TU/e Research Portal · 2014 · 85 citations · 12 references
BusinessChemical EngineeringBusiness Process ManagementData MiningProcess Systems EngineeringEvolutionary ComputationProcess ArchitectureProcess EngineeringProcess MiningProcess ModelingProcess OptimizationEvolutionary AlgorithmsProcess Architecture ModelingProcess DiscoveryProcess Model Evolution
Process mining automatically produces a process model while considering only an organization's records of its operational processes.Over the last decade, many process discovery techniques have been developed, and many authors have compared these techniques by focusing on the properties of the models produced.However, none of the current techniques guarantee to produce sound (i.e., syntactically correct) process models.Furthermore, none of the current techniques provide insights into the trade-offs between the different quality dimensions of process models.In this thesis we present the Evolutionary Tree Miner (ETM) framework.Its main feature is the guarantee that the discovered process models are sound.Another feature is that the ETM framework also incorporates all four well-known quality dimensions in process discovery (replay fitness, precision, generalization and simplicity).Additional quality metrics can be easily added to the Evolutionary Tree Miner.The Evolutionary Tree Miner framework is able to balance these different quality metrics and is able to produce (a collection of) process models that have a specific balance of these quality dimensions, as specified by the user.The third main feature of the Evolutionary Tree Miner is that it is easily extensible.In this thesis we discuss extensions for the discovery of a collection of process models with different quality trade-offs, the discovery of (a collection of) process models using a given process model, and the discovery of a configurable process model that describes multiple event-logs.The Evolutionary Tree Miner is implemented as a plug-in for the process mining toolkit ProM.The Evolutionary Tree Miner and all of its extensions are evaluated using both artificial and real-life data sets.
12
Replaying history on process models for conformance checking and performance analysis
Wil M. P. van der Aalst, Arya Adriansyah, Boudewijn F. van Dongen · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · 2012 · 726 citations
Business, Information Systems, Business Process Management +14