1.
Verbeek, H. M. W.
Process Discovery Contest 2023 Miscellaneous
4TU.ResearchData, 2023.
@misc{PDC2023,
title = {Process Discovery Contest 2023},
author = {H. M. W. Verbeek},
url = {https://icpmconference.org/2023/process-discovery-contest/},
doi = {10.4121/afd6f608-469e-48f9-977d-875b45840d39.v1},
year = {2023},
date = {2023-10-04},
abstract = {PDC2023 data set},
howpublished = {4TU.ResearchData},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
PDC2023 data set
2.
Verbeek, H. M. W.
Discovering an S-Coverable WF-net using DiSCover Proceedings Article
In: Burattin, A.; Polyvyannyy, A.; Weber, B. (Ed.): Proceedings of the 2022 4th International Conference on Process Mining (ICPM 2022), pp. 64–71, IEEE, 2022, ISBN: 979-8-3503-9714-7.
@inproceedings{Verbeek22,
title = {Discovering an S-Coverable WF-net using DiSCover},
author = {H. M. W. Verbeek},
editor = {A. Burattin and A. Polyvyannyy and B. Weber},
url = {https://hverbeek.win.tue.nl/wp-content/papercite-data/pdf/verbeek22.pdf},
doi = {10.1109/ICPM57379.2022.9980723},
isbn = {979-8-3503-9714-7},
year = {2022},
date = {2022-12-24},
urldate = {2022-00-00},
booktitle = {Proceedings of the 2022 4th International Conference on Process Mining (ICPM 2022)},
pages = {64--71},
publisher = {IEEE},
abstract = {Although many algorithms exist that can discover a WF-net from an event log, only a few (if any at all) can discover advanced routing constructs. As examples, the Inductive miner uses process trees and cannot discover complex loops, or situations where choice and parallel behavior is mixed, and the Hybrid ILP miner cannot discover certain complex routing constructs because it cannot discover silent transitions. This paper introduces the DiSCover miner, a discovery algorithm that can discover these more complex constructs and that is implemented in ProM. The DiSCover miner discovers from the event log a WF-net that corresponds to a collection of state machines that need to synchronize on the visible transitions (that is, on the activities from the event log). As such, it discovers a WF-net that is S-Coverable but not necessarily sound. Initial results show that it can discover complex routing constructs and that it performs well on the data sets of the different Process Discovery Contests. It even preformed better than winners of the 2020 and 2021 contests.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Although many algorithms exist that can discover a WF-net from an event log, only a few (if any at all) can discover advanced routing constructs. As examples, the Inductive miner uses process trees and cannot discover complex loops, or situations where choice and parallel behavior is mixed, and the Hybrid ILP miner cannot discover certain complex routing constructs because it cannot discover silent transitions. This paper introduces the DiSCover miner, a discovery algorithm that can discover these more complex constructs and that is implemented in ProM. The DiSCover miner discovers from the event log a WF-net that corresponds to a collection of state machines that need to synchronize on the visible transitions (that is, on the activities from the event log). As such, it discovers a WF-net that is S-Coverable but not necessarily sound. Initial results show that it can discover complex routing constructs and that it performs well on the data sets of the different Process Discovery Contests. It even preformed better than winners of the 2020 and 2021 contests.
3.
Verbeek, H. M. W.
Process Discovery Contest 2022 Miscellaneous
4TU.ResearchData, 2022.
@misc{PDC2022,
title = {Process Discovery Contest 2022},
author = {H. M. W. Verbeek},
url = {https://icpmconference.org/2022/process-discovery-contest/},
doi = {10.4121/21261402.v1},
year = {2022},
date = {2022-10-03},
urldate = {2022-10-03},
abstract = {PDC2022 data set.},
howpublished = {4TU.ResearchData},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
PDC2022 data set.
4.
Augusto, A.; Carmona, J.; Verbeek, H. M. W.
Advanced Process Discovery Techniques Book Chapter
In: Aalst, W. M. P.; Carmona, J. (Ed.): Process Mining Handbook, vol. 448, pp. 76–107, Springer, Cham, 2022.
@inbook{Augusto22,
title = {Advanced Process Discovery Techniques},
author = {A. Augusto and J. Carmona and H. M. W. Verbeek},
editor = {W. M. P. Aalst and J. Carmona},
doi = {10.1007/978-3-031-08848-3_3},
year = {2022},
date = {2022-06-27},
urldate = {2022-06-27},
booktitle = {Process Mining Handbook},
volume = {448},
pages = {76--107},
publisher = {Springer, Cham},
series = {Lecture Notes in Business Information Processing},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
5.
Verbeek, H. M. W.
