Time series anomaly detection with reconstruction-based state-space models

Anomaly detection of time series data has wide applications in areas such as finance, health care, and manufacturing. An anomaly is usually an important sign of critical events, such as faulty operation and health deterioration, and thus capturing such signs from a data perspective is of key interest. Time series data in real life often exhibit complex patterns, which pose challenges to the methodology of anomaly detection algorithms. Particularly, high dimensionality increases the difficulty of extracting meaningful features, which is essential to algorithm performance; Highly non-linear dynamics further complicate the identification of system states. Detecting anomalies on a set of measurements over time has always been an active research area [3]. It typically consists of two phases: in the training phase, one models historical data to learn the temporal pattern of time series, and in the testing phase, one evaluates whether each observation follows a normal or abnormal pattern. Since real-world datasets usually lack labeled anomalies, and anomalies can exhibit unpredictable data behavior, the training set may only consist of data from normal operations in these scenarios.