Abstract
Concept drift in process mining refers to a situation where a process undergoes changes over time, leading to a single event log containing data from multiple process versions. To avoid mixing these versions up during analysis, various techniques have been proposed to detect concept drifts. Yet, the performance of these techniques, especially in situations when event logs involve noise or gradual drifts, is shown to be far from optimal. A possible cause for this is that existing techniques are developed according to algorithmic design decisions, operating on assumptions about how drifts manifest themselves in event logs, which may not always reflect reality. In light of this, we propose a completely different approach, using a deep learning model that we trained to learn to recognize drifts. Our computer vision approach for concept drift detection (CV4CDD) uses an image-based representation that visualizes differences in process behavior over time, which enables us to subsequently apply a state-of-the-art object detection model to detect concept drifts. Our experiments reveal that our approach is considerably more accurate and robust than existing techniques, highlighting the promising nature of this new paradigm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Available online: https://python-pillow.org.
- 2.
TensorFlow Model Garden, Available online: https://github.com/tensorflow/models.
- 3.
COCO dataset, Available online: https://cocodataset.org/.
- 4.
If an input image provided for inference has a different pixel size, i.e., because it was established using a different number of windows N, RetinaNet automatically rescales the image to the default size.
- 5.
Project repository: https://gitlab.uni-mannheim.de/processanalytics/cv4cdd,
- 6.
Given the non-determinism involved in training deep learning models, we repeated the training and inference procedure of our approach five times. These repetitions yielded standard deviations of just 0.0087 in recall, 0.0029 in precision, and 0.0067 in F1-score (for CDLG test). We report on the results of the first run in the remainder.
- 7.
Available at http://apromore.org/platform/tools.
References
van der Aalst, W.: Process Mining: Data Science in Action. Springer, Berlin, Heidelberg (2016). https://doi.org/10.1007/978-3-662-49851-4
Adams, J.N., Pitsch, C., Brockhoff, T., van der Aalst, W.: An experimental evaluation of process concept drift detection. Proc. VLDB Endow. 16(8) (2023)
Bose, R.J.C., Van Der Aalst, W., Žliobaitė, I., Pechenizkiy, M.: Dealing with concept drifts in process mining. IEEE Trans. Neural Netw. Learn. Syst. 25(1), 154–171 (2013)
Brockhoff, T., Uysal, M.S., van der Aalst, W.: Time-aware concept drift detection using the earth mover’s distance. In: Proceedings of the ICPM, pp. 33–40. IEEE (2020)
Ceravolo, P., Tavares, G.M., Junior, S.B., Damiani, E.: Evaluation goals for online process mining: a concept drift perspective. IEEE Trans. Serv. Comput. 15(4), 2473–2489 (2022)
van Der Aalst, W., Pesic, M., Schonenberg, H.: Declarative workflows: balancing between flexibility and support. CSRD 23, 99–113 (2009)
Elkhawaga, G., Abuelkheir, M., Barakat, S.I., Riad, A.M., Reichert, M.: CONDA-PM: a systematic review and framework for concept drift analysis in process mining. Algorithms 13(7), 161 (2020)
Grimm, J., Kraus, A., van der Aa, H.: CDLG: a tool for the generation of event logs with concept drifts. In: BPM Demos, vol. 3216, pp. 92–96. CEUR-WS (2022)
Hompes, B.F.A., Buijs, J.C.A.M., van der Aalst, W.M.P., Dixit, P.M., Buurman, J.: Detecting changes in process behavior using comparative case clustering. In: Ceravolo, P., Rinderle-Ma, S. (eds.) SIMPDA 2015. LNBIP, vol. 244, pp. 54–75. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-53435-0_3
