Anomaly detection in human-driven vehicle telemetry is complicated by mixed uncertainty: nominal deviations may arise either from stochastic driver behavior or from genuine departures from learned vehicle dynamics. Conventional forecastingbased detectors typically treat both as predictive error, which can produce heavytailed anomaly-score distributions and elevated false-positive rates under unseen driver behavior. To address this limitation, we propose the Uncertainty-Gated Mixture Model (U-GMM), a feature-wise anomaly-scoring framework that combines conditional probabilistic forecasting with marginal plausibility estimation through an uncertaintyaware gating mechanism. The conditional component captures temporal consistency with recent history, while the marginal component evaluates whether an observation remains plausible under the broader nominal feature distribution. The learned gate then uses predictive uncertainty to adaptively balance these two sources of anomaly evidence, reducing undue score inflation in nominally stochastic channels while preserving sensitivity to dynamically inconsistent or globally implausible deviations. Experiments on real-world vehicle telemetry datasets show that the proposed framework improves threshold transfer under unseen-driver evaluation, achieving up to a 2.5× reduction in extreme false-positive rate while maintaining competitive fault detection performance under injected anomalies. These results indicate that reliable anomaly detection in human-in-the-loop systems depends not only on predictive model capacity, but also on uncertainty-aware score construction that distinguishes difficult-to-predict nominal behavior from genuinely abnormal system dynamics.
- Open Access
- Article
Uncertainty-Gated Mixture Modeling for Anomaly Detection in Human-in-the-Loop Vehicle Systems
- Tudor Hirtopanu,
- Zidong Wang,
- Alan Serrano,
- Weibo Liu *
Author Information
Received: 24 Mar 2026 | Revised: 20 May 2026 | Accepted: 25 May 2026 | Published: 28 May 2026
Abstract
Keywords
anomaly detection | driver behavior | deep learning | false positives | multivariate time-series forecasting
References
- 1.
Pang, G.; Shen, C.; Cao, L.; et al. Deep Learning for Anomaly Detection: A Survey. ACM Comput. Surv. 2021, 54, 38. https://doi.org/10.1145/3439950.
- 2.
Darban, Z.Z.; Webb, G.I.; Pan, S.; et al. Deep Learning for Time Series Anomaly Detection: A Survey. ACM Comput. Surv. 2024, 57, 1–42. https://doi.org/10.1145/3691338.
- 3.
Su, Y.; Zhao, Y.; Niu, C.; et al. Robust Anomaly Detection for Multivariate Time Series Through Stochastic Recurrent Neural Network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA, 4–8 August 2019; pp. 2828–2837.
- 4.
Cherdo, Y.; Miramond, B.; Pegatoquet, A.; et al. Unsupervised Anomaly Detection for Cars CAN Sensors Time Series Using Small Recurrent and Convolutional Neural Networks. Sensors 2023, 23, 5013.
- 5.
Al-Zeyadi, M.; Andreu-Perez, J.; Hagras, H.; et al. Deep Learning Towards Intelligent Vehicle Fault Diagnosis. In Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 19–24 July 2020; pp. 1–7.
- 6.
Muenchhof, M.; Beck, M.; Isermann, R. Fault Diagnosis and Fault Tolerance of Drive Systems: Status and Research. Eur. J. Control 2009, 15, 370–388.
- 7.
Isermann, R. Model-Based Fault-Detection and Diagnosis: Status and Applications. Annu. Rev. Control 2005, 29, 71–85.
- 8.
Driggs-Campbell, K.; Shia, V.; Bajcsy, R. Improved Driver Modeling for Human-in-the-Loop Vehicular Control. In Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA, 26–30 May 2015; pp. 1654–1661.
- 9.
Zhang, C.; He, Z.; Wu, C.; et al. When Context Is Not Enough: Modeling Unexplained Variability in Car-Following Behavior. arXiv 2025, arXiv:2507.07012.
- 10.
Wei, C.; Qin, Z.; Li, S.; et al. PDB: Not All Drivers Are the Same—A Personalized Dataset for Understanding Driving Behavior. arXiv 2025, arXiv:2503.06477.
- 11.
Chu, H.; Zhuang, H.; Wang, W.; et al. A Review of Driving Style Recognition Methods From Short-Term and Long-Term Perspectives. IEEE Trans. Intell. Veh. 2023, 8, 4599–4612.
- 12.
Chen, C.Y.; Shin, K.G.; Dadras, S. Context-Aware Anomaly Detection Using Vehicle Dynamics. In Proceedings of the 27th International Symposium on Research in Attacks, Intrusions and Defenses, Padua Italy, 30 September–2 October 2024; pp. 531–545.
- 13.
Nunes, P.; Santos, J.; Rocha, E. Challenges in Predictive Maintenance: A Review. CIRP J. Manuf. Sci. Technol. 2023,
40, 53–67. - 14.
Song, X.; Wu, M.; Jermaine, C.; et al. Conditional Anomaly Detection. IEEE Trans. Knowl. Data Eng. 2007, 19, 631–645.
- 15.
Li, Z.; van Leeuwen, M. Explainable Contextual Anomaly Detection Using Quantile Regression Forests. Data Min. Knowl. Discov. 2023, 37, 2517–2563.
- 16.
Chandola, V.; Banerjee, A.; Kumar, V. Anomaly Detection: A Survey. ACM Comput. Surv. 2009, 41, 1–58.
- 17.
