Skip to main content
Springer Nature Link
Log in

Impact of Recurrent Neural Networks and Deep Learning Frameworks on Real-Time Lightweight Time Series Anomaly Detection

  • Conference paper
  • First Online:
Information and Communications Security (ICICS 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15056))

Included in the following conference series:

  • 502 Accesses

  • 5 Citations

Abstract

Real-time lightweight time series anomaly detection has become increasingly crucial in cybersecurity and many other domains. Its ability to adapt to unforeseen pattern changes and swiftly identify anomalies enables prompt responses and critical decision-making. While several such anomaly detection approaches have been introduced in recent years, they primarily utilize a single type of recurrent neural networks (RNNs) and have been implemented in only one deep learning framework. It is unclear how the use of different types of RNNs available in various deep learning frameworks affects the performance of these anomaly detection approaches due to the absence of comprehensive evaluations. Arbitrarily choosing a RNN variant and a deep learning framework to implement an anomaly detection approach may not reflect its true performance and could potentially mislead users into favoring one approach over another. In this paper, we aim to study the influence of various types of RNNs available in popular deep learning frameworks on real-time lightweight time series anomaly detection. We reviewed several state-of-the-art approaches and implemented a representative anomaly detection approach using well-known RNN variants supported by three widely recognized deep learning frameworks. A comprehensive evaluation is then conducted to analyze the performance of each implementation across real-world, open-source time series datasets. The evaluation results provide valuable guidance for selecting the appropriate RNN variant and deep learning framework for real-time, lightweight time series anomaly detection.

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+
from €37.37 /Month
  • Starting from 10 chapters or articles per month
  • Access and download chapters and articles from more than 300k books and 2,500 journals
  • Cancel anytime
View plans

Buy Now

Chapter
EUR 29.95
Price includes VAT (Norway)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
EUR 53.49
Price includes VAT (Norway)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
EUR 65.99
Price excludes VAT (Norway)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, books and news in related subjects, suggested using machine learning.

References

  1. Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: OSDI, Savannah, GA, USA, vol. 16, pp. 265–283 (2016)

    Google Scholar 

  2. Ahmed, M., Mahmood, A.N., Hu, J.: A survey of network anomaly detection techniques. J. Netw. Comput. Appl. 60, 19–31 (2016)

    Article  Google Scholar 

  3. Al-Ghuwairi, A.R., Sharrab, Y., Al-Fraihat, D., AlElaimat, M., Alsarhan, A., Algarni, A.: Intrusion detection in cloud computing based on time series anomalies utilizing machine learning. J. Cloud Comput. 12(1), 127 (2023)

    Article  Google Scholar 

  4. Alimohammadi, H., Chen, S.N.: Performance evaluation of outlier detection techniques in production timeseries: a systematic review and meta-analysis. Exp. Syst. Appl. 191, 116371 (2022)

    Article  Google Scholar 

  5. Anton, S.D., Ahrens, L., Fraunholz, D., Schotten, H.D.: Time is of the essence: machine learning-based intrusion detection in industrial time series data. In: 2018 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 1–6. IEEE (2018)

    Google Scholar 

  6. Blázquez-García, A., Conde, A., Mori, U., Lozano, J.A.: A review on outlier/anomaly detection in time series data. ACM Comput. Surv. (CSUR) 54(3), 1–33 (2021)

    Article  Google Scholar 

  7. Braei, M., Wagner, S.: Anomaly detection in univariate time-series: a survey on the state-of-the-art. arXiv preprint arXiv:2004.00433 (2020)

  8. Cho, K., Van Merriënboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)

  9. Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)

  10. Deeplearning4j: Introduction to core Deeplearning4j concepts (2023). https://deeplearning4j.konduit.ai/. Accessed 23 Jul 2024

  11. Deka, P.K., Verma, Y., Bhutto, A.B., Elmroth, E., Bhuyan, M.: Semi-supervised range-based anomaly detection for cloud systems. IEEE Trans. Netw. Serv. Manage. (2022)

