the gaps caused by data scarcity or sensor failure. The framework is validated in a real traffic disturbance scenario - the sudden closure of a main road during peak traffic hours. The results show that the framework performs very well: the traffic anomaly detection rate is improved by 12%, the structural similarity index (SSIM) of spatial reconstruction reaches 0.95, and the congestion prediction accuracy (CPA) reaches 91%. In addition, the framework can accurately model complex spatiotemporal patterns, enabling practical applications in path optimization, signal control, and connected vehicle coordination, reducing traffic delays by 15% and improving intersection efficiency by 10%. This study demonstrates the effectiveness and versatility of generative AI in intelligent transportation systems, providing practical insights into solving modern urban transportation challenges. The proposed framework pushes the state-of-the-art in traffic modeling and lays a solid foundation for the development and innovation of future smart cities.

References

Tamayo-Urgilés, D., Sanchez-Gordon, S., Valdivieso Caraguay, Á. L., & Hernández-Álvarez, M. (2024). GAN-Based Generation of Synthetic Data for Vehicle Driving Events. Applied Sciences, 14(20), 9269.

Sun, Y., Pargoo, N. S., Jin, P. J., & Ortiz, J. (2024). Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF. arXiv preprint arXiv:2406.04481.

Barceló, J. (2010). Models, traffic models, simulation, and traffic simulation. Fundamentals of traffic simulation, 1-62.

Li, Z., Chowdhury, M., Bhavsar, P., & He, Y. (2015). Optimizing the performance of vehicle-to-grid (V2G) enabled battery electric vehicles through a smart charge scheduling model. International Journal of Automotive Technology, 16, 827-837.

Gu, J., Narayanan, V., Wang, G., Luo, D., Jain, H., Lu, K., ... & Yao, L. (2020, November). Inverse design tool for asymmetrical self-rising surfaces with color texture. In Proceedings of the 5th Annual ACM Symposium on Computational Fabrication (pp. 1-12).

Yang, J., Chen, T., Qin, F., Lam, M. S., & Landay, J. A. (2022, April). Hybridtrak: Adding full-body tracking to vr using an off-the-shelf webcam. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems (pp. 1-13).

Tedjopurnomo, D. A., Bao, Z., Zheng, B., Choudhury, F. M., & Qin, A. K. (2020). A survey on modern deep neural network for traffic prediction: Trends, methods and challenges. IEEE Transactions on Knowledge and Data Engineering, 34(4), 1544-1561.

Li, Z., Dey, K., Chowdhury, M., & Bhavsar, P. (2016). Connectivity supported dynamic routing of electric vehicles in an inductively coupled power transfer environment. IET Intelligent Transport Systems, 10(5), 370-377.

Lee, I. K., Xie, R., Luz-Madrigal, A., Min, S., Zhu, J., Jin, J., ... & Ma, Z. (2023). Micromolded honeycomb scaffold design to support the generation of a bilayered RPE and photoreceptor cell construct. Bioactive Materials, 30, 142-153.

Lian, J. (2023). Applications of Machine Learning Algorithms in Data Mining for Big Data Analytics. Insights in Computer, Signals and Systems, 1(1), 1-10.

Devadhas Sujakumari, P., & Dassan, P. (2023). Generative Adversarial Networks (GAN) and HDFS-Based Realtime Traffic Forecasting System Using CCTV Surveillance. Symmetry, 15(4), 779.

Shatnawi, M. A., & Bani Younes, M. (2024). An enhanced model for detecting and classifying emergency vehicles using a generative adversarial network (GAN). Vehicles, 6(3), 1114-1139.

Mekala, M. S., Park, W., Dhiman, G., Srivastava, G., Park, J. H., & Jung, H. Y. (2022). Deep learning inspired object consolidation approaches using lidar data for autonomous driving: a review. Archives of Computational Methods in Engineering, 29(5), 2579-2599.

Zhu, J., Xu, T., Zhang, Y., & Fan, Z. (2024). Scalable Edge Computing Framework for Real-Time Data Processing in Fintech Applications. International Journal of Advance in Applied Science Research, 3, 85-92.

Lian J. Research on Data Quality Analysis Based on Data Mining. Academic Journal of Science and Technology. 2024 Oct 10;12(3):16-9.