Zimek, A.; Schubert, E.; Kriegel, H.P. A Survey on Unsupervised Outlier Detection in High-Dimensional Numerical Data. Stat. Anal. Data Min. 2012, 5, 363–387.
- 18.
Aggarwal, C.C.; Yu, P.S. Outlier Detection for High Dimensional Data. In Proceedings of the 2001 ACM SIGMOD international conference on Management of Data, Santa Barbara, CA, USA, 21–24 May 2001; pp. 37–46.
- 19.
Malhotra, P.; Ramakrishnan, A.; Anand, G.; et al. LSTM-Based Encoder-Decoder for Multi-Sensor Anomaly Detection. arXiv 2016, arXiv:1607.00148.
- 20.
Munir, M.; Siddiqui, S.A.; Dengel, A.; et al. DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series. IEEE Access 2019, 7, 1991–2005.
- 21.
Audibert, J.; Michiardi, P.; Guyard, F.; et al. USAD: UnSupervised Anomaly Detection on Multivariate Time Series. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, online, 6–10 July 2020; pp. 3395–3404.
- 22.
Ruff, L.; Vandermeulen, R.; Goernitz, N.; et al. Deep One-Class Classification. In Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, 10–15 July 2018; Volume 80, pp. 4393–4402.
- 23.
Xu, J.; Wu, H.; Wang, J.; et al. Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy. In Proceedings of the 10th International Conference on Learning Representations (ICLR 2022), online, 25–29 April 2022.
- 24.
Zhao, H.; Wang, Y.; Duan, J.; et al. Multivariate Time-Series Anomaly Detection via Graph Attention Network. In Proceedings of the 2020 IEEE International Conference on Data Mining (ICDM), Sorrento, Italy, 17–20 November 2020;
pp. 841–850. - 25.
Tuli, S.; Casale, G.; Jennings, N.R. TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data. Proc. VLDB Endow. 2022, 15, 1201–1214.
- 26.
Hayes, M.A.; Capretz, M.A.M. Contextual Anomaly Detection Framework for Big Sensor Data. J. Big Data 2015, 2, 2.
- 27.
Kwak, B.I.; Woo, J.; Kim, H.K. Know Your Master: Driver Profiling-Based Anti-Theft Method. In Proceedings of the 2016 14th Annual Conference on Privacy, Security and Trust (PST), Auckland, New Zealand, 12–14 December 2016; pp. 211–218.
- 28.
Hallac, D.; Sharang, A.; Stahlmann, R.; et al. Driver Identification Using Automobile Sensor Data From a Single Turn. In Proceedings of the 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazil, 1–4 November 2016; pp. 953–958.
- 29.
Fugiglando, U.; Massaro, E.; Santi, P.; et al. Driving Behavior Analysis Through CAN Bus Data in an Uncontrolled Environment. IEEE Trans. Intell. Transp. Syst. 2019, 20, 737–748.
- 30.
Marchegiani, L.; Posner, I. Long-Term Driving Behaviour Modelling for Driver Identification. In Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, USA, 4–7 November 2018; pp. 913–919.
- 31.
Seraji, M.H.M.; Haghshenas, S.S.; Haghshenas, S.S.; et al. A State-of-the-Art Review on Machine Learning Techniques for Driving Behavior Analysis: Clustering and Classification Approaches. Complex Intell. Syst. 2025, 11, 386.
- 32.
Xu, B.; Zhu, Q. Dynamic Probabilistic Latent Variable Model with Exogenous Variables for Dynamic Anomaly Detection. In Proceedings of the 2023 American Control Conference (ACC), San Diego, CA, USA, 31 May–2 June 2023; pp. 3945–3950.
- 33.
Usmani, U.A.; Aziz, I.A.; Jaafar, J.; et al. Deep Learning for Anomaly Detection in Time-Series Data: An Analysis of Techniques, Review of Applications, and Guidelines for Future Research. IEEE Access 2024, 12, 174564–174590.
- 34.
Scholkopf, B.; Locatello, F.; Bauer, S.; et al. Toward Causal Representation Learning. Proc. IEEE 2021, 109, 612–634.
- 35.
Bilal, H.; Rehman, A.; Aslam, M.S.; et al. Hybrid TrafficAI: A Generative AI Framework for Real-Time Traffic Simulation and Adaptive Behavior Modeling. IEEE Trans. Intell. Transp. Syst. 2025, 1–17.
- 36.
Ullah, I.; Khalil, I.; Bai, X.; et al. An Ensemble-Based Hybrid Model for the Detection of Attacks in the Internet of Vehicular Things. IEEE Trans. Intell. Transp. Syst. 2025, 26, 17914–17927.
- 37.
Wirnsberger, P.; Papamakarios, G.; Ibarz, B.; et al. Normalizing Flows for Atomic Solids. Mach. Learn. Sci. Technol. 2022, 3, 025009.
- 38.
Durkan, C.; Bekasov, A.; Murray, I.; et al. Neural Spline Flows. In Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada, 8–14 December 2019; Volume 32, pp. 7511–7522
- 39.
Park, K.H.; Kwak, B.I.; Kim, H.K. This Car Is Mine!: Driver Pattern Dataset Extracted from CAN-Bus. Available online: https://ieee-dataport.org/open-access/car-mine-driver-pattern-dataset-extracted-can-bus (accessed on 22 December 2025).
- 40.
Weber, M. Automotive OBD-II Dataset. Available online: https://doi.org/10.35097/1130 (accessed on 16 November 2025).
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com