Robust Time Series Dissimilarity Measure for Outlier Detection and Periodicity Detection
This work addresses a bottleneck in time series analysis for applications requiring robustness and speed, though it is incremental as it builds on DTW variants.
The paper tackles the sensitivity of Dynamic Time Warping (DTW) to noise and outliers and its high computational cost by proposing RobustDTW, a novel dissimilarity measure that reduces these effects and improves efficiency, demonstrating superior performance in outlier and periodicity detection on real-world datasets.
Dynamic time warping (DTW) is an effective dissimilarity measure in many time series applications. Despite its popularity, it is prone to noises and outliers, which leads to singularity problem and bias in the measurement. The time complexity of DTW is quadratic to the length of time series, making it inapplicable in real-time applications. In this paper, we propose a novel time series dissimilarity measure named RobustDTW to reduce the effects of noises and outliers. Specifically, the RobustDTW estimates the trend and optimizes the time warp in an alternating manner by utilizing our designed temporal graph trend filtering. To improve efficiency, we propose a multi-level framework that estimates the trend and the warp function at a lower resolution, and then repeatedly refines them at a higher resolution. Based on the proposed RobustDTW, we further extend it to periodicity detection and outlier time series detection. Experiments on real-world datasets demonstrate the superior performance of RobustDTW compared to DTW variants in both outlier time series detection and periodicity detection.