Lian, J., & Chen, T. (2024). Research on Complex Data Mining Analysis and Pattern Recognition Based on Deep Learning. Journal of Computing and Electronic Information Management, 12(3), 37-41.

Chen, T., Lian, J., & Sun, B. (2024). An Exploration of the Development of Computerized Data Mining Techniques and Their Application. International Journal of Computer Science and Information Technology, 3(1), 206-212.

Liu, Z., Costa, C., & Wu, Y. (2024). Data-Driven Optimization of Production Efficiency and Resilience in Global Supply Chains. Journal of Theory and Practice of Engineering Science, 4(08), 23-33.

Liu, Z., Costa, C., & Wu, Y. (2024). Quantitative Assessment of Sustainable Supply Chain Practices Using Life Cycle and Economic Impact Analysis.

Liu, Z., Costa, C., & Wu, Y. (2024). Leveraging Data-Driven Insights to Enhance Supplier Performance and Supply Chain Resilience.

Li, W. (2022, April). Rural-to-Urban Migration and Overweight Status in Low-and Middle-Income Countries: Evidence From Longitudinal Data in Indonesia. In PAA 2022 Annual Meeting. PAA.

Sun, Y., Pargoo, N. S., Ehsan, T., & Ortiz, Z. Z. J. (2024). VCHAR: Variance-Driven Complex Human Activity Recognition framework with Generative Representation. arXiv preprint arXiv:2407.03291.

Zhang, J., Zhao, Y., Chen, D., Tian, X., Zheng, H., & Zhu, W. (2024). MiLoRA: Efficient mixture of low-rank adaptation for large language models fine-tuning. arXiv. https://arxiv.org/abs/2410.18035

Lin, Y. (2024). Application and Challenges of Computer Networks in Distance Education. Computing, Performance and Communication Systems, 8(1), 17-24.

Lin, Y. (2024). Design of urban road fault detection system based on artificial neural network and deep learning. Frontiers in neuroscience, 18, 1369832.

Lin, Y. (2024). Enhanced Detection of Anomalous Network Behavior in Cloud-Driven Big Data Systems Using Deep Learning Models. Journal of Theory and Practice of Engineering Science, 4(08), 1-11.

Zhang, Y., & Fan, Z. (2024). Memory and Attention in Deep Learning. Academic Journal of Science and Technology, 10(2), 109-113.

Zhang, Y., & Fan, Z. (2024). Research on Zero knowledge with machine learning. Journal of Computing and Electronic Information Management, 12(2), 105-108.

Xie, T., Li, T., Zhu, W., Han, W., & Zhao, Y. (2024). PEDRO: Parameter-Efficient Fine-tuning with Prompt DEpenDent Representation MOdification. arXiv preprint arXiv:2409.17834.

Sun, L. (2023). A New Perspective on Cybersecurity Protection: Research on DNS Security Detection Based on Threat Intelligence and Data Statistical Analysis. Computer Life, 11(3), 35-39.

Zhou, R. (2024). Scalable Multi-View Stereo Camera Array for Real-Time Image Capture and 3D Display in Real-World Applications. Mathematical Modeling and Algorithm Application, 2(2), 43-48.

Sun, L. (2024). Securing supply chains in open source ecosystems: Methodologies for determining version numbers of components without package management files. Journal of Computing and Electronic Information Management, 12(1), 32-36.

Tu, H., Shi, Y., & Xu, M. (2023, May). Integrating conditional shape embedding with generative adversarial network-to assess raster format architectural sketch. In 2023 Annual Modeling and Simulation Conference (ANNSIM) (pp. 560-571). IEEE.

Shi, Y., Ma, C., Wang, C., Wu, T., & Jiang, X. (2024, May). Harmonizing Emotions: An AI-Driven Sound Therapy System Design for Enhancing Mental Health of Older Adults. In International Conference on Human-Computer Interaction (pp. 439-455). Cham: Springer Nature Switzerland.

Eom, M., & Kim, B. I. (2020). The traffic signal control problem for intersections: a review. European transport research review, 12, 1-20.

Malihi, S., Potseluyko, L., Mathew, A., Alavi, H., Reja, V. K., Pan, Y., ... & Brilakis, I. (2024). Review of multimodal data and their applications for road maintenance.

Downloads

Published

2024-12-19
Loading...