Explaining and upsampling anomalies in time-series sensor data.

Pirie, Craig

Abstract

The aims of this research was to improve anomaly detection methods in multi-sensor data by extending current re-sampling and explanation methods to work in a time-series setting. While there is a plethora of literature surrounding XAI for tabular data, the same cannot be said for the multivariate time-series settings. It is also known that selecting an optimal baseline for attribution methods such as integrated gradients remains an open research question. Accordingly, the author is interested to explore the role of Case-Based Reasoning (CBR) in three ways: 1) to represent time series data from multiple sensors to enable effective anomaly detection; 2) to create explanation experiences (explanation-baseline pair) that can support the identification of suitable baselines to improve attribution discovery with integrated gradients for multivariate time-series settings; and 3) to represent the disagreements between past explanations in a case-base to better inform strategies for solving disagreement between explainers in the future. A common theme across my research is the need to explore how inherent relationships between sensors (causal or other ad-hoc inter-dependencies) can be captured and represented to improve anomaly detection and the follow-on explanation phases.

Citation

PIRIE, C. 2022. Explaining and upsampling anomalies in time-series sensor data. In Reuss, P. and Schönborn, J. (eds.) Proceedings of the 30th Doctoral consortium of the international conference on case-based reasoning (ICCBR-DC 2022), co-located with the 30th International conference on case-based reasoning (ICCBR 2022), 12-15 September 2022, Nancy, France. CEUR workshop proceedings, 3418. Aachen: CEUR-WS [online], pages 16-21. Available from: https://ceur-ws.org/Vol-3418/ICCBR_2022_DC_paper13.pdf

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 30th Doctoral consortium of the international conference on case-based reasoning (ICCBR-DC 2022), co-located with the 30th International conference on case-based reasoning (ICCBR 2022)
• Start Date: Sep 12, 2022
• End Date: Sep 15, 2022
• Acceptance Date: Jul 22, 2022
• Online Publication Date: Sep 15, 2022
• Publication Date: Jun 13, 2023
• Deposit Date: Jul 21, 2023
• Publicly Available Date: Jul 21, 2023
• Publisher: CEUR-WS
• Peer Reviewed: Peer Reviewed
• Pages: 16-21
• Series Title: CEUR workshop proceedings
• Series Number: 3418
• Series ISSN: 1613-0073
• Keywords: Anomaly detection; Time-series; Negative sampling; Integrated gradients
• Public URL: https://rgu-repository.worktribe.com/output/2015549
• Publisher URL: https://ceur-ws.org/Vol-3418/ICCBR_2022_DC_paper13.pdf