A Review of Anomaly Detection Methods for Multivariate Time Series Based on Time-Domain and Frequency-Domain Perspectives

DOI: https://doi.org/10.62517/jbdc.202601123

Author(s)

Jiaming Xu, Hanqi Liu, Jun Xu

Affiliation(s)

College of Science, North China University of Science and Technology, Tangshan, China

Abstract

With the increasing proliferation of sensor fusion, industrial control systems (ICS), and internet services, multivariate time-series data has become ubiquitous in fields such as intelligent manufacturing, financial monitoring, network security, and transportation. Multivariate Time-Series Anomaly Detection (MTSAD) aims to identify patterns that deviate significantly from normal behavior within high-dimensional dynamic metrics, thereby providing critical support for system monitoring and early warning. Compared with static data and univariate sequences, multivariate time series are characterized by temporal dependencies, complex inter-variable interactions, and dynamic distribution shifts, posing strictly higher requirements for anomaly detection. This paper first introduces the definitions of time-series anomaly detection and categorizes common anomaly types. Secondly, it classifies existing methods from both time-domain and frequency-domain perspectives, providing a comprehensive analysis of their advantages, limitations, and application scenarios. Finally, the paper explores key research directions for the future design of anomaly detection methods, offering a reference for both theoretical and applied research in this domain.

Keywords

Industrial Internet of Things; Multivariate Time Series Data; Time-Domain Methods; Frequency-Domain Methods; Industrial Control Systems

