Unsupervised anomaly detection is a promising approach for vehicle health monitoring, but its deployment in human-driven telemetry is often limited by nominal false positives. A key difficulty is that many telemetry channels are influenced not only by vehicle dynamics, but also by partially observed driver behavior and operating context, making some signals systematically less predictable than others. This paper presents a systematic empirical analysis of how such variability affects false-positive behavior in vehicle telemetry anomaly detection. Using multiple public vehicle telemetry datasets and representative detector families, the feature-level structure of nominal residual error and its contribution to false-positive detections are analysed. Experimental results show that residual error is not distributed uniformly across the telemetry space but is instead concentrated in a small subset of driver-controlled channels. Residual-error concentration persists across model classes, becoming more pronounced in falsely flagged nominal windows, and is not eliminated by increasing training-driver diversity. Feature-level analysis further shows that steering-, braking-, and accelerator-related variables dominate the residual hierarchy, whereas more tightly regulated vehicle-state channels remain comparatively stable. The findings identify a structured and recurrent false-positive failure mode in human-driven telemetry. It is further suggested that reliable deployment will require channel-aware or context-conditioned scoring strategies, rather than increased model complexity alone.
- Open Access
- Article
- Tudor Hirtopanu,
- Zidong Wang,
- Alan Serrano,
- Weibo Liu *
Author Information
Received: 24 Mar 2026 | Revised: 19 Apr 2026 | Accepted: 29 May 2026 | Published: 26 Jun 2026
Abstract
Keywords
anomaly detection | vehicle telemetry | false positives | driver behavior | unsupervised learning | multivariate time series
References
- 1.
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.
- 2.
Ȃström, K.J.; Murray, R.M. Feedback Systems: An Introduction for Scientists and Engineers; Princeton University Press: Princeton, NJ, USA, 2008.
- 3.
Abbaspour, A.; Mokhtari, S.; Sargolzaei, A.; et al. A survey on active fault-tolerant control systems. Electronics 2020, 9, 1513.
- 4.
Zamanzadeh Darban, Z.; Webb, G.I.; Pan, S.; et al. Deep learning for time series anomaly detection: A survey. ACM Comput. Surv. 2024, 56, 263.
- 5.
Pang, G.; Shen, C.; Cao, L.; et al. Deep learning for anomaly detection: A survey. ACM Comput. Surv. 2021, 54, 15.
- 6.
Negash, N.M.; Yang, J. Driver behavior modeling toward autonomous vehicles: Comprehensive review. IEEE Access 2023, 11, 22788–22821.
- 7.
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.
- 8.
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.
- 9.
Lavin, A.; Ahmad, S. Evaluating real-time anomaly detection algorithms: The Numenta Anomaly Benchmark. In Proceedings of the 14th International Conference on Machine Learning and Applications (IEEE ICMLA), Miami, FL, USA, 9–11 December 2015; pp. 38–44.
- 10.
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.
- 11.
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.
- 12.
Zhang, C.; He, Z.; Wu, C.; et al. When context is not enough: Modeling unexplained variability in car-following behavior. arXiv 2026, arXiv:2507.07012.
- 13.
Mannering, F.L.; Shankar, V.; Bhat, C.R. Unobserved heterogeneity and the statistical analysis of highway accident data. Anal. Methods Accid. Res. 2016, 11, 1–16.
- 14.
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.
- 15.
Nunes, P.; Santos, J.; Rocha, E. Challenges in predictive maintenance—A review. CIRP J. Manuf. Sci. Technol. 2023, 40, 53–67.
- 16.
Chandola, V.; Banerjee, A.; Kumar, V. Anomaly detection: A survey. ACM Comput. Surv. 2009, 41, 15.
- 17.
Song, X.; Wu, M.; Jermaine, C.; et al. Conditional anomaly detection. IEEE Trans. Knowl. Data Eng. 2007, 19, 631–645.
- 18.
Wickramasinghe, C.S.; Marino, D.L.; Mavikumbure, H.S.; et al. RX-ADS: Interpretable anomaly detection using adversarial ML for electric vehicle CAN data. IEEE Open J. Ind. Electron. Soc. 2022, 3, 549–561.
- 19.
Nazat, S.; Abdallah, M. XAI-based feature ensemble for enhanced anomaly detection in autonomous driving systems. arXiv 2024, arXiv:2410.15405.
- 20.
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, Virtual, 6–10 July 2020; pp. 3395–3404.
- 21.
Caetano, F.; Carvalho, P.; Cardoso, J.S. Deep anomaly detection for in-vehicle monitoring—An application-oriented review. Appl. Sci. 2022, 12, 10011.