Lin, L., Wen, L., Lin, L., Pei, J., Yang, H.: LCDD: detecting business process drifts based on local completeness. IEEE Trans. Serv. Comput. 15(4), 2086–2099 (2020)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, L., et al.: Deep learning for generic object detection: a survey. IJCV 128, 261–318 (2020)
Lu, X., Fahland, D., van den Biggelaar, F.J.H.M., van der Aalst, W.M.P.: Detecting deviating behaviors without models. In: Reichert, M., Reijers, H.A. (eds.) BPM 2015. LNBIP, vol. 256, pp. 126–139. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-42887-1_11
Maaradji, A., Dumas, M., La Rosa, M., Ostovar, A.: Detecting sudden and gradual drifts in business processes from execution traces. IEEE Trans. Knowl. Data Eng. 29(10), 2140–2154 (2017)
Martjushev, J., Bose, R.P.J.C., van der Aalst, W.M.P.: Change point detection and dealing with gradual and multi-order dynamics in process mining. In: Matulevičius, R., Dumas, M. (eds.) BIR 2015. LNBIP, vol. 229, pp. 161–178. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-21915-8_11
Nguyen, H., Dumas, M., La Rosa, M., ter Hofstede, A.H.M.: Multi-perspective comparison of business process variants based on event logs. In: Trujillo, J.C., et al. (eds.) ER 2018. LNCS, vol. 11157, pp. 449–459. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00847-5_32
Ostovar, A., Maaradji, A., La Rosa, M., ter Hofstede, A.H.M., van Dongen, B.F.V.: Detecting drift from event streams of unpredictable business processes. In: Comyn-Wattiau, I., Tanaka, K., Song, I.-Y., Yamamoto, S., Saeki, M. (eds.) ER 2016. LNCS, vol. 9974, pp. 330–346. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46397-1_26
Pasquadibisceglie, V., Appice, A., Castellano, G., Malerba, D., Modugno, G.: Orange: outcome-oriented predictive process monitoring based on image encoding and CNNs. IEEE Access 8, 184073–184086 (2020)
Pfeiffer, P., Lahann, J., Fettke, P.: Multivariate business process representation learning utilizing Gramian angular fields and convolutional neural networks. In: Polyvyanyy, A., Wynn, M.T., Van Looy, A., Reichert, M. (eds.) BPM 2021. LNCS, vol. 12875, pp. 327–344. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-85469-0_21
Sato, D.M.V., De Freitas, S.C., Barddal, J.P., Scalabrin, E.E.: A survey on concept drift in process mining. ACM Comput. Surv. 54(9), 1–38 (2021)
Seeliger, A., Nolle, T., Mühlhäuser, M.: Detecting concept drift in processes using graph metrics on process graphs. In: Proceedings of the S-BPM, vol. 9, pp. 1–10. ACM (2017)
Smirnov, S., Weidlich, M., Mendling, J.: Business process model abstraction based on synthesis from well-structured behavioral profiles. Int. J. Coop. Inf. Syst. 21(01), 55–83 (2012)
van der Aalst, W., et al.: Process mining manifesto. In: Daniel, F., Barkaoui, K., Dustdar, S. (eds.) BPM 2011. LNBIP, vol. 99, pp. 169–194. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-28108-2_19
Yeshchenko, A., Di Ciccio, C., Mendling, J., Polyvyanyy, A.: Visual drift detection for event sequence data of business processes. IEEE Trans. Vis. Comput. Graph. 28(8), 3050–3068 (2021)
Zheng, C., Wen, L., Wang, J.: Detecting process concept drifts from event logs. In: Panetto, H., et al. (eds.) OTM 2017. LNCS, vol. 10573, pp. 524–542. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-69462-7_33
Acknowledgment
We acknowledge the work of Jonathan Kößler for conducting the initial testing of the paper’s idea in his master’s thesis.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kraus, A., van der Aa, H. (2024). Looking for Change: A Computer Vision Approach for Concept Drift Detection in Process Mining. In: Marrella, A., Resinas, M., Jans, M., Rosemann, M. (eds) Business Process Management. BPM 2024. Lecture Notes in Computer Science, vol 14940. Springer, Cham. https://doi.org/10.1007/978-3-031-70396-6_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-70396-6_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-70395-9
Online ISBN: 978-3-031-70396-6
eBook Packages: Computer ScienceComputer Science (R0)