    Google Scholar 

  12. EarlyStopping: What is early stopping? (2023). https://deeplearning4j.konduit.ai/. Accessed 31 Jul 2024

  13. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735

    Article  Google Scholar 

  14. Hochreiter, S.: The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int. J. Uncertain. Fuzziness Knowl. Based Syst. 6(02), 107–116 (1998)

    Article  Google Scholar 

  15. Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79(8), 2554–2558 (1982)

    Article  MathSciNet  Google Scholar 

  16. Keras: Keras - a deep learning API written in Python (2023). https://keras.io/about/. Accessed 31 Jul 2024

  17. Ketkar, N., Santana, E.: Deep learning with Python, vol. 1. Springer, Heidelberg (2017)

    Google Scholar 

  18. Kieu, T., Yang, B., Jensen, C.S.: Outlier detection for multidimensional time series using deep neural networks. In: 2018 19th IEEE International Conference on Mobile Data Management (MDM), pp. 125–134. IEEE (2018)

    Google Scholar 

  19. Kovalev, V., Kalinovsky, A., Kovalev, S.: Deep learning with theano, torch, caffe, tensorflow, and deeplearning4J: which one is the best in speed and accuracy? (2016)

    Google Scholar 

  20. Lee, M.C., Lin, J.C.: Impact of deep learning libraries on online adaptive lightweight time series anomaly detection. In: Proceedings of the 18th International Conference on Software Technologies - ICSOFT, pp. 106–116. INSTICC, SciTePress (2023). https://doi.org/10.5220/0012082900003538

  21. Lee, M.C., Lin, J.C.: RePAD2: real-time, lightweight, and adaptive anomaly detection for open-ended time series. In: Proceedings of the 8th International Conference on Internet of Things, Big Data and Security - IoTBDS, pp. 208–217. INSTICC, SciTePress. arXiv preprint arXiv:2303.00409 (2023)

  22. Lee, M.C., Lin, J.C.: RoLA: a real-time online lightweight anomaly detection system for multivariate time series. In: Proceedings of the 18th International Conference on Software Technologies - ICSOFT, pp. 313–322. INSTICC, SciTePress (2023). https://doi.org/10.5220/0012077200003538

  23. Lee, M.C., Lin, J.C., Gan, E.G.: ReRe: a lightweight real-time ready-to-go anomaly detection approach for time series. In: 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), pp. 322–327. IEEE. arXiv preprint arXiv:2004.02319 (2020)

  24. Lee, M.-C., Lin, J.-C., Gran, E.G.: RePAD: real-time proactive anomaly detection for time series. In: Barolli, L., Amato, F., Moscato, F., Enokido, T., Takizawa, M. (eds.) AINA 2020. AISC, vol. 1151, pp. 1291–1302. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-44041-1_110

    Chapter  Google Scholar 

  25. Lee, M.-C., Lin, J.-C., Gran, E.G.: How far should we look back to achieve effective real-time time-series anomaly detection? In: Barolli, L., Woungang, I., Enokido, T. (eds.) AINA 2021. LNNS, vol. 225, pp. 136–148. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-75100-5_13

    Chapter  Google Scholar 

  26. Lee, M.C., Lin, J.C., Gran, E.G.: SALAD: self-adaptive lightweight anomaly detection for real-time recurrent time series. In: 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), pp. 344–349. IEEE. arXiv preprint arXiv:2104.09968 (2021)

  27. LinkedIn: LinkedIn/Luminol [online code repository] (2018). https://github.com/linkedin/luminol. Accessed 31 Jul 2024

  28. Moso, J.C., Cormier, S., de Runz, C., Fouchal, H., Wandeto, J.M.: Anomaly detection on data streams for smart agriculture. Agriculture 11(11), 1083 (2021)

    Article  Google Scholar 

  29. Nguyen, G., et al.: Machine learning and deep learning frameworks and libraries for large-scale data mining: a survey. Artif. Intell. Rev. 52, 77–124 (2019)

    Article  Google Scholar 

  30. Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)

    Google Scholar 

  31. Pereira, J., Silveira, M.: Learning representations from healthcare time series data for unsupervised anomaly detection. In: 2019 IEEE International Conference on Big Data and Smart Computing (BigComp), pp. 1–7. IEEE (2019)

