Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines

By Kukjin Choi, Jihun Yi, Changhwa Park, Sungroh Yoon. IEEE Access, 2021

521 citations recorded by the source corpus.

As industries become automated and connectivity technologies advance, a wide range of systems continues to generate massive amounts of data. Many approaches have been proposed to extract principal indicators from the vast sea of data to represent the entire system state. Detecting anomalies using these indicators on time prevent potential accidents and economic losses. Anomaly detection in multivariate time series data poses a particular challenge because it requires simultaneous consideration of temporal dependencies and relationships between variables. Recent deep learning-based works have made impressive progress in this field. They are highly capable of learning representations of the large-scaled sequences in an unsupervised manner and identifying anomalies from the data. However, most of them are highly specific to the individual use case and thus require domain knowledge for appropriate deployment. This review provides a background on anomaly detection in time-series data and reviews the latest applications in the real world. Also, we comparatively analyze state-of-the-art deep-anomaly-detection models for time series with several benchmark datasets. Finally, we offer guidelines for appropriate model selection and training strategy for deep learning-based time series anomaly detection.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/712e279ecea207968717d8401000e7ca0b7bb74d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Junchi Yan
2. Ziqing Ma
3. Chao Zhang
4. Weiqiu Chen
5. Liang Sun
6. Qingsong Wen
7. Tian Zhou

In Computer Networks and Communications

1. Liang Sun
2. Qingsong Wen
3. Tian Zhou

In Signal Processing

1. Junchi Yan
2. Ziqing Ma
3. Liang Sun
4. Qingsong Wen
5. Tian Zhou
6. Qiang Xu
7. Ailing Zeng

Citations in the corpus

• Deep Learning for Time Series Anomaly Detection: A Survey (2022, unknown): “Although the field of anomaly detection has been explored in several literature surveys [26], [137], [24], [17], [20] and some evaluation review papers exist [152], [99], there is only one survey on deep anomaly detection methods for time series data [38].”
• Transformers in Time Series: A Survey (2022, background): “…[ Lim and Zohren, 2021; Benidis et al. , 2022; Torres et al. , 2021 ] , classification [ Is-mail Fawaz et al. , 2019 ] , anomaly detection [ Choi et al. , 2021; Bl ´ azquez-Garc ´ ıa et al. , 2021 ] , and data augmentation [ Wen et al. , 2021b ] , but there is no comprehensive survey for…”