Skip to main content
Springer Nature Link
Log in

Anomaly Detection for Multivariate Time Series with Multi-scale Feature Interactions

  • Conference paper
  • First Online:
Database Systems for Advanced Applications (DASFAA 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14854))

Included in the following conference series:

  • 346 Accesses

Abstract

Efficient anomaly detection in multivariate time series (MTS) data holds paramount importance in the realm of monitoring intricate systems. However, numerous recent methods tend to disregard the vital intra-variable and inter-variable dependencies across distinct temporal and variable scales, leading to inadequate anomaly detection outcomes. To tackle these challenges, we propose a Multi-scale Feature Interactions (MSFI), a novel unsupervised model for anomaly detection in MTS. The MSFI model leverages multi-scale feature interaction blocks, which exploit the variance of each timestamp vector within various scale windows to capture the interdependency among neighboring timestamps. This model also facilitates a comprehensive exploration of variable correlations. Moreover, we propose a normalization-based method for computing attention coefficients to enhance inter-variable correlations and evidence its superiority over the softmax-based method under certain conditions. The resulting dependency features are merged, and a transformer is employed for time series data reconstruction. Furthermore, we introduce three types of noise and incorporate a dynamic noise regulation mechanism during model training to enhance robustness. Extensive experimental evaluations validate the superior performance of our model compared to state-of-the-art approaches.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Ajami, A., Daneshvar, M.: Data driven approach for fault detection and diagnosis of turbine in thermal power plant using independent component analysis (ica). Int. J. Electr. Power Energy Syst. 43(1), 728–735 (2012)

    Article  Google Scholar 

  2. Amiri-Simkooei, A.: Noise in multivariate gps position time-series. J. Geodesy 83, 175–187 (2009)

    Article  Google Scholar 

  3. Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: Proceedings of the International Conference on Learning Representations (2019)

    Google Scholar 

  4. Chen, X., Deng, L., Huang, F., Zhang, C., Zhang, Z., Zhao, Y., Zheng, K.: DAEMON: unsupervised anomaly detection and interpretation for multivariate time series. In: Proceedings of the IEEE International Conference on Data Engineering. pp. 2225–2230 (2021)

    Google Scholar 

  5. Deng, L., Chen, X., Zhao, Y., Zheng, K.: HIFI: Anomaly detection for multivariate time series with high-order feature interactions. In: Proceedings of International Conference on Database Systems for Advanced Applications. pp. 641–649 (2021)

    Google Scholar 

  6. Ding, X., Liu, Y., Wang, H., Yang, D., Song, Y.: SNN-AAD: active anomaly detection method for multivariate time series with sparse neural network. In: Proceedings of International Conference on Database Systems for Advanced Applications. pp. 253–269 (2023)

    Google Scholar 

  7. Ergen, T., Kozat, S.S.: Unsupervised anomaly detection with LSTM neural networks. IEEE Transactions on Neural Networks and Learning Systems 31(8), 3127–3141 (2020)

    Article  MathSciNet  Google Scholar 

  8. Guo, T., Xu, Z., Yao, X., Chen, H., Aberer, K., Funaya, K.: Robust online time series prediction with recurrent neural networks. In: Proceedings of the IEEE International Conference on Data Science and Advanced Analytics. pp. 816–825 (2016)

    Google Scholar 

  9. Hundman, K., Constantinou, V., Laporte, C., Colwell, I., Söderström, T.: Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 387–395 (2018)

    Google Scholar 

  10. Jin, M., Koh, H.Y., Wen, Q., Zambon, D., Alippi, C., Webb, G.I., King, I., Pan, S.: A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection. CoRR abs/2307.03759 (2023)

    Google Scholar 

  11. Jin, X., Sun, Y., Que, Z., Wang, Y., Chow, T.W.S.: Anomaly detection and fault prognosis for bearings. IEEE Trans. Instrum. Meas. 65(9), 2046–2054 (2016)

    Article  Google Scholar 

  12. Leahy, K., Hu, R.L., Konstantakopoulos, I.C., Spanos, C.J., Agogino, A.M.: Diagnosing wind turbine faults using machine learning techniques applied to operational data. In: Proceedings of IEEE International Conference on Prognostics and Health Management. pp. 1–8 (2016)

    Google Scholar 

  13. Li, D., Chen, D., Jin, B., Shi, L., Goh, J., Ng, S.: MAD-GAN: multivariate anomaly detection for time series data with generative adversarial networks. In: Proceedings of International Conference on Artificial Neural Networks. pp. 703–716 (2019)

    Google Scholar 

  14. Lin, Z., Khetan, A., Fanti, G., Oh, S.: PacGAN: the power of two samples in generative adversarial networks. IEEE Journal on Selected Areas in Information Theory 1(1), 324–335 (2020)

    Article  Google Scholar 

  15. Liu, F., Zhou, X., Cao, J., Wang, Z., Wang, T., Wang, H., Zhang, Y.: Anomaly detection in quasi-periodic time series based on automatic data segmentation and attentional LSTM-CNN. IEEE Trans. Knowl. Data Eng. 34(6), 2626–2640 (2022)

    Article  Google Scholar 

  16. Liu, P., Han, Q., Wu, T., Tao, W.: Anomaly detection in industrial multivariate time-series data with neutrosophic theory. IEEE Internet Things J. 10(15), 13458–13473 (2023)

    Article  Google Scholar 

  17. Pang, G., Shen, C., Cao, L., van den Hengel, A.: Deep learning for anomaly detection: A review. ACM Computing Surveys 54(2), 38:1–38:38 (2022)