The Log Skeleton Visualizer in ProM 6.9: The winning contribution to the Process Discovery Contest 2019 Journal Article
In: International Journal on Software Tools for Technology Transfer, vol. 24, no. 4, pp. 549–561, 2022, (Accepted for publication in 'STTT Competitions and Challenges Track - TOOLympics 2019').
@article{Verbeek21,
title = {The Log Skeleton Visualizer in ProM 6.9: The winning contribution to the Process Discovery Contest 2019},
author = {H. M. W. Verbeek},
doi = {10.1007/s10009-021-00618-y},
year = {2022},
date = {2022-05-17},
urldate = {2022-00-00},
issuetitle = {TOOLympics 2019},
journal = {International Journal on Software Tools for Technology Transfer},
volume = {24},
number = {4},
pages = {549--561},
abstract = {Process discovery is an important area in the field of process mining. To help advance this area, a Process Discovery Contest (PDC) has been set up, which allows us to compare different approaches. At the moment of writing, there have been three instances of the PDC: In 2016, in 2017, and in 2019. This paper introduces the winning contribution to the PDC 2019, called the Log Skeleton Visualizer. This visualizer uses a novel type of process models called log skeletons. In contrast to many workflow-net-based discovery techniques, these log skeletons do not rely on the directly follows relation. As a result, log skeletons offer circumstantial information on the event log at hand rather than only sequential information. Using this visualizer we were able to classify 898 out of 900 traces correctly for the PDC 2019, and to win this contest.},
note = {Accepted for publication in 'STTT Competitions and Challenges Track - TOOLympics 2019'},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Process discovery is an important area in the field of process mining. To help advance this area, a Process Discovery Contest (PDC) has been set up, which allows us to compare different approaches. At the moment of writing, there have been three instances of the PDC: In 2016, in 2017, and in 2019. This paper introduces the winning contribution to the PDC 2019, called the Log Skeleton Visualizer. This visualizer uses a novel type of process models called log skeletons. In contrast to many workflow-net-based discovery techniques, these log skeletons do not rely on the directly follows relation. As a result, log skeletons offer circumstantial information on the event log at hand rather than only sequential information. Using this visualizer we were able to classify 898 out of 900 traces correctly for the PDC 2019, and to win this contest.
6.
Wynn, M. T.; Lebherz, J.; van der Aalst, W. M. P.; Accorsi, R.; Di Ciccio, C.; Jayarathna, L.; Verbeek, H. M. W.
Rethinking the Input for Process Mining: Insights from the XES Survey and Workshop Proceedings Article
In: Munoz-Gama, J.; Lu, X. (Ed.): Process Mining Workshops, pp. 3–16, Springer International Publishing, Cham, 2022, ISBN: 978-3-030-98581-3.
@inproceedings{Wynn22,
title = {Rethinking the Input for Process Mining: Insights from the XES Survey and Workshop},
author = {M. T. Wynn and J. Lebherz and W. M. P. van der Aalst and R. Accorsi and Di Ciccio, C. and L. Jayarathna and H. M. W. Verbeek},
editor = {J. Munoz-Gama and X. Lu},
doi = {10.1007/978-3-030-98581-3_1},
isbn = {978-3-030-98581-3},
year = {2022},
date = {2022-03-24},
urldate = {2022-03-24},
booktitle = {Process Mining Workshops},
volume = {433},
pages = {3--16},
publisher = {Springer International Publishing},
address = {Cham},
series = {Lecture Notes in Business Information Processing (LNBIP)},
abstract = {Although the popularity and adoption of process mining techniques grew rapidly in recent years, a large portion of effort invested in process mining initiatives is still consumed by event data extraction and transformation rather than process analysis. The IEEE Task Force on Process Mining conducted a study focused on the challenges faced during event data preparation (from source data to event log). This paper presents findings from the online survey with 289 participants spanning the roles of practitioners, researchers, software vendors, and end-users. These findings were presented at the XES 2.0 workshop co-located with the 3rd International Conference on Process Mining. The workshop also hosted presentations from various stakeholder groups and a discussion panel on the future of XES and the input needed for process mining. This paper summarises the main findings of both the survey and the workshop. These outcomes help us to accelerate and improve the standardisation process, hopefully leading to a new standard widely adopted by both academia and industry.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Although the popularity and adoption of process mining techniques grew rapidly in recent years, a large portion of effort invested in process mining initiatives is still consumed by event data extraction and transformation rather than process analysis. The IEEE Task Force on Process Mining conducted a study focused on the challenges faced during event data preparation (from source data to event log). This paper presents findings from the online survey with 289 participants spanning the roles of practitioners, researchers, software vendors, and end-users. These findings were presented at the XES 2.0 workshop co-located with the 3rd International Conference on Process Mining. The workshop also hosted presentations from various stakeholder groups and a discussion panel on the future of XES and the input needed for process mining. This paper summarises the main findings of both the survey and the workshop. These outcomes help us to accelerate and improve the standardisation process, hopefully leading to a new standard widely adopted by both academia and industry.
