By Marcello Leida, Basim Majeed (auth.), Philippe Cudre-Mauroux, Paolo Ceravolo, Dragan Gašević (eds.)
This publication constitutes the completely refereed court cases of the second one overseas Symposium on Data-Driven method Discovery and research held in Campione d'Italia, Italy, in June 2012.
The six revised complete papers have been conscientiously chosen from 17 submissions. to enhance the standard of the contributions the symposium fostered the dialogue in the course of the presentation, giving authors the chance to enhance their paintings extending the awarded effects. the chosen papers conceal themes spanning from theoretical concerns on the topic of approach illustration, discovery and research to functional and operational reports in approach discovery and analysis.
Read or Download Data-Driven Process Discovery and Analysis: Second IFIP WG 2.6, 2.12 International Symposium, SIMPDA 2012, Campione d’Italia, Italy, June 18-20, 2012, Revised Selected Papers PDF
Best international books
This quantity comprises the refereed complaints of the overseas convention on Abelian teams and Modules held on the Dublin Institute of know-how in eire, from August 10 till August 14, 1998. The assembly introduced jointly greater than 50 researchers and graduate scholars from 14 international locations world wide.
This ebook incorporates a selection of essays through top specialists associated with the exceptional features of the student in honour of whom it truly is released, Tullio Treves, who combines his educational heritage together with his useful studies of a negotiator of overseas treaties and a pass judgement on of a world tribunal.
- Renormalization Theory: Proceedings of the NATO Advanced Study Institute held at the International School of Mathematical Physics at the ‘Ettore Majorana’ Centre for Scientific Culture in Erice (Sicily) Italy, 17–31 August, 1975
- Phase Separation in Cuprate Superconductors: Proceedings of the second international workshop on “Phase Separation in Cuprate Superconductors” September 4–10, 1993, Cottbus, Germany
- Transcranial Magnetic Stimulation and Transcranial Direct Current Stimulation, Proceedings of the 2nd International Transcranial Magnetic Stimulation (TMS) and Transcranial Direct Current Stimulation (t: DCS) Symposium
- International standard problem isp36 : cora-w2 experiment on severe fuel damage for a russian type pwr
- Advances in Computational Intelligence: 11th International Work-Conference on Artificial Neural Networks, IWANN 2011, Torremolinos-Málaga, Spain, June 8-10, 2011, Proceedings, Part I
- Speech and Computer: 15th International Conference, SPECOM 2013, Pilsen, Czech Republic, September 1-5, 2013. Proceedings
Extra resources for Data-Driven Process Discovery and Analysis: Second IFIP WG 2.6, 2.12 International Symposium, SIMPDA 2012, Campione d’Italia, Italy, June 18-20, 2012, Revised Selected Papers
To explain our approach, it is useful to reﬂect on the four basic quality dimensions of the process model with respect to the observed behavior [1,2] (cf. Figure 1a). The replay fitness dimension quantiﬁes the extent to which the discovered model can accurately replay the cases recorded in the log. The precision dimension measures whether the discovered model prohibits behavior which is not seen in the event log. The generalization dimension assesses the extent to which the resulting model will be able to reproduce possible future, yet unseen, behavior of the process.
Al. . t. the unsound process model, whereby ‘badness’ indicates the ability of a solution to produce traces that lead to unsound behavior. The approach uses simulated annealing to simultaneously minimize all three dimensions. The edits applied to the process model are aimed to correct the model rather than to balance the ﬁve diﬀerent forces. Detecting deviations of a process model from the observed behavior has been researched, among others, by Adriansyah et. al. [2,4]. Given a process model and an event log, deviations are expressed in the form of skipped activities (activities that should be performed according to the model, but do not occur in the log) and inserted activities (activities that are not supposed to happen according to the model, but that occur in the log).
By incorporating this dimension, we can present a discovered model that maximizes the four dimensions while remaining aligned, as far as possible, with the intuitions and familiar notions modeled in a reference model. “able to replay event log” “not overfitting the log” “Occam’s razor” “not underfitting the log” (a) Diﬀerent quality dimensions for Process Model Discovery  (b) Incorporating similarity Fig. 1. M. Buijs et al. Figure 1b illustrates the eﬀects of introducing this additional dimension.
Data-Driven Process Discovery and Analysis: Second IFIP WG 2.6, 2.12 International Symposium, SIMPDA 2012, Campione d’Italia, Italy, June 18-20, 2012, Revised Selected Papers by Marcello Leida, Basim Majeed (auth.), Philippe Cudre-Mauroux, Paolo Ceravolo, Dragan Gašević (eds.)