    Google Scholar 

  18. Park, D., Hoshi, Y., Kemp, C.C.: A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder. IEEE Robotics and Automation Letters 3(2), 1544–1551 (2018)

    Article  Google Scholar 

  19. Qi, S., Chen, J., Chen, P., Wen, P., Niu, X., Xu, L.: An efficient GAN-based predictive framework for multivariate time series anomaly prediction in cloud data centers. Journal of Supercomputing 80(1), 1268–1293 (2023)

    Article  Google Scholar 

  20. Ruff, L., Kauffmann, J.R., Vandermeulen, R.A., Montavon, G., Samek, W., Kloft, M., Dietterich, T.G., Müller, K.: A unifying review of deep and shallow anomaly detection. Proc. IEEE 109(5), 756–795 (2021)

    Article  Google Scholar 

  21. Su, Y., Zhao, Y., Niu, C., Liu, R., Sun, W., Pei, D.: Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 2828–2837 (2019)

    Google Scholar 

  22. Tao, H., Miao, J., Li, Z., Zhang, Z., Feng, S., Wang, S., Cao, J.: HAN-CAD: hierarchical attention network for context anomaly detection in multivariate time series. World Wide Web 26(5), 2785–2800 (2023)

    Article  Google Scholar 

  23. Tuli, S., Casale, G., Jennings, N.R.: TranAD: deep transformer networks for anomaly detection in multivariate time series data. Proceedings of the VLDB Endowment 15(6), 1201–1214 (2022)

    Article  Google Scholar 

  24. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Proceedings of the Annual Conference on Neural Information Processing Systems. pp. 5998–6008 (2017)

    Google Scholar 

  25. Wang, J., Shao, S., Bai, Y., Deng, J., Lin, Y.: Multiscale wavelet graph autoencoder for multivariate time-series anomaly detection. IEEE Trans. Instrum. Meas. 72, 1–11 (2023)

    Google Scholar 

  26. Wu, H.S.: A survey of research on anomaly detection for time series. In: Proceedings of the International Computer Conference on Wavelet Active Media Technology and Information Processing. pp. 426–431 (2016)

    Google Scholar 

  27. Xu, J., Wu, H., Wang, J., Long, M.: Anomaly transformer: Time series anomaly detection with association discrepancy. In: Proceedings of the International Conference on Learning Representations (2022)

    Google Scholar 

  28. Zhang, Z., Li, W., Ding, W., Zhang, L., Lu, Q., Hu, P., Gui, T., Lu, S.: STAD-GAN: unsupervised anomaly detection on multivariate time series with self-training generative adversarial networks. ACM Transactions on Knowledge Discovery from Data 17(5), 71:1–71:18 (2023)

    Google Scholar 

  29. Zhao, H., Wang, Y., Duan, J., Huang, C., Cao, D., Tong, Y., Xu, B., Bai, J., Tong, J., Zhang, Q.: Multivariate time-series anomaly detection via graph attention network. In: Proceedings of the IEEE International Conference on Data Mining. pp. 841–850 (2020)

    Google Scholar 

  30. Zhou, B., Liu, S., Hooi, B., Cheng, X., Ye, J.: BeatGAN: anomalous rhythm detection using adversarially generated time series. In: Proceedings of the International Joint Conference on Artificial Intelligence. pp. 4433–4439 (2019)

    Google Scholar 

Download references

Acknowledgement

This paper is supported by the Major Science and Technology Special Foundation of Yunnan Province (202303AC100004), Joint Key Project of National Natural Science Foundation of China (U23A20298), and National Natural Science Foundation of China (62106217).

Author information

Authors and Affiliations

  1. Yunnan Key Laboratory of Intelligent Systems and Computing, Yunnan University, Kunming, China

    Fulu Kou, Lixing Yu, Kun Yue, Liang Duan & Zhongbin Li

  2. School of Information Science and Engineering, Yunnan University, Kunming, China

    Fulu Kou, Lixing Yu, Kun Yue, Liang Duan & Zhongbin Li

Authors
  1. Fulu Kou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lixing Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kun Yue
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Liang Duan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhongbin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kun Yue .

Editor information

Editors and Affiliations

  1. Osaka University, Suita, Osaka, Japan

    Makoto Onizuka

  2. KAIST, Daejeon, Korea (Republic of)

    Jae-Gil Lee

  3. Beihang University, Beijing, China

    Yongxin Tong

  4. Osaka University, Osaka, Japan

    Chuan Xiao

  5. Nagoya University, Nagoya, Japan

    Yoshiharu Ishikawa

  6. University of Grenoble Alpes, Saint-Martin d’Hères, France

    Sihem Amer-Yahia

  7. University of Michigan, Ann Arbor, MI, USA

    H. V. Jagadish

  8. Nagoya University, Nagoya, Japan

    Kejing Lu

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Kou, F., Yu, L., Yue, K., Duan, L., Li, Z. (2024). Anomaly Detection for Multivariate Time Series with Multi-scale Feature Interactions. In: Onizuka, M., et al. Database Systems for Advanced Applications. DASFAA 2024. Lecture Notes in Computer Science, vol 14854. Springer, Singapore. https://doi.org/10.1007/978-981-97-5569-1_30

Download citation

  • DOI: https://doi.org/10.1007/978-981-97-5569-1_30

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-97-5568-4

  • Online ISBN: 978-981-97-5569-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics