Keywords
vehicular communication streams
online anomaly detection
delayed cluster updating
V2I monitoring
data stream mining
connected transportation security
Abstract
Roadside units in connected transportation systems generate continuous communication streams from vehicle messages, signal controllers, traffic sensors, edge servers, and cooperative perception services. These streams are affected by traffic density, weather, road events, handover behavior, and temporary communication congestion. Repeated abnormal communication patterns, such as spoofed message bursts or unstable vehicle-to-infrastructure links, may be gradually treated as normal by conventional online clustering models. This study proposes a delay-constrained cluster updating method for roadside unit communication stream anomaly detection. The method constructs online clusters from message frequency, packet interval, vehicle-density context, signal-phase state, handover count, retransmission rate, and source-location consistency. A delayed update mechanism restricts cluster movement when suspicious communication patterns appear repeatedly within short temporal windows. Experiments are conducted on a roadside communication dataset containing 420 roadside units, 68 signalized corridors, 1.86 million vehicle identifiers, and 42 communication indicators collected over 76 days. The dataset includes 529 million message-flow records and 3,180 annotated abnormal episodes, including spoofed safety-message bursts, abnormal retransmission storms, unstable handover sequences, malicious location inconsistency, and edge-link congestion. The proposed method reduces median detection delay from 8.6 minutes to 2.1 minutes compared with streaming k-means. False alerts are limited to 3.6 cases per corridor-month. The clustering engine processes 116,000 message records per second, and the median update latency remains 19 ms per roadside unit window. The delayed update mechanism prevents 2,480 suspicious communication patterns from being prematurely absorbed into normal clusters during rush-hour traffic. The results demonstrate that anti-habituation cluster updating can improve anomaly detection in dynamic vehicle-to-infrastructure data streams.
References
Jiao, Y., Zhao, B., Wang, A., & Shi, T. (2026). Construction and Empirical Study of a Modularized Teaching System for Art Courses Based on a Unified Training Pathway.
Ukkusuri, S., Hamim, O. F., Lei, Z., Ka, E., Salek, M. S., Chowdhury, M., ... & Thuraisingham, B. (2025). Cybersecurity for next-generation road transportation: A review. Journal on Autonomous Transportation Systems, 3(2), 1-42.
Du, Y., Dong, Y., Liu, Q., & Chen, Z. (2026). Modal Reliability Assessment and Drift Early Warning in Visible-Infrared Target Tracking. Available at SSRN 7132381.
Kadiyala, A. (2025). Securing intelligent intersections: the effects of physical sensor attacks on traffic efficiency and tracking accuracy (Master's thesis, University of California, Irvine).
Chen, X., Xiao, H., Zeng, Z., Zhang, S., & Xiao, R. (2025). Fine-Grained Multivariate Time Series Anomaly Detection via Causal Inference. Knowledge-Based Systems, 114765.
Xiong, W., Zeng, Y., & Guo, Y. (2026). A Study on the Characterization of Building MEP System States and the Learning of Behavioral Patterns Driven by Large-Scale Operational Data. Available at SSRN 7121883.
Hota, L., Nayak, B. P., Sahoo, B., & Kumar, A. (2025). Performance Analysis of An Adaptive Contention Window Approach for Message Dissemination in VANETs. Wireless Personal Communications, 143(3), 503-528.
Yin, J., Huang, Y., & Rao, H. (2026). A Study on the Dynamic Evolution of Learning Behavior and Outcome Prediction in Digital Educational Environments. Available at SSRN 6607139.
Yang, J. (2026). Computational Analysis of How Digital Non-Clinical Communication Tools Influence Social Participation Among Older Adults in Community-Based Elderly Care. Available at SSRN 6682838.
Abreu, R., Branco, F., Reis, M. J. C. S., & Serôdio, C. (2025). Cybersecurity in connected and autonomous vehicles: A systematic review of automotive security. IEEE Access, 13, 116818-116855.
Zhang, Z. (2026). A Study on Multimodal Product Understanding and Assembly Guidance Optimization in e-commerce for Complex Consumer Goods. Available at SSRN 6734559.
Hong, Z., Xu, T., & Chen, H. (2026). Automated Detection and Reclamation of Orphaned Compute and Storage Resources in Cloud Infrastructure. Available at SSRN 7116258.
Abdulkadhim, F. G., Al Farttoosi, D. S., Al-Shammari, A. H. S., Al Muqarm, A. M. A., & Kadhim, A. R. (2025). Efficient deployment of roadside units in vehicular networks using optimization methods. National Journal of Antennas and Propagation, 7(2), 187-199.