- 22.
Li, Z.; van Leeuwen, M. Explainable contextual anomaly detection using quantile regression forests. Data Min. Knowl. Discov. 2023, 37, 2432–2469.
- 23.
Cherdo, Y.; Miramond, B.; Pgatoquet, A.; et al. Unsupervised anomaly detection for cars CAN sensors time series using small recurrent and convolutional neural networks. Sensors 2023, 23, 5013.
- 24.
Wang, F.; Jiang, Y.; Zhang, R.; et al. A survey of deep anomaly detection in multivariate time series: Taxonomy, applications, and directions. Sensors 2025, 25, 190.
- 25.
King, S.; Zhang, Z.; Yu, R.; et al. Contextual learning for anomaly detection in tabular data. Trans. Mach. Learn. Res. 2026. Available online: https://openreview.net/forum?id=PmqZslRENW (accessed on 2 November 2025).
- 26.
Han, X.; Absar, S.; Zhang, L.; et al. Root cause analysis of anomalies in multivariate time series through Granger causal discovery. In Proceedings of the Thirteenth International Conference on Learning Representations (ICLR), Singapore, 24–28 April 2025. Available online: Available: https://openreview.net/forum?id=k38Th3x4d9 (accessed on 17 November 2025).
- 27.
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 (RAID), Padua, Italy, 30 September–2 October 2024; pp. 531–545.
- 28.
Yao, X.; Calvert, S.C.; Hoogendoorn, S.P. Driving heterogeneity identification using machine learning: A review and framework for analysis. Transp. Res. Interdiscip. Perspect. 2025, 32, 101511.
- 29.
Makridis, M.A.; Anesiadou, A.; Mattas, K.; et al. Characterising driver heterogeneity within stochastic traffic simulation. Transp. B Transp. Dyn. 2023, 11, 725–743.
- 30.
Shi, Y.; Wu, T.; Guo, T.; et al. Traffic simulation optimization considering driving styles. Commun. Transp. Res. 2025, 5, 100181.
- 31.
Yarlagadda, J.; Pawar, D.S. Heterogeneity in the driver behavior: An exploratory study using real-time driving data. J. Adv. Transp. 2022, 2022, 4509071.
- 32.
Ghosh, S.; Zaboli, A.; Hong, J.; et al. A physics-informed context-aware approach for anomaly detection in tele-driving operations under false data injection attacks. IEEE Access 2025, 13, 1.
- 33.
Wasicek, A.R.; Pesé, M.D.; Weimerskirch, A.; et al. Context-aware intrusion detection in automotive control systems. In Proceedings of the 5th ESCAR USA Conference, Ypsilanti, MI, USA, 21–22 June 2017; pp. 1–14. Available online: https://www.weimerskirch.org/files/WasicekEtAl_CAIDS.pdf (accessed on 9 November 2025).
- 34.
Campbell, S.; O’Mahony, N.; Krpalcova, L.; et al. Sensor technology in autonomous vehicles: A review. In Proceedings of the 29th Irish Signals and Systems Conference (ISSC), Belfast, UK, 21–22 June 2018; pp. 1–6.
- 35.
Kwak, B.I.; Woo, J.; Kim, H.K. Know your master: Driver profiling-based anti-theft method. In Proceedings of the 14th Annual Conference on Privacy, Security and Trust (PST), Auckland, New Zealand, 12–14 December 2016; pp. 211–218.
- 36.
Park, K.H.; Kwak, B.I.; Kim, H.K. This car is mine!: Driver pattern dataset extracted from can-bus. 2020. Available online: https://dx.doi.org/10.21227/qar8-sd42 (accessed on 20 October 2025).
- 37.
Weber, M. Automotive OBD-II Dataset. 2023. Available online: https://radar.kit.edu/radar/en/dataset/bCtGxdTklQlfQcAq (accessed on 16 November 2025).
- 38.
Jolliffe, I.T.; Cadima, J. Principal component analysis: A review and recent developments. Philos. Trans. R. Soc. A 2016, 374, 20150202.
- 39.
Cho, K.; van Merrienboer, B.; Gülçehre, Ç.; et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 25–29 October 2014; pp. 1724–1734.
- 40.
Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735–1780.
- 41.
Vaswani, A.; Shazeer, N.; Parmar, N.; et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 2017, 30, 5998–6008. Available online: https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html (accessed on 23 September 2025).
- 42.
Park, D.; Hoshi, Y.; Kemp, C.C. A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder. IEEE Robot. Autom. Lett. 2018, 3, 1544–1551.
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