Robust Projection based Anomaly Extraction (RPE) in Univariate Time-Series
This addresses the need for efficient anomaly detection in time-series applications where large training data is unavailable, though it is an incremental improvement over existing window-based methods.
The paper tackles the problem of online anomaly detection in univariate time-series by proposing RPE, a robust, closed-form algorithm that efficiently handles multiple large anomalies within a window and identifies them at the timestamp level, outperforming existing methods by a notable margin in experiments.
This paper presents a novel, closed-form, and data/computation efficient online anomaly detection algorithm for time-series data. The proposed method, dubbed RPE, is a window-based method and in sharp contrast to the existing window-based methods, it is robust to the presence of anomalies in its window and it can distinguish the anomalies in time-stamp level. RPE leverages the linear structure of the trajectory matrix of the time-series and employs a robust projection step which makes the algorithm able to handle the presence of multiple arbitrarily large anomalies in its window. A closed-form/non-iterative algorithm for the robust projection step is provided and it is proved that it can identify the corrupted time-stamps. RPE is a great candidate for the applications where a large training data is not available which is the common scenario in the area of time-series. An extensive set of numerical experiments show that RPE can outperform the existing approaches with a notable margin.