Skip to main content

Adaptive Anomaly Detection and Root Cause Analysis by Fusing Semantics and Machine Learning

Part of the Lecture Notes in Computer Science book series (LNISA,volume 11155)

Abstract

Anomaly detection (AD) systems are either manually built by experts setting thresholds on data or constructed automatically by learning from the available data through machine learning (ML). The first requires profound prior knowledge and are non-adaptive to changing environments but can perform root cause analysis (RCA) to give an understanding of the detected anomaly. The second has a huge need for data, is unable to perform RCA and is often only trained once and deployed in various contexts, leading to a lot of false positives. Fusing the prior knowledge with ML techniques could resolve the generation of these alarms and should define the causes. The primary challenges to create such a detection system are: (1) Augmenting the current ML techniques with prior knowledge to enhance the detection rate. (2) Incorporate knowledge to interpret the cause of a detected anomaly automatically. (3) Reduce of human-involvement by automating the design of detection patterns.

Keywords

  • Anomaly detection
  • Root cause analysis
  • Machine learning
  • Expert knowledge
  • Semantic web
  • Knowledge graphs

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-319-98192-5_46
  • Chapter length: 11 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   69.99
Price excludes VAT (USA)
  • ISBN: 978-3-319-98192-5
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   89.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.

Notes

  1. 1.

    https://www.imec-int.com/en/articles/imec-s-sweet-study-collects-world-s-largest-dataset-on-stress-detection.

  2. 2.

    https://www.televic-rail.com.

  3. 3.

    https://www.renson.eu.

References

  1. Abele, L., et al.: Combining knowledge modeling and machine learning for alarm root cause analysis. IFAC Proc. 46(9), 1843–1848 (2010)

    CrossRef  Google Scholar 

  2. Smith, B.A., et al.: Fault diagnosis using first order logic tools. In: Proceedings of the 32nd Midwest Symposium on Circuits and Systems, vol. 1, pp. 299–302, August 1989

    Google Scholar 

  3. Berners-Lee, T., Hendler, J., Lassila, O.: The semantic web. Sci. Am. 284(5), 34–43 (2001)

    CrossRef  Google Scholar 

  4. Calvier, FÉ., Kammoun, A., Zimmermann, A., Singh, K., Fayolle, J.: Ontology driven complex event pattern definition (Short Paper). In: Debruyne, C., et al. (eds.) On the Move to Meaningful Internet Systems: OTM 2016 Conferences. OTM 2016. Lecture Notes in Computer Science, vol. 10033. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48472-3_31

  5. Camossi, E., et al.: Semantic-based Anomalous Pattern Discovery in Moving Object Trajectories, pp. 1–20. CoRR abs/1305.1 (2013)

    Google Scholar 

  6. Ehsani-Besheli, F., Zarandi, H.R.: Context-aware anomaly detection in embedded systems. In: Zamojski, W., Mazurkiewicz, J., Sugier, J., Walkowiak, T., Kacprzyk, J. (eds.) DepCoS-RELCOMEX 2017. AISC, vol. 582, pp. 151–165. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-59415-6_15

    CrossRef  Google Scholar 

  7. Hammar, K.: Modular semantic CEP for threat detection. In: Operations Research and Data Mining ORADM 2012 workshop proceedings (2012). ISBN: 978–607-414-284-6

    Google Scholar 

  8. Huang, H., et al.: Streaming anomaly detection using randomized matrix sketching. Proc. VLDB Endow. 9(3), 192–203 (2015)

    CrossRef  Google Scholar 

  9. Kdouh, H., et al.: Wireless sensor network on board vessels. In: 2012 19th International Conference on Telecommunications, ICT 2012, pp. 1–6. IEEE, April 2012

    Google Scholar 

  10. Schlichtkrull, M.S., et al.: Modeling relational data with graph convolutional networks. CoRR abs/1703.06103 (2017)

    Google Scholar 

  11. Nguyen, D.Q.: An overview of embedding models of entities and relationships for knowledge base completion. arXiv preprint arXiv 1703.08098 (2017)

