Temporal convolutional autoencoder for unsupervised anomaly detection in time series

Learning temporal patterns in time series remains a challenging task up until today. Particularly for anomaly detection in time series, it is essential to learn the underlying structure of a system's normal behavior. Periodic or quasiperiodic signals with complex temporal patterns make the problem even more challenging: Anomalies may be a hard-to-detect deviation from the normal recurring pattern. In this paper, we present TCN-AE, a temporal convolutional network autoencoder based on dilated convolutions. Contrary to many other anomaly detection algorithms, TCN-AE is trained in an unsupervised manner. The algorithm demonstrates its efficacy on a comprehensive real-world anomaly benchmark comprising electrocardiogram (ECG) recordings of patients with cardiac arrhythmia. TCNAE significantly outperforms several other unsupervised state-of-the-art anomaly detection algorithms. Moreover, we investigate the contribution of the individual enhancements and show that each new ingredient improves the overall performance on the investigated benchmark. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

Learning temporal patterns in time series, especially for anomaly detection, remains challenging. The TCN-AE, an unsupervised temporal convolutional network autoencoder based on dilated convolutions, significantly outperforms other state-of-the-art anomaly detection algorithms on a real-world benchmark. Each new enhancement contributes to improving the overall performance of the algorithm.