Fond bitcoin pour l'amélioration du site: 1memzGeKS7CB3ECNkzSn2qHwxU6NZoJ8o
  Dogecoin (tips/pourboires): DCLoo9Dd4qECqpMLurdgGnaoqbftj16Nvp

Home | Publier un mémoire | Une page au hasard


Comparison of process mining techniques application to flexible and unstructured processes

( Télécharger le fichier original )
Université Paris est créteil - Master 2 2014

précédent sommaire

Bitcoin is a swarm of cyber hornets serving the goddess of wisdom, feeding on the fire of truth, exponentially growing ever smarter, faster, and stronger behind a wall of encrypted energy

Conclusion and Future Works

The work presented in this thesis is motivated by the omnipresence of event logs and the relevance of good processes models. An increasing number of processes and systems are being monitored. For example, any enterprise information system is recording business events, moreover also professional and consumer systems are recording events.

Process discovery aims to reconstruct process models from event logs. It is a collection of tools and techniques used to define, map and analyze an organization's existing business processes. Along with business process modeling, it is widely viewed as critical for successful Business Process Management (BPM) initiatives, in fact, it is often an initial step in BPM. The basic idea is to extract knowledge from event logs recorded by an information system. Without these techniques it is difficult to obtain a valuable information. So, process models are readily available and their importance is increasing. Moreover, process models are used for all kinds of analysis (e.g. simulation). The availability of event logs and the need for high-quality process models has been the starting point of this thesis.

It has been noticed in many different works in literature that process mining techniques can deliver valuable, factual insights into how processes are being executed in real life. This makes them especially important for analyzing flexible environments, where actors and even process owners are often unaware of how exactly the process is structured. In such domains, however, process mining algorithms tend to generate complex, unstructured process models, which are hard to understand, and thus of limited value. One reason for these problems is diversity, i.e. processes which can generate a set of cases that are structured very differently. However, there are many process mining algorithms with different theoretical foundations and aims, which leads to different mining results. Existing techniques perform well on structured processes, but still have problems discovering and visualizing less structured ones. In reality, there is a lot of diversity leading to complex models that are difficult to interpret.


Conclusion and Future Works

Trace clustering is one of very promising technique to best mining results. Trace clustering approach aims at splitting the event log into homogeneous subsets and for each subset a process model is created.

In this thesis, we have introduced an approach for traces clustering in order get better mined models. We have presented a generic methodology for trace clustering, which can effectively resolve diversity-related problems, by dividing the log into smaller, more homogeneous subsets of traces. We were inspired by the work of song et al. [32] who have introduced the concept of trace profiles, which are a suitable means for characterizing and comparing traces.

Unlike their work, Trace profile is composed only of binary values. Traces are characterized by profiles (vectors) composed of n items : Profile_V ectori = (a1, a2, ..., an).

We proposed a new function for measuring the distance between two cases and to calculate new clusters. As it is an "exclusive OR", we use XOR to calculate the distance between two points (represented by their profiles). It only returns a "true" value (1) if the two values are exclusive, i.e. they are both different. So, applying XOR between two profiles provides a serie of 1 for each two different items of the traces profiles. This serves as a mean to calculate the difference degree of two profiles, and consequently, to collect similar traces together.

To build new clusters, we use the logical AND, which is an operator on two logical values that produces a value of true if and only if both of its operands are true. We apply the logical AND on the values of two traces profiles among all the traces in the same cluster to build a new cluster center.

We have demonstrated the applicability of our approach with a real process logs. We have implemented it with JAVA, experimented and the obtained results were compared with an existing approach. The comparison showed that we obtained improvement, especially, in the fitness metric.

We conclude this section, and therefore this thesis, with the expectation that trace clustering, in the near future, will play an important role in the improvement of the results of any process mining algorithm. As the traces clustering techniques operate on event logs, using them will be very benefit to construct and build more homogenous set of traces, and therefore, more precise process models. So, traces clustering is a promising approach which can be used to improve the results of any process mining algorithm.