7.
Verbeek, H. M. W.; Fahland, D.
CPN IDE: An Extensible Replacement for CPN Tools That Uses Access/CPN Proceedings Article
In: Jans, M.; Janssenswillen, G.; Kalenkova, A.; Maggi, F. M. (Ed.): Proceedings of the ICPM Doctoral Consortium and Demo Track 2021 co-located with 10th International Conference on Process Mining (ICPM 2021), pp. 29–30, CEUR-WS.org, 2021.
@inproceedings{Verbeek21a,
title = {CPN IDE: An Extensible Replacement for CPN Tools That Uses Access/CPN},
author = {H. M. W. Verbeek and D. Fahland},
editor = {M. Jans and G. Janssenswillen and A. Kalenkova and F. M. Maggi},
url = {http://ceur-ws.org/Vol-3098/demo_197.pdf
https://hverbeek.win.tue.nl/wp-content/uploads/2023/02/Verbeek21a.pdf},
year = {2021},
date = {2021-11-04},
urldate = {2021-11-04},
booktitle = {Proceedings of the ICPM Doctoral Consortium and Demo Track 2021 co-located with 10th International Conference on Process Mining (ICPM 2021)},
pages = {29--30},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
abstract = {This extended abstract introduces CPN IDE, which replaces CPN Tools as a tool for editing and simulating (Coloured) Petri Net models. The main advantage of CPN IDE is that it is an extensible tool, which is needed to keep it running and to add new features which are of interest to the process mining community, like easily generating event logs.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This extended abstract introduces CPN IDE, which replaces CPN Tools as a tool for editing and simulating (Coloured) Petri Net models. The main advantage of CPN IDE is that it is an extensible tool, which is needed to keep it running and to add new features which are of interest to the process mining community, like easily generating event logs.
8.
Verbeek, H. M. W.
Process Discovery Contest 2021 Miscellaneous
4TU.ResearchData, 2021.
@misc{PDC2021,
title = {Process Discovery Contest 2021},
author = {H. M. W. Verbeek},
url = {https://icpmconference.org/2021/process-discovery-contest/},
doi = {10.4121/16803232.v1},
year = {2021},
date = {2021-10-13},
urldate = {2021-10-13},
abstract = {PDC2021 data set.},
howpublished = {4TU.ResearchData},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
PDC2021 data set.
9.
Verbeek, H. M. W.
Process Discovery Contest 2020 Miscellaneous
4TU.ResearchData, 2021.
@misc{PDC2020,
title = {Process Discovery Contest 2020},
author = {H. M. W. Verbeek},
url = {https://icpmconference.org/2020/process-discovery-contest/},
doi = {10.4121/14626020.v1},
year = {2021},
date = {2021-05-21},
urldate = {2021-05-21},
abstract = {This is the data set that was used for the Process Discovery Contest of 2020 (PDC 2020). The data set contains 192 training logs, 192 corresponding test logs, 192 corresponding ground truth logs, and 96 models. The logs are all stored using the IEEE XES file format (see either https://www.xes-standard.org/ or https://ieeexplore.ieee.org/document/7740858), while the models are workflow nets (a subclass of Petri nets) stored in the PNML file format (see
https://www.iso.org/obp/ui/#iso:std:iso-iec:15909:-2:ed-1:v1:en).},
howpublished = {4TU.ResearchData},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
This is the data set that was used for the Process Discovery Contest of 2020 (PDC 2020). The data set contains 192 training logs, 192 corresponding test logs, 192 corresponding ground truth logs, and 96 models. The logs are all stored using the IEEE XES file format (see either https://www.xes-standard.org/ or https://ieeexplore.ieee.org/document/7740858), while the models are workflow nets (a subclass of Petri nets) stored in the PNML file format (see
https://www.iso.org/obp/ui/#iso:std:iso-iec:15909:-2:ed-1:v1:en).
https://www.iso.org/obp/ui/#iso:std:iso-iec:15909:-2:ed-1:v1:en).
10.
Dixit, P. M.; Verbeek, H. M. W.; van der Aalst, W. M. P.
Fast Conformance Analysis based on Activity Log Abstraction Proceedings Article
In: Nurcan, Selmin; Johnson, Pontus (Ed.): 2018 IEEE 22nd International Enterprise Distributed Object Computing Conference, Proceedings, pp. 135–144, IEEE, 2018.
