Unsupervised Distance Metric Learning for Anomaly Detection Over Multivariate Time Series
This addresses the scarcity of unsupervised methods for anomaly detection in multivariate time series, which is important for applications like monitoring and fault detection, though it is incremental as it builds on existing techniques like DTW and fuzzy clustering.
The paper tackles the problem of unsupervised anomaly detection in multivariate time series by proposing FCM-wDTW, a method that learns a distance metric using fuzzy C-means clustering with weighted dynamic time warping, achieving competitive accuracy and efficiency on 11 benchmarks.
Distance-based time series anomaly detection methods are prevalent due to their relative non-parametric nature and interpretability. However, the commonly used Euclidean distance is sensitive to noise. While existing works have explored dynamic time warping (DTW) for its robustness, they only support supervised tasks over multivariate time series (MTS), leaving a scarcity of unsupervised methods. In this work, we propose FCM-wDTW, an unsupervised distance metric learning method for anomaly detection over MTS, which encodes raw data into latent space and reveals normal dimension relationships through cluster centers. FCM-wDTW introduces locally weighted DTW into fuzzy C-means clustering and learns the optimal latent space efficiently, enabling anomaly identification via data reconstruction. Experiments with 11 different types of benchmarks demonstrate our method's competitive accuracy and efficiency.