Future work will focus on:

· Implementing our approach in the context of the ProM framework,

· Finding a solution for loops.



[1] D.and Agrawal, R.and Gunopulos and F. Leymann. Mining process models from workflow logs. In Schek, H., Saltor, F., Ramos, I., and Alonso, G., editors, Proceedings of the 6th International Conference on Extending Database Technology (EDBT'98),, 1377 of Lecture Notes in Computer Science,:469-483., 1998.

[2] A. K. Alves de Medeiros, W. M. P. van Dongen, B. F.and van der Aalst, and A. J. M. M. Weijters. Process mining: Extending the alpha-algorithm to mine short loops. BETA working paper series 113, Eindhoven University of Technology, 2004.

[3] A.Karla: A.Medeiros. Genetic process mining. phd thesis, University Press Facilities, Eindhoven.

[4] W. A.Rozinat, van der Aalst. Decision mining in prom. In Dustdar, S., Fiadeiro, J., Sheth, A., eds.: BPM 2006.of Lecture Notes in Computer Science., Springer-Verlag, ,.

[5] J. Bae, L. Liu, J.Caverlee, L.J. Zhan, and H. Bae. Development of distance measures for process mining, discovery, and integration. International Journal of Web Services Research,, 4 ( 4 ), 2007.

[6] B.Dongen. Process mining and verification. Phd thesis, by University Press Facilities, Eindhoven, 2007.

[7] J. Cook and A. Wolf. Discovering models of software processes from event-based data. ACM Transactions on Software Engineering and Methodology,, 7(3):215-249., 1998.

[8] J. Cortadella, Lavagno L. Kishinevsky, M., and A.: Yakovlev. Deriving petri nets from finite transition systems. IEEE Transactions on Computers,, 47(8) 1998.



[9] R. Dijkman, M. Dumas, B.van Dongen, R. Kaarik, and J.Mendling. Similarity of business process models: Metrics and evaluation. Information Systems,, 36(2), 2011.

[10] Zacarias M. Malheiros M. Ferreira P. Ferreira, D. Approaching process mining with sequence clustering: Experiments and findings. In: Proceedings of the 5th International Conference on Business Process Management (BPM 2007)., 4714:360-374, 2007.

[11] J. Gama and J. Carmona. A fresh look at precision in process conformance. In Business Process Management, Springer Berlin / Heidelberg,:211 - 226, 2010.

[12] Guzzo A. Pontieri L. Sacca D. Greco, G. Mining expressive process models by clustering workflow traces. In Dai, H., Srikant, R., Zhang, C., eds.: PAKDD., Springer, 3056:52-62, 2004.

[13] M. Hammer and J. Champy. Reengineering the corporation: A manifesto for business revolution. Harper Business, New York, NY, USA,, 1993.

[14] Boudewijn F. van Dongen H.M.W. Verbeek, Joos C.A.M. Buijs and Wil M.P. van der Aalst. Xes, xesame, and prom 6. P. Soffer and E. Proper (Eds.): CAiSE Forum 2010,Springer-Verlag Berlin Heidelberg, 72:60-75, 2010.

[15] W.M.P. van der Aalst M. Dumas and A.H.M. ter Hofstede. Process-aware information systems: Bridging people and software through process technology. Wiley and Sons,.

[16] Mirjam Minor, Alexander Tartakovski, and Ralph Bergmann. Representation and structure-based similarity assessment for agile workflows. In Case-Based Reasoning Research and Development,.

[17] Tadao Murata. Petri nets: Properties, analysis and applications. Proceedings of the IEEE,, 77 ( 4 ):541 - 580, 1989.

[18] J. NAKATUMBA and W.M.P. VAN DER AALST. Analyzing resource behavior using process mining. In Alonso, G., Dadam, P., Rosemann, M., eds.: International Conference on Business Process Management,of Lecture Notes in Computer Science., Springer-Verlag.