@inproceedings{Dixit18b,
title = {Fast Conformance Analysis based on Activity Log Abstraction},
author = {P. M. Dixit and H. M. W. Verbeek and W. M. P. van der Aalst},
editor = {Selmin Nurcan and Pontus Johnson},
url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8536157
https://hverbeek.win.tue.nl/wp-content/uploads/2023/02/Dixit18b.pdf},
doi = {10.1109/EDOC.2018.00026},
year = {2018},
date = {2018-10-01},
urldate = {2018-10-01},
booktitle = {2018 IEEE 22nd International Enterprise Distributed Object Computing Conference, Proceedings},
pages = {135--144},
publisher = {IEEE},
abstract = {Process mining techniques focus on bridging the gap between activity logs and business process management. Process discovery is a sub-field of process mining which uses activity logs in order to discover process models. Some process discovery techniques, such as interactive process discovery and genetic algorithms, rely on the so-called conformance analysis. In such techniques, process models are discovered in an incremental way, and the quality of the process models is quantified by the results of conformance analysis. State-of-the-art conformance analysis techniques are typically optimized and devised for one-time use. However, in process discovery settings which are incremental in nature, it is imperative to have fast conformance analysis. Moreover, the activity logs used for conformance analysis at each stage remain the same. In this paper, we propose an approach that exploits this fact in order to expedite conformance analysis by approximating the conformance results. We use an abstracted version of an activity log, which can be used to compare withthe changing (or new) process models in an incremental processdiscovery setting. Our results show that the proposed technique isable to outperform traditional conformance techniques in terms of performance by approximating conformance scores.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Process mining techniques focus on bridging the gap between activity logs and business process management. Process discovery is a sub-field of process mining which uses activity logs in order to discover process models. Some process discovery techniques, such as interactive process discovery and genetic algorithms, rely on the so-called conformance analysis. In such techniques, process models are discovered in an incremental way, and the quality of the process models is quantified by the results of conformance analysis. State-of-the-art conformance analysis techniques are typically optimized and devised for one-time use. However, in process discovery settings which are incremental in nature, it is imperative to have fast conformance analysis. Moreover, the activity logs used for conformance analysis at each stage remain the same. In this paper, we propose an approach that exploits this fact in order to expedite conformance analysis by approximating the conformance results. We use an abstracted version of an activity log, which can be used to compare withthe changing (or new) process models in an incremental processdiscovery setting. Our results show that the proposed technique isable to outperform traditional conformance techniques in terms of performance by approximating conformance scores.
11.
Dixit, P. M.; Verbeek, H. M. W.; Buijs, J. C. A. M.; van der Aalst, W. M. P.
Interactive Data-driven Process Model Construction Conference
37th International Conference on Conceptual Modeling, ER 2018, Proceedings, vol. 11157, LNCS Springer, 2018.
@conference{Dixit18a,
title = {Interactive Data-driven Process Model Construction},
author = {P. M. Dixit and H. M. W. Verbeek and J. C. A. M. Buijs and W. M. P. van der Aalst},
editor = {Z. Li and J. C. Trujillo and X. Du and M. L. Lee and K. C. Davis and T. W. Ling and G. Li},
url = {https://hverbeek.win.tue.nl/wp-content/uploads/2023/02/Dixit18a.pdf},
doi = {10.1007/978-3-030-00847-5_19},
year = {2018},
date = {2018-10-01},
urldate = {2018-10-01},
booktitle = {37th International Conference on Conceptual Modeling, ER 2018, Proceedings},
volume = {11157},
pages = {251--265},
publisher = {Springer},
series = {LNCS},
abstract = {Process discovery algorithms address the problem of learning process models from event logs. Typically, in such settings a user's activity is limited to con guring the parameters of the discovery algorithm, and hence the user expertise/domain knowledge can not be incorporated during traditional process discovery. In a setting where the event logs are noisy, incomplete and/or contain uninteresting activities, the process models discovered by discovery algorithms are often inaccurate and/or incomprehensible. Furthermore, many of these automated techniques can produce unsound models and/or cannot discover duplicate activities, silent activities etc. To overcome such shortcomings, we introduce a new concept to interactively discover a process model, by combining a user's domain knowledge with the information from the event log. The discovered models are always sound and can have duplicate activities, silent activities etc. An objective evaluation and a case study shows that the proposed approach can outperform traditional discovery techniques.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Process discovery algorithms address the problem of learning process models from event logs. Typically, in such settings a user's activity is limited to con guring the parameters of the discovery algorithm, and hence the user expertise/domain knowledge can not be incorporated during traditional process discovery. In a setting where the event logs are noisy, incomplete and/or contain uninteresting activities, the process models discovered by discovery algorithms are often inaccurate and/or incomprehensible. Furthermore, many of these automated techniques can produce unsound models and/or cannot discover duplicate activities, silent activities etc. To overcome such shortcomings, we introduce a new concept to interactively discover a process model, by combining a user's domain knowledge with the information from the event log. The discovered models are always sound and can have duplicate activities, silent activities etc. An objective evaluation and a case study shows that the proposed approach can outperform traditional discovery techniques.