References

[1] GARG A, ZHANG W Y, SAMARAN J, et al. An evaluation of anomaly detection and diagnosis in multivariate time series[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(6): 2508-2517. [2] JIANG J R, KAO J B, LI Y L. Semi-supervised time series anomaly de-tection based on statistics and deep learning [J]. Applied Sciences, 2021, 11(15): 6698. [3] Mathur A P, Tippenhauer N O. SWaT: A water treatment testbed for research and training on ICS security[C]//2016 international workshop on cyber-physical systems for smart water networks (CySWater). IEEE, 2016: 31-36. [4] Ahmed C M, Palleti V R, Mathur A P. WADI: a water distribution testbed for research in the design of secure cyber physical systems[C]//Proceedings of the 3rd international workshop on cyber-physical systems for smart water networks. 2017: 25-28. [5] Su Y, Zhao Y, Niu C, et al. Robust anomaly detection for multivariate time series through stochastic recurrent neural network[C]//Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 2019: 2828-2837. [6] Hundman K, Constantinou V, Laporte C, et al. Detecting spacecraft anomalies using lstms and nonparametric dynamic thresholding[C]//Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 2018: 387-395. [7] Katser I D, Kozitsin V O. Skoltech anomaly benchmark (skab)[J]. Kaggle, 2020. [8]. Vieira R G, Leone Filho M A, Semolini R. An Enhanced Seasonal-Hybrid ESD technique for robust anomaly detection on time series[C]//Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC). SBC, 2018: 281-294. [9] ZHANG Y, MERATNIA N, HAVINGA P. Outlier detection techniques for wireless sensor networks: A survey [J]. IEEE Communications Surveys & Tutorials, 2010, 12(2): 159-170. [10] Münz, G., Li, S., & Carle, G. (2007). Traffic anomaly detection using k-means clustering. GI/ITG Workshop MMBnet, 13–14. [11] CHESNOKOV M Y. Time series anomaly searching based on DB-SCAN ensembles[J]. Scientific and Technical Information Processing, 2019, 46(5): 299-305. [12] Ding Z, Fei M. An anomaly detection approach based on isolation forest algorithm for streaming data using sliding window[J]. IFAC Proceedings Volumes, 2013, 46(20): 12-17. [13] Malhotra P. LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection[J]. arXiv preprint arXiv:1607.00148, 2016. [14] Zhang C, Song D, Chen Y, et al. A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data[C]//Proceedings of the AAAI conference on artificial intelligence. 2019, 33(01): 1409-1416. [15] Zong B, Song Q, Min M R, et al. Deep autoencoding gaussian mixture model for unsupervised anomaly detection[C]//International conference on learning representations. 2018. [16] Audibert J, Michiardi P, Guyard F, et al. Usad: Unsupervised anomaly detection on multivariate time series[C]//Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. 2020: 3395-3404. [17] Li D, Chen D, Jin B, et al. MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks[C]//International conference on artificial neural networks. Cham: Springer International Publishing, 2019: 703-716. [18] Geiger A, Liu D, Alnegheimish S, et al. Tadgan: Time series anomaly detection using generative adversarial networks[C]//2020 ieee international conference on big data (big data). IEEE, 2020: 33-43. [19] Ding N, Ma H X, Gao H, et al. Real-time anomaly detection based on long short-Term memory and Gaussian Mixture Model[J]. Computers & Electrical Engineering, 2019, 79: 106458. [20] Munir M, Siddiqui S A, Dengel A, et al. DeepAnT: A deep learning approach for unsupervised anomaly detection in time series[J]. Ieee Access, 2018, 7: 1991-2005. [21] Wu H, Hu T, Liu Y, et al. Timesnet: Temporal 2d-variation modeling for general time series analysis[J]. arXiv preprint arXiv:2210.02186, 2022. [22] Tuli S, Casale G, Jennings N R. Tranad: Deep transformer networks for anomaly detection in multivariate time series data[J]. arXiv preprint arXiv:2201.07284, 2022. [23] Xu J, Wu H, Wang J, et al. Anomaly transformer: Time series anomaly detection with association discrepancy[J]. arXiv preprint arXiv:2110.02642, 2021. [24] Zhao H, Wang Y, Duan J, et al. Multivariate time-series anomaly detection via graph attention network[C]//2020 IEEE international conference on data mining (ICDM). IEEE, 2020: 841-850. [25] Hu J, Li T, Zhao M, et al. Hyperspectral image superresolution via deep structure and texture interfusion[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 8665-8678. [26] REN H, XU B, WANG Y, et al. Time-series anomaly detection service at Microsoft[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, NY, USA: ACM, 2019: 3009-3017. [27] AMADA A, SHIRAISHI T, NISHINO S, et al. Change point detection in the frequency domain with statistical reliability[J]. Transactions on Machine Learning Research, 2025. [28] CHEN Y, WANG H, HONG M, et al. Dual-TF: A dual-domain time-frequency framework for time-series anomaly detection[J]. IEEE Transactions on Big Data, 2024, 10(2): 184-196. [29] ZHANG Y, LI X, WANG J. TFCLNet: Time-frequency contrastive learning network for time series anomaly detection[J]. IEEE Transactions on Instrumentation and Measurement, 2025, 74: 1-12. [30] Zhang C, Zhou T, Wen Q, et al. Tfad: A decomposition time series anomaly detection architecture with time-frequency analysis[C]//Proceedings of the 31st ACM international conference on information & knowledge management. 2022: 2497-2507. [31] Fang Y, Xie J, Zhao Y, et al. Temporal-frequency masked autoencoders for time series anomaly detection[C]//2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 2024: 1228-1241. [32] Lu Y X, Jin X B, Chen J, et al. F-SE-LSTM: A Time Series Anomaly Detection Method with Frequency Domain Information[J]. arXiv preprint arXiv:2412.02474, 2024. [33] Li S, Wang Z, Wang X, et al. Frequency-enhanced and decomposed transformer for multivariate time series anomaly detection[J]. Applied Intelligence, 2025, 55(6): 1-18. [34] Wu X, Qiu X, Li Z, et al. Catch: Channel-aware multivariate time series anomaly detection via frequency patching[J]. arXiv preprint arXiv:2410.12261, 2024. [35] Chen F, Zhang Y, Qin Z, et al. Learning multi-pattern normalities in the frequency domain for efficient time series anomaly detection[C]//2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 2024: 747-760.