1. Proceedings
  2. I3M
  3. 2020
  4. EMSS
  5. 10.46354/i3m.2020.emss.044

Towards a stream based machine learning testbed

  • a Jan Zenisek ,
  • b Josef Wolfartsberger ,
  • c Norbert Wild ,
  • d Michael Affenzeller 
  • a,b,c,d Center of Excellence for Smart Production, University of Applied Sciences Upper Austria, Softwarepark 11, 
    Hagenberg, 4232, Austria
  • a,d Institute for Formal Models and Verification, Johannes Kepler University, Altenberger Straße 69, Linz, 4040, 
    Austria
Cite as
Zenisek J., Wolfartsberger J., Wild N., Affenzeller M. (2020). Towards a stream based machine learning testbed. Proceedings of the 32nd European Modeling & Simulation Symposium (EMSS 2020), pp. 305-310. DOI: https://doi.org/10.46354/i3m.2020.emss.044

Abstract

With the rise of data analytics in industrial applications a heterogeneous tool landscape developed over the past few years. To cope with highly dynamic and domain-specific requirements of such applications, scripting programming languages and frameworks, which offer ecosystems comprising numerous publicly available plugin libraries, are gaining more and more attraction as a starting point, since they enable rapid prototyping and thus, quick results. At the other end, cloud service providers are continuously extending their data analysis product palette in order to support large enterprise solutions for real-world deployments. As scripted prototypes and cloud based solutions have their strengths in different phases of an analytics project, we identified several pitfalls in recent case studies when moving a prototypic approach to release. In this work, we present a software design for a data stream analysis testbed, with the aim to address some of these challenges. Therefore, an interaction pattern for common analysis steps (data acquisition, visualization, preprocessing and machine learning model evaluation) is detailed, results gained from a sample case study are summarized and future leads are discussed.

References

  1. Baptista, M., Sankararaman, S., de Medeiros, I. P., Nascimento Jr, C., Prendinger, H., and  Henriques, E. M. (2018). Forecasting fault events for predictive maintenance using data-driven techniques and pharma modeling. Computers & Industrial Engineering, 115:41–53.
  2. Bifet, A., Holmes, G., Pfahringer, B., Kranen, P., Kremer, H., Jansen, T., and Seidl, T. (2010). Moa: Massive online analysis, a framework for stream classification and clustering. In Proceedings of the First Workshop on Applications of Pattern Analysis, pages 44–50.
  3. Kanawaday, A. and Sane, A. (2017). Machine learning for predictive maintenance of industrial machines using iot sensor data. In 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), pages 87–90. IEEE.
  4. Katsikeas, S., Fysarakis, K., Miaoudakis, A., Van Bemten, A., Askoxylakis, I., Papaefstathiou, I., and
    Plemenos, A. (2017). Lightweight & secure industrial iot communications via the mq telemetry transport protocol. In 2017 IEEE Symposium on Computers and Communications (ISCC), pages 1193–1200. IEEE.
  5. Li, Z., Wang, Y., and Wang, K.-S. (2017). Intelligent predictive maintenance for fault diagnosis and prognosis in machine centers: Industry 4.0 scenario. Advances in Manufacturing, 5(4):377–387.
  6. Orriols, A. and Bernadó-Mansilla, E. (2005). The class imbalance problem in learning classifier systems: a preliminary study. In Proceedings of the 7th annual workshop on Genetic and evolutionary computation, pages 74–78.
  7. Schmidt, B. and Wang, L. (2018). Cloud-enhanced predictive maintenance. The International Journal of Advanced Manufacturing Technology, 99(1-4):5–13.
  8. Wagner, S., Kronberger, G., Beham, A., Kommenda, M., Scheibenpflug, A., Pitzer, E., Vonolfen, S., Kofler, M., Winkler, S., Dorfer, V., et al. (2014). Architecture and design of the heuristiclab optimization environment. In Advanced methods and applications in computational intelligence, pages 197–261. Springer.
  9. Zenisek, J., Kronberger, G., Wolfartsberger, J., Wild, N., and Affenzeller, M. (2019). Concept drift detection with variable interaction networks. In International Conference on Computer Aided Systems Theory, pages 296–303. Springer.
  10. Zenisek, J., Wolfartsberger, J., Sievi, C., and Affenzeller, M. (2018). Streaming synthetic time series for simulated condition monitoring. IFAC-PapersOnLine, 51(11):643–648.