[19] N.C.Russell. Foundations of process-aware information systems. PhD thesis, Faculty of Information Technology, Queensland University of Technology Brisbane, Australia,, 2007.

[20] M. NETJES and H.A.. REIJERS. Supporting the bpm life-cycle with filenet.



[21] Wil M. P, van der Aalst, Ton A. J. M. M. Weijters, and Ana Karla Alves de Medeiros. Process mining with the heuristics miner-algorithm. BETA Working Paper Series, WP 166 , Eindhoven University of Technology, Eindhoven.

[22] S.S. Pinter and M. Golani. Discovering workflow models from activities' lifespans. comput. Ind.,, 2004.

[23] Reijers, Weijters H.A., Dongen A.J.M.M., M edeiros B.F.V., A.K.A.D., M. Song, Ver-beek, and H.M.W. Business process mining: An industrial application. information systems,. Wiley and Sons,.

[24] M. Dumas Remco M. Dijkman and C. Ouyang. Semantics and analysis of business process models in bpmn. Information and Soft-ware Technology, 50(12):1281-1294, 2008.

[25] S. Rindele and W. Van Dar Alaast. Life-cycle support for staff assignment rules in process-aware information systems. Department of Mathematics and Computing Science, Eindhoven University of Technology,.

[26] S. Rinderle, M. Reichert, and P. Dadam. Evaluation of correctness criteria for dynamic workflow changes. In Aalst et al. [AHW03],.

[27] A. Rozinat, A.K. Alves de Medeiros, C.W. Gunther, A.J.M.M. Weijters, and W.M.P. van der Aalst. Towards an evaluation framework for process mining algorithms. IEEE Transactions on Knowledge and Data Engineering,, 2007.

[28] A. Rozinat, A.K. Alves de Medeiros, Christian W., Gunther Ton A, J. M. M. Weijters, and Wil M. P. van der Aalst. Towards an evaluation framework for process mining algorithms. BPM Center Report BPM-07-06,.

[29] A. Rozinat and W.M.P. van der Aalst. Conformance checking of processes based on monitoring real behavior,. Information Systems,, 2008.

[30] Wichian P. Sawitree W., Parham P. Process mining a-algorithm as a tool (a case study of student registration). IEEE, pages 4673-2317, 2012.

[31] G. Schimm. Process miner - a tool for mining process schemes from event-based data. In S. Flesca and G. Ianni, editors, Proceedings of the 8th European Conference on Artificial Intelligence (JELIA),, 2002.

[32] M. Song, C.W. Gunther, and W.M.P. van der Aalst. Trace clustering in process mining. Eindhoven University of Technology P.O.Box 513, NL-5600 MB, Eindhoven, The Netherlands.



[33] PHD DEREK MIERS STEPHEN A. WHITE. BPMN Modeling and Reference Guide: Understanding and Using BPMN. Published by Future Strategies Inc., Book Division, 2010.

[34] MacLennan J. Tang, Z. 8. in: Data mining with sql server 2005. Wiley Publishing, Inc.,, page 209-227, 2005.

[35] van der Aalst, Weijters W. M. P., A. J. M. M., and L Maruster. Workflow mining: Discovering process models from event logs. IEEE Transactions on Knowledge and Data Engineering,, 16(9):1128-1142, 2004.

[36] de Medeiros A.A. Weijters A.: van der Aalst, W. Genetic process mining an experimental evaluation. Data Mining and Knowledge Discovery,., 14(2), 2007.

[37] REIJERS H.A. VAN DER AALST, W.M.P. and M.: SONG. Discovering social networks from event logs. Comput. Supported Coop. Work,.

[38] V.and van Dongen B. F.and Kindler E. van der Aalst, W. M. P.and Rubin and C. W.: Gunther. Process mining: A two-step approach using transition systems and regions. BPM Center Report,.

