Skip to main content
SpringerLink
Log in

Ensemble Deep Learning for Proactive Terminal Process Management at the Port of Duisburg “duisport”

  • Chapter
  • First Online:
Business Process Management Cases Vol. 2

Abstract

  1. (a)

    Situation faced: The case presented here is located at duisport, the world’s largest inland container port. Duisport is situated at the center of Germany’s largest metropolitan region, with close to 10 million inhabitants. A multitude of roads, tracks, and waterways serve as entry and exit points for containers to and from duisport, and this transport infrastructure is shared with the metropolitan region. Thus, any increase in container volumes due to the overall growth in freight transport cannot be captured by growing in terms of space but requires improvement in the terminal’s productivity.

  2. (b)

    Action taken: We employed advanced data analytics to provide decision support for terminal operators and facilitate proactive management of the terminal’s processes. Using ensembles of deep learning models, we prototypically developed the Terminal Productivity Cockpit (TPC). The TPC predicts delays in the execution of a running process and provides operators with decision support regarding whether to intervene by adapting the process. The case employed more than 30 million data entries from eight data sources, such as cranes and towing vehicles.

  3. (c)

    Results achieved: We estimated that, by using the TPC, terminal operators may increase the rate of successful process outcomes by 4.7%, leading to estimated cost savings of up to 22.5%.

  4. (d)

    Lessons learned: Big data and deep learning offer opportunities for management and innovation of transport processes. We observed that ensemble deep learning contributes to the efficient engineering of data-driven applications because it works well without extensive feature engineering and hyper-parameter tuning. Still, the effectiveness of data analytics solutions depends to a large degree on the quality of data. In this case, understanding, integrating, and cleansing of data consumed around 80% of the overall development time and resources.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 129.99
Price excludes VAT (USA)
  • Durable hardcover 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

Notes

  1. 1.

    https://github.com/Chemsorly/BusinessProcessOutcomePrediction

  2. 2.

    Further performance increases are possible via special-purpose hardware and RNN implementations, reducing RNN training time to 8 min on GPUs and to 2 min on Tensor Processing Units (TPUs).

References

  • Bosnic, Z., & Kononenko, I. (2008). Comparison of approaches for estimating reliability of individual regression predictions. Data & Knowledge Engineering, 67(3), 504–516.

    Article  Google Scholar 

  • Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140.

    Google Scholar 

  • Cabanillas, C., Ciccio, C. D., Mendling, J., & Baumgrass, A. (2014). Predictive task monitoring for business processes. In S. W. Sadiq, P. Soffer, & H. Völzer (Eds.), Business Process Management – 12th International Conference, BPM 2014, Haifa, Israel, September 7–11, 2014. Proceedings. Vol. 8659: Lecture Notes in Computer Science (pp. 424–432). Springer.

    Google Scholar 

  • Camargo, M., Dumas, M., & Rojas, O. G. (2019). Learning accurate LSTM models of business processes. In T. T. Hildebrandt, B. F. van Dongen, M. Röglinger, & J. Mendling (Eds.), 17th International Conference on Business Process Management (BPM 2019). Vol. 11675: LNCS (pp. 286–302). Springer.

    Google Scholar 

  • Castiñera, R., & Metzger, A. (2018). The transforming transport project – Mobility meets big data. In 7th Transport Research Arena (TRA 2018), Vienna, April 16–19, 2018. Elsevier Transportation Research Procedia.

    Google Scholar 

  • DG MOVE. (2018). EU transport in figures: Statistical pocketbook 2018, Directorate- General for Mobility and Transport (European Commission).

    Google Scholar 

  • DHL. (2014). Big data in logistics: A DHL perspective on how to move beyond the hype.

    Google Scholar 

  • Dietterich, T. G. (2000). Ensemble methods in machine learning (pp. 1–15). Berlin: Springer.

    Google Scholar 

  • Dumas, M., La Rosa, M., Mendling, J., & Reijers, H. A. (2018). Fundamentals of business process management (2nd ed.). New York: Springer.

    Book  Google Scholar 

  • Endsley, M. R. (2011). Designing for situation awareness: An approach to user-centered design (2nd ed.). Boca Raton: CRC.

    Google Scholar 

  • Evermann, J., Rehse, J., & Fettke, P. (2017). Predicting process behaviour using deep learning. Decision Support Systems, 100.

    Google Scholar 

  • Francescomarino, C. D., Ghidini, C., Maggi, F. M., & Milani, F. (2018). Predictive process monitoring methods: Which one suits me best? In M. Weske, M. Montali, I. Weber, & J. vom Brocke (Eds.), BPM, Sydney, Australia, September 9–14, 2018. Vol. 11080: LNCS (pp. 462–479). Springer.