12.
Lee, W. L. J.; Verbeek, H. M. W.; Munoz-Gama, J.; van der Aalst, W. M. P.; Sepúlveda, M.
Recomposing conformance: Closing the circle on decomposed alignment-based conformance checking in process mining Journal Article
In: Information Sciences, vol. 466, pp. 55–91, 2018.
@article{Lee18a,
title = {Recomposing conformance: Closing the circle on decomposed alignment-based conformance checking in process mining},
author = {W. L. J. Lee and H. M. W. Verbeek and J. Munoz-Gama and W. M. P. van der Aalst and M. Sepúlveda},
doi = {10.1016/j.ins.2018.07.026},
year = {2018},
date = {2018-10-01},
urldate = {2018-10-01},
journal = {Information Sciences},
volume = {466},
pages = {55--91},
abstract = {In the area of process mining, efficient conformance checking is one of the main challenges. Several process mining vendors are in the process of implementing conformance checking in their tools to allow the user to check how well a model fits an event log. Current approaches for conformance checking are monolithic and compute exact fitness values but this may take excessive time. Alternatively, one can use a decomposition approach, which runs much faster but does not always compute an exact fitness value.
This paper introduces a recomposition approach that takes the best of both: it returns the exact fitness value by using the decomposition approach in an iterative manner. Results show that similar speedups can be obtained as by using the decomposition approach, but now the exact fitness value is guaranteed. Even better, this approach supports a configurable time-bound: “Give me the best fitness estimation you can find within 10 minutes.” In such a case, the approach returns an interval that contains the exact fitness value. If such an interval is sufficiently narrow, there is no need to spend unnecessary time to compute the exact value.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In the area of process mining, efficient conformance checking is one of the main challenges. Several process mining vendors are in the process of implementing conformance checking in their tools to allow the user to check how well a model fits an event log. Current approaches for conformance checking are monolithic and compute exact fitness values but this may take excessive time. Alternatively, one can use a decomposition approach, which runs much faster but does not always compute an exact fitness value.
This paper introduces a recomposition approach that takes the best of both: it returns the exact fitness value by using the decomposition approach in an iterative manner. Results show that similar speedups can be obtained as by using the decomposition approach, but now the exact fitness value is guaranteed. Even better, this approach supports a configurable time-bound: “Give me the best fitness estimation you can find within 10 minutes.” In such a case, the approach returns an interval that contains the exact fitness value. If such an interval is sufficiently narrow, there is no need to spend unnecessary time to compute the exact value.
This paper introduces a recomposition approach that takes the best of both: it returns the exact fitness value by using the decomposition approach in an iterative manner. Results show that similar speedups can be obtained as by using the decomposition approach, but now the exact fitness value is guaranteed. Even better, this approach supports a configurable time-bound: “Give me the best fitness estimation you can find within 10 minutes.” In such a case, the approach returns an interval that contains the exact fitness value. If such an interval is sufficiently narrow, there is no need to spend unnecessary time to compute the exact value.
13.
Sonke, W. M.; Verbeek, K. A. B.; Meulemans, W.; Verbeek, H. M. W.; Speckmann, B.
Optimal Algorithms for Compact Linear Layouts Conference
2018 IEEE Pacific Visualization Symposium, PacificVis 2018, Proceedings, IEEE Computer Society, 2018.
@conference{Sonke18,
title = {Optimal Algorithms for Compact Linear Layouts},
author = {W. M. Sonke and K. A. B. Verbeek and W. Meulemans and H. M. W. Verbeek and B. Speckmann},
doi = {10.1109/PacificVis.2018.00010},
year = {2018},
date = {2018-05-01},
booktitle = {2018 IEEE Pacific Visualization Symposium, PacificVis 2018, Proceedings},
pages = {1--10},
publisher = {IEEE Computer Society},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
14.
van Zelst, S. J.; van Dongen, B. F.; van der Aalst, W. M. P.; Verbeek, H. M. W.
Discovering workflow nets using integer linear programming Journal Article
In: Computing, vol. 100, no. 5, pp. 529–556, 2018.
