analiza aiqbench
This research presents an unsupervised anomaly detection framework leveraging Optimal Transport theory to address critical challenges in Industry 4.0, such as data labeling constraints and sensor noise. By utilizing a sliding reference window, the method adapts dynamically to real-time industrial environments while providing counterfactual explanations for improved auditability. The approach demonstrates superior performance over traditional techniques across diverse datasets, including shipping logistics and HVAC systems, without requiring extensive labeled training data.
Optimal Transport for Efficient, Unsupervised Anomaly Detection on Industrial Data
arXiv:2609.13940v1 Announce Type: new Abstract: Effective anomaly detection frameworks are a central pillar of the Industry 4.0 paradigm. In this paper, we introduce an Optimal Transport (OT)-based framework for anomaly detection, designed to detect deviations from normal behaviour in time-series sensor data. The OT-based method requires minimal user input and adapts to real-time data without the need for labelled training data. Our method effectively addresses existing limitations related to data labelling, generalisability, and scalability, demonstrating resilience against short-term fluctuations, noise, and data gaps - common challenges in industrial environments. Additionally, our method provides counterfactual explanations improving the auditability of the approach when deployed in industrial settings. The proposed method learns the mapping between normal and observed operating conditions through a sliding reference window that adapts to the dynamicity of the data. We evaluate our approach on three industrial datasets, from shipping, industrial HVAC systems, and publicly available benchmark data. The method was highly effective in identifying anomalies and reducing false positives, outperforming traditional methods, while maintaining computational efficiency and ease of configuration.
Abstract:Effective anomaly detection frameworks are a central pillar of the Industry 4.0 paradigm. In this paper, we introduce an Optimal Transport (OT)-based framework for anomaly detection, designed to detect deviations from normal behaviour in time-series sensor data. The OT-based method requires minimal user input and adapts to real-time data without the need for labelled training data. Our method effectively addresses existing limitations related to data labelling, generalisability, and scalability, demonstrating resilience against short-term fluctuations, noise, and data gaps - common challenges in industrial environments. Additionally, our method provides counterfactual explanations improving the auditability of the approach when deployed in industrial settings. The proposed method learns the mapping between normal and observed operating conditions through a sliding reference window that adapts to the dynamicity of the data. We evaluate our approach on three industrial datasets, from shipping, industrial HVAC systems, and publicly available benchmark data. The method was highly effective in identifying anomalies and reducing false positives, outperforming traditional methods, while maintaining computational efficiency and ease of configuration.
Machine Learning (cs.LG)
arXiv:2609.13940 [cs.LG]
(or arXiv:2609.13940v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.13940 arXiv-issued DOI via DataCite (pending registration)
Langbridge, Abigail, et al. "Optimal transport for efficient, unsupervised anomaly detection on industrial data." 2024 IEEE International Conference on Big Data (BigData). IEEE, 2024
https://doi.org/10.1109/BigData62323.2024.10825081 DOI(s) linking to related resources
Text integral sub licența deschisă a publicației · 215 cuvinte