    Google Scholar 

  12. Nickel, M., et al.: A review of relational machine learning for knowledge graph. Proc. IEEE 104(28), 1–23 (2015)

    Google Scholar 

  13. Patri, O., et al.: Sensors to events: semantic modeling and recognition of events from data streams. Int. J. Semant. Comput. 10, 461–501 (2016)

    CrossRef  Google Scholar 

  14. Paulheim, H., et al.: Exploiting linked open data as background knowledge in data mining. In: International Workshop on Linked Data, pp. 1–10 (2013)

    Google Scholar 

  15. Ristoski, P., et al.: RDF2Vec: RDF Graph Embeddings and Their Applications. IOS Press (2016)

    Google Scholar 

  16. Sandha, S.S., et al.: Complex Event Processing of Health Data in Real-time to Predict Heart Failure Risk and Stress (2017)

    Google Scholar 

  17. Solé, M., et al.: Survey on models and techniques for root-cause analysis. In: Clinical Orthopaedics and Related Research (CoRR), pp. 1–18 (2017)

    Google Scholar 

  18. Song, Y., et al.: Machine Learning with World Knowledge: The Position and Survey, pp. 1–20. arXiv preprint arXiv 1705.02908 (2017)

    Google Scholar 

  19. Souiden, I., Brahmi, Z., Toumi, H.: A survey on outlier detection in the context of stream mining: review of existing approaches and recommadations. In: Madureira, A.M., Abraham, A., Gamboa, D., Novais, P. (eds.) ISDA 2016. AISC, vol. 557, pp. 372–383. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-53480-0_37

    CrossRef  Google Scholar 

  20. Ahmad, S., et al.: Unsupervised real-time anomaly detection for streaming data. Neurocomputing 262, 134–147 (2017)

    CrossRef  Google Scholar 

  21. Ebisu, T., et al.: Toruse: Knowledge graph embedding on a lie group. CoRR abs/1711.05435 (2017)

    Google Scholar 

  22. Ademujimi, T.T., Brundage, M.P., Prabhu, V.V.: A review of current machine learning techniques used in manufacturing diagnosis. In: Lödding, H., Riedel, R., Thoben, K.-D., von Cieminski, G., Kiritsis, D. (eds.) APMS 2017. IAICT, vol. 513, pp. 407–415. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66923-6_48

    CrossRef  Google Scholar 

  23. Ukil, A., et al.: IoT healthcare analytics: the importance of anomaly detection. In: Conference on Advanced Information Networking and Applications, pp. 994–997 (2016)

    Google Scholar 

  24. Uzun, Y., et al.: Rule extraction from training artificial neural network. Multi. Eng. Sci. Technol. 3(8), 2458–9403 (2016)

    MathSciNet  Google Scholar 

  25. Wang, Q., et al.: Knowledge base completion via coupled path ranking. In: ACL, pp. 1308–1318 (2014)

    Google Scholar 

  26. Xiao, F., et al.: New parallel processing strategies in complex event processing systems with data streams. Distrib. Sens. Netw. 13(8), 1–15 (2017)

    Google Scholar 

  27. Xu, Y., et al.: Semantic-based complex event processing in the AAL domain. In: 9th International Semantic Web Conference (ISWC2010) (2010)

    Google Scholar 

  28. He, Y., et al.: Mechanism-indepedent outlier detection method for online experimentation. In: IEEE International Conference on Data Science, pp. 640–647 (2017)

    Google Scholar 

  29. YE: Big data: Changing the way businesses compete and operate (2014)

    Google Scholar 

  30. Zheng, A.X., et al.: Failure diagnosis using decision trees. In: Proceedings of the First International Conference on Autonomic Computing (2004)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Bram Steenwinckel .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Steenwinckel, B. (2018). Adaptive Anomaly Detection and Root Cause Analysis by Fusing Semantics and Machine Learning. In: , et al. The Semantic Web: ESWC 2018 Satellite Events. ESWC 2018. Lecture Notes in Computer Science(), vol 11155. Springer, Cham. https://doi.org/10.1007/978-3-319-98192-5_46

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-98192-5_46

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-98191-8

  • Online ISBN: 978-3-319-98192-5

  • eBook Packages: Computer ScienceComputer Science (R0)