    Google Scholar 

  32. Ren, H., et al.: Time-series anomaly detection service at Microsoft. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3009–3017 (2019)

    Google Scholar 

  33. Schneider, J., Wenig, P., Papenbrock, T.: Distributed detection of sequential anomalies in univariate time series. VLDB J. 30(4), 579–602 (2021). https://doi.org/10.1007/s00778-021-00657-6

    Article  Google Scholar 

  34. Twitter: AnomalyDetection R package [online code repository] (2015). https://github.com/twitter/AnomalyDetection. Accessed 31 Jul 2024

  35. Vito, S.: Air Quality. UCI Machine Learning Repository (2016). https://doi.org/10.24432/C59K5F

  36. Wang, Z., Liu, K., Li, J., Zhu, Y., Zhang, Y.: Various frameworks and libraries of machine learning and deep learning: a survey. Arch. Computat. Meth. Eng. 31, 1–24 (2019)

    Article  Google Scholar 

  37. Yatish, H., Swamy, S.: Recent trends in time series forecasting - a survey. Int. Res. J. Eng. Technol. (IRJET) 7(04), 5623–5628 (2020)

    Google Scholar 

  38. Zahidi, Y., El Younoussi, Y., Al-Amrani, Y.: A powerful comparison of deep learning frameworks for Arabic sentiment analysis. Int. J. Electr. Comput. Eng. (2088-8708) 11(1) (2021)

    Google Scholar 

  39. Zhang, J.E., Wu, D., Boulet, B.: Time series anomaly detection for smart grids: a survey. In: 2021 IEEE Electrical Power and Energy Conference (EPEC), pp. 125–130. IEEE (2021)

    Google Scholar 

  40. Zhang, Q., et al.: A comprehensive benchmark of deep learning libraries on mobile devices. In: Proceedings of the ACM Web Conference 2022, pp. 3298–3307 (2022)

    Google Scholar 

  41. Zhang, X., Wang, Y., Shi, W.: pCAMP: performance comparison of machine learning packages on the edges. In: HotEdge (2018)

    Google Scholar 

Download references

Acknowledgement

The authors want to thank the anonymous reviewers for their reviews and valuable suggestions to this paper. This work has received funding from the Research Council of Norway through the SFI Norwegian Centre for Cybersecurity in Critical Sectors (NORCICS) project no. 310105.

Author information

Authors and Affiliations

  1. Department of Information Security and Communication Technology, Norwegian University of Science and Technology (NTNU), Gjøvik, Norway

    Ming-Chang Lee, Jia-Chun Lin & Sokratis Katsikas

Authors
  1. Ming-Chang Lee
    View author publications

    Search author on:PubMed Google Scholar

  2. Jia-Chun Lin
    View author publications

    Search author on:PubMed Google Scholar

  3. Sokratis Katsikas
    View author publications

    Search author on:PubMed Google Scholar

Corresponding author

Correspondence to Ming-Chang Lee .

Editor information

Editors and Affiliations

  1. Norwegian University of Science and Technology - NTNU, Gjøvik, Norway

    Sokratis Katsikas

  2. University of Piraeus, Piraeus, Greece

    Christos Xenakis

  3. University of the Aegean, Mytilene, Greece

    Christos Kalloniatis

  4. University of Piraeus, Piraeus, Greece

    Costas Lambrinoudakis

Rights and permissions

Reprints and permissions

Copyright information

© 2025 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

Lee, MC., Lin, JC., Katsikas, S. (2025). Impact of Recurrent Neural Networks and Deep Learning Frameworks on Real-Time Lightweight Time Series Anomaly Detection. In: Katsikas, S., Xenakis, C., Kalloniatis, C., Lambrinoudakis, C. (eds) Information and Communications Security. ICICS 2024. Lecture Notes in Computer Science, vol 15056. Springer, Singapore. https://doi.org/10.1007/978-981-97-8798-2_12

Download citation

Keywords

Publish with us

Policies and ethics

Profiles

  1. Ming-Chang Lee View author profile
  2. Jia-Chun Lin View author profile