@article{Zelst18,
title = {Discovering workflow nets using integer linear programming},
author = {S. J. van Zelst and B. F. van Dongen and W. M. P. van der Aalst and H. M. W. Verbeek},
url = {https://doi.org/10.1007/s00607-017-0582-5},
doi = {10.1007/s00607-017-0582-5},
year = {2018},
date = {2018-05-01},
journal = {Computing},
volume = {100},
number = {5},
pages = {529--556},
abstract = {Process mining is concerned with the analysis, understanding and improvement of business processes. Process discovery, i.e. discovering a process model based on an event log, is considered the most challenging process mining task. State-of-the-art process discovery algorithms only discover local control flow patterns and are unable to discover complex, non-local patterns. Region theory based techniques, i.e. an established class of process discovery techniques, do allow for discovering such patterns. However, applying region theory directly results in complex, overfitting models, which is less desirable. Moreover, region theory does not cope with guarantees provided by state-of-the-art process discovery algorithms, both w.r.t. structural and behavioural properties of the discovered process models. In this paper we present an ILP-based process discovery approach, based on region theory, that guarantees to discover relaxed sound workflow nets. Moreover, we devise a filtering algorithm, based on the internal working of the ILP-formulation, that is able to cope with the presence of infrequent, exceptional behaviour. We have extensively evaluated the technique using different event logs with different levels of exceptional behaviour. Our experiments show that the presented approach allows us to leverage the inherent shortcomings of existing region-based approaches. The techniques presented are implemented and readily available in the HybridILPMiner package in the open-source process mining tool-kits ProM (http://promtools.org) and RapidProM (http://rapidprom.org).},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Process mining is concerned with the analysis, understanding and improvement of business processes. Process discovery, i.e. discovering a process model based on an event log, is considered the most challenging process mining task. State-of-the-art process discovery algorithms only discover local control flow patterns and are unable to discover complex, non-local patterns. Region theory based techniques, i.e. an established class of process discovery techniques, do allow for discovering such patterns. However, applying region theory directly results in complex, overfitting models, which is less desirable. Moreover, region theory does not cope with guarantees provided by state-of-the-art process discovery algorithms, both w.r.t. structural and behavioural properties of the discovered process models. In this paper we present an ILP-based process discovery approach, based on region theory, that guarantees to discover relaxed sound workflow nets. Moreover, we devise a filtering algorithm, based on the internal working of the ILP-formulation, that is able to cope with the presence of infrequent, exceptional behaviour. We have extensively evaluated the technique using different event logs with different levels of exceptional behaviour. Our experiments show that the presented approach allows us to leverage the inherent shortcomings of existing region-based approaches. The techniques presented are implemented and readily available in the HybridILPMiner package in the open-source process mining tool-kits ProM (http://promtools.org) and RapidProM (http://rapidprom.org).
15.
Meulemans, W.; Sonke, W. M.; Speckmann, B.; Verbeek, H. M. W.; Verbeek, K. A. B.
Optimal Algorithms for Compact Linear Layouts Conference
34th European Workshop on Computational Geometry (EuroCG2018), Proceedings, 2018.
@conference{Meulemans18,
title = {Optimal Algorithms for Compact Linear Layouts},
author = {W. Meulemans and W. M. Sonke and B. Speckmann and H. M. W. Verbeek and K. A. B. Verbeek},
doi = {10.1109/PacificVis.2018.00010},
year = {2018},
date = {2018-03-01},
booktitle = {34th European Workshop on Computational Geometry (EuroCG2018), Proceedings},
pages = {10:1--10:6},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
16.
Dixit, P. M.; Buijs, J. C. A. M.; Verbeek, H. M. W.; van der Aalst, W. M. P.
Fast Incremental Conformance Analysis for Interactive Process Discovery Conference
Business Information Systems - 21st International Conference, BIS 2018, Proceedings, vol. 320, LNBIP Springer, 2018.
@conference{Dixit18,
title = {Fast Incremental Conformance Analysis for Interactive Process Discovery},
author = {P. M. Dixit and J. C. A. M. Buijs and H. M. W. Verbeek and W. M. P. van der Aalst},
editor = {W. Abramowicz and A. Paschke},
url = {http://www.scopus.com/inward/record.url?scp=85050635542&partnerID=8YFLogxK},
doi = {10.1007/978-3-319-93931-5_12},
year = {2018},
date = {2018-01-01},
booktitle = {Business Information Systems - 21st International Conference, BIS 2018, Proceedings},
volume = {320},
pages = {163--175},
publisher = {Springer},
series = {LNBIP},
abstract = {Interactive process discovery allows users to specify domain knowledge while discovering process models with the help of event logs. Typically the coherence of an event log and a process model is calculated using conformance analysis. Many state-of-the-art conformance techniques emphasize on the correctness of the results, and hence can be slow, impractical and undesirable in interactive process discovery setting, especially when the process models are complex. In this paper, we present a framework (and its application) to calculate conformance fast enough to guide the user in interactive process discovery. The proposed framework exploits the underlying techniques used for interactive process discovery in order to incrementally update the conformance results. We trade the accuracy of conformance for performance. However, the user is also provided with some diagnostic information, which can be useful for decision making in an interactive process discovery setting. The results show that our approach can be considerably faster than the traditional approaches and hence better suited in an interactive setting.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Interactive process discovery allows users to specify domain knowledge while discovering process models with the help of event logs. Typically the coherence of an event log and a process model is calculated using conformance analysis. Many state-of-the-art conformance techniques emphasize on the correctness of the results, and hence can be slow, impractical and undesirable in interactive process discovery setting, especially when the process models are complex. In this paper, we present a framework (and its application) to calculate conformance fast enough to guide the user in interactive process discovery. The proposed framework exploits the underlying techniques used for interactive process discovery in order to incrementally update the conformance results. We trade the accuracy of conformance for performance. However, the user is also provided with some diagnostic information, which can be useful for decision making in an interactive process discovery setting. The results show that our approach can be considerably faster than the traditional approaches and hence better suited in an interactive setting.
