M$^2$AD: Multi-Sensor Multi-System Anomaly Detection through Global Scoring and Calibrated Thresholding

Sarah Alnegheimish, Zelin He, Matthew Reimherr, Akash Chandrayan, Abhinav Pradhan, Luca D’Angelo
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:4384-4392, 2025.

Abstract

With the widespread availability of sensor data across industrial and operational systems, we frequently encounter heterogeneous time series from multiple systems. Anomaly detection is crucial for such systems to facilitate predictive maintenance. However, most existing anomaly detection methods are designed for either univariate or single-system multivariate data, making them insufficient for these complex scenarios. To address this, we introduce M$^2$AD, a framework for unsupervised anomaly detection in multivariate time series data from multiple systems. M$^2$AD employs deep models to capture expected behavior under normal conditions, using the residuals as indicators of potential anomalies. These residuals are then aggregated into a global anomaly score through a Gaussian Mixture Model and Gamma calibration. We theoretically demonstrate that this framework can effectively address heterogeneity and dependencies across sensors and systems. Empirically, M$^2$AD outperforms existing methods in extensive evaluations by 21% on average, and its effectiveness is demonstrated on a large-scale real-world case study on 130 assets in Amazon Fulfillment Centers. Our code and results are available at \url{https://github.com/sarahmish/M2AD.}

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-alnegheimish25a, title = {M$^2$AD: Multi-Sensor Multi-System Anomaly Detection through Global Scoring and Calibrated Thresholding}, author = {Alnegheimish, Sarah and He, Zelin and Reimherr, Matthew and Chandrayan, Akash and Pradhan, Abhinav and D'Angelo, Luca}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {4384--4392}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/alnegheimish25a/alnegheimish25a.pdf}, url = {https://proceedings.mlr.press/v258/alnegheimish25a.html}, abstract = {With the widespread availability of sensor data across industrial and operational systems, we frequently encounter heterogeneous time series from multiple systems. Anomaly detection is crucial for such systems to facilitate predictive maintenance. However, most existing anomaly detection methods are designed for either univariate or single-system multivariate data, making them insufficient for these complex scenarios. To address this, we introduce M$^2$AD, a framework for unsupervised anomaly detection in multivariate time series data from multiple systems. M$^2$AD employs deep models to capture expected behavior under normal conditions, using the residuals as indicators of potential anomalies. These residuals are then aggregated into a global anomaly score through a Gaussian Mixture Model and Gamma calibration. We theoretically demonstrate that this framework can effectively address heterogeneity and dependencies across sensors and systems. Empirically, M$^2$AD outperforms existing methods in extensive evaluations by 21% on average, and its effectiveness is demonstrated on a large-scale real-world case study on 130 assets in Amazon Fulfillment Centers. Our code and results are available at \url{https://github.com/sarahmish/M2AD.}} }
Endnote
%0 Conference Paper %T M$^2$AD: Multi-Sensor Multi-System Anomaly Detection through Global Scoring and Calibrated Thresholding %A Sarah Alnegheimish %A Zelin He %A Matthew Reimherr %A Akash Chandrayan %A Abhinav Pradhan %A Luca D’Angelo %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-alnegheimish25a %I PMLR %P 4384--4392 %U https://proceedings.mlr.press/v258/alnegheimish25a.html %V 258 %X With the widespread availability of sensor data across industrial and operational systems, we frequently encounter heterogeneous time series from multiple systems. Anomaly detection is crucial for such systems to facilitate predictive maintenance. However, most existing anomaly detection methods are designed for either univariate or single-system multivariate data, making them insufficient for these complex scenarios. To address this, we introduce M$^2$AD, a framework for unsupervised anomaly detection in multivariate time series data from multiple systems. M$^2$AD employs deep models to capture expected behavior under normal conditions, using the residuals as indicators of potential anomalies. These residuals are then aggregated into a global anomaly score through a Gaussian Mixture Model and Gamma calibration. We theoretically demonstrate that this framework can effectively address heterogeneity and dependencies across sensors and systems. Empirically, M$^2$AD outperforms existing methods in extensive evaluations by 21% on average, and its effectiveness is demonstrated on a large-scale real-world case study on 130 assets in Amazon Fulfillment Centers. Our code and results are available at \url{https://github.com/sarahmish/M2AD.}
APA
Alnegheimish, S., He, Z., Reimherr, M., Chandrayan, A., Pradhan, A. & D’Angelo, L.. (2025). M$^2$AD: Multi-Sensor Multi-System Anomaly Detection through Global Scoring and Calibrated Thresholding. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:4384-4392 Available from https://proceedings.mlr.press/v258/alnegheimish25a.html.

Related Material