Interpreting Outliers in Time Series Data through Decoding Autoencoder
This work addresses the need for explainable AI in safety-critical manufacturing systems, offering a domain-specific solution for outlier interpretation.
The study tackled the problem of interpreting outliers in manufacturing time series data by using autoencoders for anomaly detection and proposing AEE, a novel method that aggregates multiple XAI techniques for better interpretation, achieving quantitative and qualitative improvements in explanation quality.
Outlier detection is a crucial analytical tool in various fields. In critical systems like manufacturing, malfunctioning outlier detection can be costly and safety-critical. Therefore, there is a significant need for explainable artificial intelligence (XAI) when deploying opaque models in such environments. This study focuses on manufacturing time series data from a German automotive supply industry. We utilize autoencoders to compress the entire time series and then apply anomaly detection techniques to its latent features. For outlier interpretation, we (i) adopt widely used XAI techniques to the autoencoder's encoder. Additionally, (ii) we propose AEE, Aggregated Explanatory Ensemble, a novel approach that fuses explanations of multiple XAI techniques into a single, more expressive interpretation. For evaluation of explanations, (iii) we propose a technique to measure the quality of encoder explanations quantitatively. Furthermore, we qualitatively assess the effectiveness of outlier explanations with domain expertise.