Nigam, N., Singh, D. P., Choudhary, J., & Solanki, S. (2025). An Efficient Model for Real-Time Traffic Density Analysis and Management Using Visual Graph Networks. IEEE Access.
Li, J., Ma, R., & Gu, Y. (2026). From Audit Requirements to Computable Software Architecture: A Rule-Engine and Evidence-Indexing Method for Trusted Digital Infrastructure.
Zhang, Z., Gao, Y., & Tong, Y. (2026). Semantic-Temporal Graph Learning for Demand Forecasting and Resource Allocation in Public Information Systems. Available at SSRN 6792279.
Basso, F., Fernández-Figueroa, V., Maldonado, T., Martínez, D. A., Pezoa, R., Varas, M., & Villa-Rodríguez, F. (2026). Recalibration strategies for real-time crash prediction: adaptive drift detection vs. cumulative retraining under rare-event class imbalance. Transportation Letters, 1-41.
Qi, C., & Qiao, X. (2026). Building Reliable AI Systems: A Framework That Bridges Architecture and Operations. Available at SSRN 6795298.
Zhang, Y., Gu, W., & Wang, J. (2025, December). Construction of Wind Farm Asset Health Index Based on Multi-Dimensional Indicators and Analytic Hierarchy Process and Its Correlation with Operational Performance. In Proceedings of the 2025 International Conference on Digital Transformation and Management (pp. 317-323).
Su, D., & Zhang, H. Developing a Data-Driven Computational Framework for Scalable Special Education Practices for Autism and Intellectual Disabilities in the US Public School System.
Aghayengejeh, N. P., Balafar, M. A., Tanha, J., & Selver, M. A. (2026). Beyond predefined clusters: A comprehensive review of clustering methods for unknown cluster numbers. IEEE Transactions on Knowledge and Data Engineering.
Du, Y., Liu, Q., Dong, Y., & Chen, Z. (2026). Cross-Domain Transfer and Few-Shot Recognition of Defect Images in Complex Industrial Settings.
Kirmayer, N., Tayouri, D., Murillo, A., Sekiya, M., Shabtai, A., & Puzis, R. (2026). 2: Event-Centric Explainability for Cybersecurity Through Multi-Agent LLM Investigations. arXiv preprint arXiv:2607.26201.
Zhang, Y., & Wang, J. (2026, February). Design and Implementation of a Computer-Aided Full Lifecycle Quality Management System for Wind Farms in Upgrades, Renovations, and Subcontractor Supervision. In Proceedings of the 2026 International Conference on Big Data and Informatization Education (pp. 1309-1314).
Saoud, B., Shayea, I., Alnakhli, M. A., & Mohamad, H. (2025). Mobility and handover management in 5G/6G networks: Challenges, innovations, and sustainable solutions. Technologies, 13(8), 352.
Xiong, W., & Zeng, Y. (2026). Multi-Layer Coupled Diagnosis of Energy Efficiency Degradation in Complex Building MEP Systems and Identification of Optimization Boundaries. Available at SSRN 7121782.
Hong, Z., Chen, H., & Xu, T. (2026). Real-Time Capacity Risk Forecasting for Low-Latency Financial Trading Cloud Platforms. Available at SSRN 7118180.
Li, J., Zhang, Y., & Gu, Y. (2026). Chain-Hash Audit Framework with Trusted Anchoring for Tamper-Evident Evidence Lifecycle Management.
Kavitha, K. N., Saranya, M., Arun Balaji, P., & Ramya, R. (2026, May). Edge-Intelligent Deep Learning Framework for Real-Time Anomaly Detection in AI-Enabled Internet of Things Systems. In 2026 6th International Conference on Pervasive Computing and Social Networking (ICPCSN) (pp. 665-672). IEEE.
Fu, Y., Gui, H., Li, W., & Wang, Z. (2020, August). Virtual Material Modeling and Vibration Reduction Design of Electron Beam Imaging System. In 2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) (pp. 1063-1070). IEEE.
Hamood, M. A. M. (2025). Towards Reliable and Resource-Efficient Federated Learning in Hierarchical Wireless Edge Networks (Doctoral dissertation, Hamad Bin Khalifa University (Qatar)).
Zhu, W., Yao, Y., & Yang, J. (2025). Optimizing Financial Risk Control for Multinational Projects: A Joint Framework Based on CVaR-Robust Optimization and Panel Quantile Regression.