In: Proceedings of Applications and Theory of Petri Nets 2004: 25th International Conference, ICATPN 2004, Bologna, Italy, June 21-25, 2004, pages 454-463. Volume 3099 of Lecture Notes in Computer Science / Cortadella, Reisig (Eds.) --- Springer-Verlag, September 2004.
Abstract: Process mining offers a way to distill process models from event logs originating from transactional systems in logistics, banking, e-business, health-care, etc. The algorithms used for process mining are complex and in practise large logs are needed to derive a high-quality process model. To support these efforts, the process mining tool EMiT has been built. EMiT is a tool that imports event logs using a standard XML format as input. Using an extended version of the alpha-algorithm it can discover the underlying process model and represent it in terms of a Petri net. This Petri net is then visualized by the program, automatically generating a "smart" layout of the model. To support the practical application of the tool, various adapters have been developed that allow for the translation of system-specific logs to the standard XML format. As a running example, we use an event log generated by the workflow management system Staffware.