mlsanityData to 14 Oct 2026

Online Model-based Anomaly Detection in Multivariate Time Series: Taxonomy, Survey, Research Challenges and Future Directions

arXiv 2408.03747 ↗First posted 7 Aug 2024cs.LG cs.AI cs.SYcited by 6

Not on the map. Why?

Abstract (arXiv)

Time-series anomaly detection plays an important role in engineering processes, like development, manufacturing and other operations involving dynamic systems. These processes can greatly benefit from advances in the field, as state-of-the-art approaches may aid in cases involving, for example, highly dimensional data. To provide the reader with understanding of the terminology, this survey introduces a novel taxonomy where a distinction between online and offline, and training and inference is made. Additionally, it presents the most popular data sets and evaluation metrics used in the literature, as well as a detailed analysis. Furthermore, this survey provides an extensive overview of the state-of-the-art model-based online semi- and unsupervised anomaly detection approaches for multivariate time-series data, categorising them into different model families and other properties. The biggest research challenge revolves around benchmarking, as currently there is no reliable way to compare different approaches against one another. This problem is two-fold: on the one hand, public data sets suffers from at least one fundamental flaw, while on the other hand, there is a lack of intuitive and representative evaluation metrics in the field. Moreover, the way most publications choose a detection threshold disregards real-world conditions, which hinders the application in the real world. To allow for tangible advances in the field, these issues must be addressed in future work.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 37 of its 105 references that are in the map. First posted on arXiv 7 Aug 2024.

Builds on

37 of 105 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  7. 2015Variational Inference with Normalizing Flowscited by 2,170
  8. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  9. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  10. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  11. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  12. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
25 more
  1. 2019Deep Learning for Anomaly Detection: A Surveycited by 358
  2. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 224
  3. 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 215
  4. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 214
  5. 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
  6. 2020A review on outlier/anomaly detection in time series datacited by 189
  7. 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 182
  8. 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
  9. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 151
  10. 2021Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoTcited by 104
  11. 2022Local Evaluation of Time Series Anomaly Detection Algorithmscited by 79
  12. 2018Precision and Recall for Time Seriescited by 67
  13. 2020TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networkscited by 55
  14. 2021Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encodercited by 39
  15. 2016Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Modelcited by 34
  16. 2021A Survey on Anomaly Detection for Technical Systems using LSTM Networkscited by 27
  17. 2022Do Deep Neural Networks Contribute to Multivariate Time Series Anomaly Detection?cited by 19
  18. 2022TiSAT: Time Series Anomaly Transformercited by 15
  19. 2021Federated Variational Learning for Anomaly Detection in Multivariate Time Seriescited by 12
  20. 2022An Attention-based ConvLSTM Autoencoder with Dynamic Thresholding for Unsupervised Anomaly Detection in Multivariate Time Seriescited by 9
  21. 2017RNN-based Early Cyber-Attack Detection for the Tennessee Eastman Processcited by 6
  22. 2023DTAAD: Dual Tcn-Attention Networks for Anomaly Detection in Multivariate Time Series Datacited by 3
  23. 2023Coupled Attention Networks for Multivariate Time Series Anomaly Detectioncited by 3
  24. 2020Reconstruct Anomaly to Normal: Adversarial Learned and Latent Vector-constrained Autoencoder for Time-series Anomaly Detectioncited by 2
  25. 2022Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencodercited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 2.

6 papers.

  1. 2025mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scalecited by 7
  2. 2025ANSR-DT: A Neuro-Symbolic Framework for Adaptive and Explainable Digital Twinscited by 2
  3. 2024PATH: A Discrete-sequence Dataset for Evaluating Online Unsupervised Anomaly Detection Approaches for Multivariate Time Seriescited by 1
  4. 2025DQS: A Low-Budget Query Strategy for Enhancing Unsupervised Data-driven Anomaly Detection Approachescited by 0
  5. 2026Multivariate time-series forecasting of ASTRI-Horn monitoring data: A Normal Behavior Modelcited by 0
  6. 2026Deep Learning for Anomaly Detection in Railway Systems: A Structured Surveycited by 0