    Google Scholar 

  • Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. Cambridge, MA: MIT.

    Google Scholar 

  • Gutierrez, A., Cassales Marquezan, C., Resinas, M., Metzger, A., Ruiz-Cortés, A., et al. (2013). Extending WS-Agreement to support automated conformity check on transport & logistics service agreements. In S. Basu, et al. (Eds.), ICSOC, Berlin, December 2–5, 2013. Vol. 8274: LNCS (pp. 567–574). Springer.

    Google Scholar 

  • Khatri, V., & Samuel, B. M. (2019). Analytics for managerial work. Communications of the ACM, 62(4), 100.

    Article  Google Scholar 

  • Leitner, P., Ferner, J., Hummer, W., & Dustdar, S. (2013). Data-driven and automated prediction of service level agreement violations in service compositions. Distributed and Parallel Databases, 31(3), 447–470.

    Article  Google Scholar 

  • Márquez-Chamorro, A. E., Resinas, M., & Ruiz-Cortés, A. (2018). Predictive monitoring of business processes: A survey. IEEE Transactions on Services Computing, 11(6), 962–977.

    Article  Google Scholar 

  • Mehdiyev, N., Emrich, A., Stahmer, B. P., Fettke, P., & Loos, P. (2017). iprodict – Intelligent process prediction based on big data analytics. In Brambilla & T. Hildebrandt (Eds.), BPM 2017 Industry Track, Barcelona, Spain, September 10–15, 2017. Vol. 1985: CEUR Workshop Proceedings (pp. 13–24). CEUR-WS.org.

  • Mehdiyev, N., Evermann, J., & Fettke, P. (2017). A multi-stage deep learning approach for business process event prediction. In Conference on Business Informatics (CBI 2017), Thessaloniki, July 24–27, 2017.

    Google Scholar 

  • Metzger, A., Leitner, P., Ivanović, D., Schmieders, E., Franklin, R., Carro, M., et al. (2015). Comparing and combining predictive business process monitoring techniques. IEEE Trans. on Systems Man Cybernetics: Systems, 45(2), 276–290.

    Article  Google Scholar 

  • Metzger, A., & Neubauer, A. (2018). Considering non-sequential control flows for process prediction with recurrent neural networks. In 44th Euromicro Conference on Software Engineering and Advanced Applications (SEAA 2018), Prague, August 29–31, 2018. IEEE Computer Society, 2018.

    Google Scholar 

  • Metzger, A., Neubauer, A., Bohn, P., & Pohl, K. (2019). Proactive process adaptation using deep learning ensembles. In P. Giorgini & B. Weber (Eds.), CAiSE 2019, Rome, June 3–7, 2019. Vol. 11483: LNCS. Springer.

    Google Scholar 

  • Metzger, A., Sammodi, O., & Pohl, K. (2012). Accurate proactive adaptation of service- oriented systems. In J. Camara, R. de Lemos, C. Ghezzi, & A. Lopes (Eds.), Assurances for self-adaptive systems (pp. 240–265). New York: Springer.

    Google Scholar 

  • Metzger, A., Thornton, J., Valverde, F., Lopez, J. F. G., & Rublova, D. (2019). Predictive analytics and predictive maintenance innovation via big data: The case of TransformingTransport. In 13th Intelligent Transport Systems - European Congress (ITS Europe), Brainport-Eindhoven, June 3–6, 2019.

    Google Scholar 

  • Moreno, G. A., Cámara, J., Garlan, D., & Schmerl, B. R. (2018). Flexible and efficient decision-making for proactive latency-aware self-adaptation. ACM Transactions on Autonomous and Adaptive Systems, 13(1), 3:1–3:36.

    Article  Google Scholar 

  • Nunes, V. T., Santoro, F. M., Werner, C. M. L., & Ralha, C. G. (2018). Real-time process adaptation: A context-aware replanning approach. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 48(1), 99–118.

    Article  Google Scholar 

  • OECD. (2013). Exploring data-driven innovation as a new source of growth – Mapping the policy issues raised by ‘big data.

    Google Scholar 

  • Polikar, R. (2006). Ensemble based systems in decision making. IEEE Circuits and Systems Magazine, 6(3), 21–45.

    Article  Google Scholar 

  • Poll, R., Polyvyanyy, A., Rosemann, M., Röglinger, M., & Rupprecht, L. (2018). Process forecasting: Towards proactive business process management. In M. Weske, M. Montali, Weber, & J. vom Brocke (Eds.), BPM 2018, Sydney, Australia, September 9–14, 2018. Vol. 11080: LNCS (pp. 496–512). Springer.