17.
Dixit, P. M.; Verbeek, H. M. W.; van der Aalst, W. M. P.
Incremental Computation of Synthesis Rules for Free-Choice Petri nets Conference
Formal Aspects of Component Software - 15th International Conference, FACS 2018, Proceedings, vol. 11222, LNCS 2018.
@conference{Dixit18c,
title = {Incremental Computation of Synthesis Rules for Free-Choice Petri nets},
author = {P. M. Dixit and H. M. W. Verbeek and W. M. P. van der Aalst},
editor = {P. C. Ölveczky and K. Bae},
year = {2018},
date = {2018-01-01},
booktitle = {Formal Aspects of Component Software - 15th International Conference, FACS 2018, Proceedings},
volume = {11222},
pages = {97--117},
series = {LNCS},
abstract = {In this paper, we propose a novel approach that calculates all the possible applications of synthesis rules, for well-formed free-choice Petri nets, in a speedy way to enable an interactive editing system. The proposed approach uses a so-called incremental synthesis structure, which can be used to extract all the synthesis rules, corresponding to a given net. Furthermore, this structure is updated incrementally, i.e. after usage of a synthesis rule, to obtain the incremental synthesis structure of the newly synthesized net. We prove that the proposed approach is correct and complete in order to synthesize any well-formed free-choice Petri net, starting with an initial well-formed atomic net and the corresponding incremental synthesis structure. A variant of the proposed approach has been implemented that allows interactive modeling (discovery) of sound business processes (from event logs). Experimental results show that the proposed approach is fast, and outperforms the baseline, and hence is well-suited for enabling interactive synthesis of very large nets.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
In this paper, we propose a novel approach that calculates all the possible applications of synthesis rules, for well-formed free-choice Petri nets, in a speedy way to enable an interactive editing system. The proposed approach uses a so-called incremental synthesis structure, which can be used to extract all the synthesis rules, corresponding to a given net. Furthermore, this structure is updated incrementally, i.e. after usage of a synthesis rule, to obtain the incremental synthesis structure of the newly synthesized net. We prove that the proposed approach is correct and complete in order to synthesize any well-formed free-choice Petri net, starting with an initial well-formed atomic net and the corresponding incremental synthesis structure. A variant of the proposed approach has been implemented that allows interactive modeling (discovery) of sound business processes (from event logs). Experimental results show that the proposed approach is fast, and outperforms the baseline, and hence is well-suited for enabling interactive synthesis of very large nets.
18.
Caballero, H. S. Garcia; Westenberg, M. A.; Verbeek, H. M. W.; van der Aalst, W. M. P.
Visual analytics for soundness verification of process models Book Section
In: Teniente, E.; Weidlich, M. (Ed.): BPM 2017 International Workshops, Barcelona, Spain, September 10-11, 2017, Revised Papers, vol. 308, pp. 744–756, Springer, 2018.