[39] W. M. P. van der Aalst and A. H. M. ter Hofstede. Yawl: Yet another workflow language. information systems. 30(4):245-275, 2005.

[40] W.M.P. van der Aalst. The application of petri nets to workflow management. Department of Mathematics and Computing Science, Eindhoven University of Technology,.

[41] W.M.P. van der Aalst. Process mining discovery, conformance and enhancement of business processes. Department of Mathematics and Computing Science,Eindhoven University of Technology,.

[42] W.M.P. van der Aalst. Woflan: A petri-net-based workflow analyzer. Department of Mathematics and Computing Science,Eindhoven University of Technology,.

[43] W.M.P. van der Aalst. Verification of workflow nets,. In P. Azema and G. Balbo, editors, Application and Theory of Petri Nets, 1248 of Lecture Notes in Computer Science:407-426, 1997.

[44] W.M.P. van der Aalst, A. Adriansyah, and B.F. van Dongen. Causal nets: a modeling language tailored towards process discovery. In Proceedings of the 22nd International Conference on Concurrency Theory, CONCUR'11,Springer-Verlag., 2011.



[45] W.M.P. van der Aalst, V. Rubin, H. Verbeek, B.F. van Dongen, E. Kindler, and C.W.Gunther. Process mining: a two-step approach to balance between underfitting and over-fitting. Software and Systems Modeling, 2(16) 2009.

[46] W.M.P. van der Aalst and K.M. van Hee. Workflow management: Models, methods, and systems. MIT press, Cambridge, MA,, 2002.

[47] de Medeiros A.A. Verbeek H. Weijters A. van der Aalst W. van Dongen, B. The prom framework: A new era in process mining tool support. In Ciardo, G., Darondeau, P., eds.: Application and Theory of Petri Nets 2005. Lecture Notes in Computer Science., Springer-Verlag, Berlin, 3536:444-454, 2005.

[48] van der Aalst W. van Dongen, B. A meta model for process mining data. In Casto, J., Teniente, E., eds.: Proceedings of the CAiSE'05 Workshops (EMOI-INTEROP Workshop). FEUP, Porto, Portugal,, page 309-320, 2005.

[49] H.M.W. Verbeek. Verification of wf-nets. phd thesis, eindhoven university of technology, eindhoven, the netherlands,. 2004.

[50] van der Aalst W. de Medeiros A.A. Weijters, A. Process mining with the heuristics miner algorithm. BETA Working Paper Series WP 166, Eindhoven University of Technology, 2006.

[51] L. Wen, J. Wang, W.M.P. van der Aalst, Z. Wang, , and J. Sun. A novel approach for process mining based on event types. BETA Working Paper Series, Eindhoven University of Technology, Eindhoven, page 118, 2004.

[52] L. Wen, J. Wang, W.M.P. van der Aalst, Z. Wang, , and J. Sun. Mining process models with non-free-choice constructs. Data Mining and Knowledge Discovery,, 2007.

[53] I. H. Witten and E. Frank. Data mining: practical machine learning tools and techniques with java implementations.,. Morgan Kaufmann Publishers Inc.,San Francisco, CA, USA., 2000.

[54] M. Zerari. Une approche pour l'amélioration de la flexibilité des processus métier basée sur les techniques du process mining. Thèse, Faculté des Sciences et de l'ingénieur, université de Constantine, Algérie, 2012.

[55] R. Zurawski. Petri nets and industrial applications: A tutorial. IEEE Trans-actions on Industrial Electronics,, 41 ( 6 ):567 - 583, 1994.

précédent sommaire

Bitcoin is a swarm of cyber hornets serving the goddess of wisdom, feeding on the fire of truth, exponentially growing ever smarter, faster, and stronger behind a wall of encrypted energy

"L'imagination est plus importante que le savoir"   Albert Einstein