Expert enhanced dynamic time warping based anomaly detection

Dynamic time warping (DTW) is a well-known algorithm for time series elastic dissimilarity measure. Its ability to deal with non-linear time distortions makes it helpful in a variety of data mining tasks. Such a task is also anomaly detection which aims to reveal unexpected behaviour in the given dataset. Anomaly detection becomes particularly challenging when there is only a small set of data for training. In this paper, we propose a novel anomaly detection method named Expert enhanced dynamic time warping anomaly detection (E-DTWA). It is based on DTW with additional enhancements involving the human-in-the-loop concept. The main benefits of our approach comprise efficient detection, flexible retraining based on strong consideration of the expert's detection feedback, and a step towards explainability while retaining low computational and space complexity.