@incollection{GarciaCaballero18,
title = {Visual analytics for soundness verification of process models},
author = {H. S. Garcia Caballero and M. A. Westenberg and H. M. W. Verbeek and W. M. P. van der Aalst},
editor = {E. Teniente and M. Weidlich},
doi = {10.1007/978-3-319-74030-0_59},
year = {2018},
date = {2018-01-01},
booktitle = {BPM 2017 International Workshops, Barcelona, Spain, September 10-11, 2017, Revised Papers},
volume = {308},
pages = {744--756},
publisher = {Springer},
series = {Lecture Notes in Business Information Processing},
abstract = {Soundness validation of process models is a complex task for process modelers due to all the factors that must be taken into account. Although there are tools to verify this property, they do not provide users with easy information on where soundness starts breaking and under which conditions. Providing insights such as states in which problems occur, involved activities, or paths leading to those states, is crucial for process modelers to better understand why the model is not sound. In this paper we address the problem of validating the soundness property of a process model by using a novel visual approach and a new tool called PSVis (Petri net Soundness Visualization) supporting this approach. The PSVis tool aims to guide expert users through the process models in order to get insights into the problems that cause the process to be unsound.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Soundness validation of process models is a complex task for process modelers due to all the factors that must be taken into account. Although there are tools to verify this property, they do not provide users with easy information on where soundness starts breaking and under which conditions. Providing insights such as states in which problems occur, involved activities, or paths leading to those states, is crucial for process modelers to better understand why the model is not sound. In this paper we address the problem of validating the soundness property of a process model by using a novel visual approach and a new tool called PSVis (Petri net Soundness Visualization) supporting this approach. The PSVis tool aims to guide expert users through the process models in order to get insights into the problems that cause the process to be unsound.
19.
Lee, W. L. J.; Munoz-Gama, J.; Verbeek, H. M. W.; van der Aalst, W. M. P.; Sepúlveda, M.
Improving merging conditions for recomposing conformance checking Proceedings Article
In: Proceedings of the BPI 2018 workshop, 2018.
@inproceedings{Lee18,
title = {Improving merging conditions for recomposing conformance checking},
author = {W. L. J. Lee and J. Munoz-Gama and H. M. W. Verbeek and W. M. P. van der Aalst and M. Sepúlveda},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
booktitle = {Proceedings of the BPI 2018 workshop},
abstract = {Efficient conformance checking is a hot topic in the field of process mining. Much of the recent work focused on improving the scalability of alignment-based approaches to support the larger and more complex processes. This is needed because process mining is increasingly applied in areas where models and logs are “big”. Decomposition techniques are able to achieve significant performance gains by breaking down a conformance problem into smaller ones. Moreover, recent work showed that the alignment problem can be resolved in an iterative manner by alternating between aligning a set of decomposed subcomponents before merging the computed sub-alignments and recomposing subcomponents to fix merging issues. Despite experimental results showing the gain of applying recomposition in large scenarios, there is still a need for improving the merging step, where log traces can take numerous recomposition steps before reaching the required merging condition. This paper contributes by defining and structuring the recomposition step, and proposes strategies with significant performance improvement on synthetic and real-life datasets over both the state-of-the-art decomposed and monolithic approaches.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Efficient conformance checking is a hot topic in the field of process mining. Much of the recent work focused on improving the scalability of alignment-based approaches to support the larger and more complex processes. This is needed because process mining is increasingly applied in areas where models and logs are “big”. Decomposition techniques are able to achieve significant performance gains by breaking down a conformance problem into smaller ones. Moreover, recent work showed that the alignment problem can be resolved in an iterative manner by alternating between aligning a set of decomposed subcomponents before merging the computed sub-alignments and recomposing subcomponents to fix merging issues. Despite experimental results showing the gain of applying recomposition in large scenarios, there is still a need for improving the merging step, where log traces can take numerous recomposition steps before reaching the required merging condition. This paper contributes by defining and structuring the recomposition step, and proposes strategies with significant performance improvement on synthetic and real-life datasets over both the state-of-the-art decomposed and monolithic approaches.
20.
Schunselaar, D. M. M.; Verbeek, H. M. W.
Task Elimination may Actually Increase Throughput Time Technical Report
arXiv.org 2018, (arXiv identifier 1812.11793).
@techreport{Schunselaar18,
title = {Task Elimination may Actually Increase Throughput Time},
author = {D. M. M. Schunselaar and H. M. W. Verbeek},
url = {http://arxiv.org/abs/1812.11793},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
institution = {arXiv.org},
abstract = {The well-known Task Elimination redesign principle suggests to remove unnecessary tasks from a process to improve on time and cost. Although there seems to be a general consensus that removing work can only improve the throughput time of the process, this paper shows that this is not necessarily the case by providing an example that uses plain M/M/c activities. This paper also shows that the Task Automation and Parallelism redesign principles may also lead to longer throughput times. Finally, apart from these negative results, the paper also show under which assumption these redesign principles indeed can only improve the throughput time.},
note = {arXiv identifier 1812.11793},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
The well-known Task Elimination redesign principle suggests to remove unnecessary tasks from a process to improve on time and cost. Although there seems to be a general consensus that removing work can only improve the throughput time of the process, this paper shows that this is not necessarily the case by providing an example that uses plain M/M/c activities. This paper also shows that the Task Automation and Parallelism redesign principles may also lead to longer throughput times. Finally, apart from these negative results, the paper also show under which assumption these redesign principles indeed can only improve the throughput time.