    Google Scholar 

  • Pufahl, L., & Weske, M. (2016). Batch processing across multiple business processes based on object life cycles. In W. Abramowicz, R. Alt, & B. Franczyk (Eds.), Business Information Systems – 19th International Conference, BIS 2016, Leipzig, July, 6–8, 2016, Proceedings. Vol. 255: Lecture Notes in Business Information Processing (pp. 195–208). Springer.

    Google Scholar 

  • Rahm, E., & Do, H. H. (2000). Data cleaning: Problems and current approaches. IEEE Data Engineering Bulletin, 23(4), 3–13.

    Google Scholar 

  • Rosemann, M., & vom Brocke, J. (2015). The six core elements of business process management. In Handbook on business process management 1 (pp. 105–122). New York: Springer.

    Google Scholar 

  • Salfner, F., Lenk, M., & Malek, M. (2010). A survey of online failure prediction methods. ACM Computing Surveys, 42(3), 10:1–10:42.

    Article  Google Scholar 

  • Tax, N., Verenich, I., Rosa, M. L., & Dumas, M. (2017). Predictive business process monitoring with LSTM neural networks. In E. Dubois & K. Pohl (Eds.), CAiSE 2017, Essen, June 12–16, 2017, Vol. 10253: LNCS. Springer, 2017.

    Google Scholar 

  • Teinemaa, I., Dumas, M., Rosa, M. L., & Maggi, F. M. (2019). Outcome-oriented predictive process monitoring: Review and benchmark. ACM Transactions on Knowledge Discovery from Data (TKDD), 13.

    Google Scholar 

  • Teinemaa, I., Tax, N., de Leoni, M., Dumas, M., & Maggi, F. M. (2018). Alarm-based prescriptive process monitoring. In M. Weske, M. Montali, I. Weber, & J. vom Brocke (Eds.), BPM Forum 2018, Sydney, September 9–14, 2018, Vol. 329: LNBIP (pp. 91–107). Springer.

    Google Scholar 

  • vom Brocke, J., Mendling, J., & Rosemann, M. (2021). Planning and scoping business process management projects and programs with the BPM Billboard. In J. vom Brocke, J. Mendling, & M. Rosemann (Eds.), BPM cases. Digital innovation and business transformation in practice (Vol. 2). New York: Springer.

    Google Scholar 

  • Wang, D. Yu, C. L., & Sun, X. (2019). Outcome-oriented predictive process monitoring with attention-based bidirectional LSTM neural networks. In E. Bertino, C. K. Chang, P. Chen, E. Damiani, M. Goul, & K. Oyama (Eds.), IEEE International Conference on Web Services, ICWS 2019, Milan, July 8–13, 2019 (pp. 360–367). IEEE.

    Google Scholar 

  • Zhou, Z.-H. (2012). Ensemble methods: Foundations and algorithms. London: Chapman and Hall/CRC.

    Book  Google Scholar 

  • Zillner, S., Gomez, J., Garcia, A., & Curry, E. (Eds.). (2018). Data for artificial intelligence for European economic competitiveness and societal progress. BDVA Position Statement.

    Google Scholar 

Download references

Acknowledgments

This research received funding from the EU’s Horizon 2020 R&I program under grant agreements no. 731932 (TransformingTransport), 871493 (DataPorts), and 732630 (BDVe).

Author information

Authors and Affiliations

  1. paluno (The Ruhr Institute for Software Technology), University of Duisburg-Essen, Duisburg, Germany

    Andreas Metzger

  2. duisport (Duisburger Hafen AG), Duisburg, Germany

    Johannes Franke & Thomas Jansen

Authors
  1. Andreas Metzger
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Johannes Franke
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Thomas Jansen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andreas Metzger .

Editor information

Editors and Affiliations

  1. Department of Information Systems, University of Liechtenstein, Vaduz, Liechtenstein

    Jan vom Brocke

  2. Institute for Information Business, WU Vienna, Vienna, Austria

    Jan Mendling

  3. Centre for Future Enterprise, Queensland University of Technology (QUT), Brisbane, QLD, Australia

    Michael Rosemann

Rights and permissions

Reprints and permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer-Verlag GmbH, DE, part of Springer Nature

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Metzger, A., Franke, J., Jansen, T. (2021). Ensemble Deep Learning for Proactive Terminal Process Management at the Port of Duisburg “duisport”. In: vom Brocke, J., Mendling, J., Rosemann, M. (eds) Business Process Management Cases Vol. 2. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-63047-1_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-662-63047-1_12

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-662-63046-4

  • Online ISBN: 978-3-662-63047-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation