Äriplaani protsessi hälbe kindlakstegemine Declarega
| dc.contributor.advisor | Maggi, Fabrizio Maria | |
| dc.contributor.advisor | Milani, Fredrik | |
| dc.contributor.author | Jarabek, Juraj | |
| dc.date.accessioned | 2017-04-26T07:12:28Z | |
| dc.date.available | 2017-04-26T07:12:28Z | |
| dc.date.issued | 2016 | |
| dc.description.abstract | See töö tutvustab äriprotsessi hälbe kaevandust, mis kuulub protsessi\n\rkaevandamise gruppi ja annab ülevaate mitme hälbivaga kaevandamise lähenemisviisidest.\n\rKeskendutakse ka hälbiva kaevandamise kasutamise diskrimineerivatele mustritele, mis kuulub kontserni järjestikumustrite kaevandustehnoloogiatega samasse gruppi. Selles töös vaadeldakse uute diskrimineerivate mustrite kaevandamise algoritmi, mis põhineb Declare keelel. Rakendati plug-in lähenemisviisi protsessi kaevandamise näitajaga ProMile. Kirjeldatakse kogu protsessi kuni klassifitseerimiseni. Töö lõpus hinnati algoritmi tõhusust ja eksperimente erinevates variatsioonides. | |
| dc.description.abstract | This thesis introduces business process deviance mining, which belongs to the group\n\rof process mining, and gives an overview on multiple deviance mining approaches. After that\n\rwe focus on deviance mining using discriminative patterns, which belongs to the group of\n\rsequential patterns mining techniques. In this work we propose new discriminative pattern\n\rmining algorithm based on the Declare language. We implemented the approach as a plug-in\n\rof the Process Mining tool ProM. We describe the whole proposed approach from the labelling\n\rof the event logs until building the classifier and classifying the test logs. In the end of the\n\rthesis we evaluate the effectiveness of our proposed algorithm on variety of experiments on\n\revent logs. | |
| dc.identifier.uri | http://hdl.handle.net/10062/56188 | |
| dc.language.iso | eng | |
| dc.title | Äriplaani protsessi hälbe kindlakstegemine Declarega | |
| dc.title.alternative | Exploring Business Process Deviance with Declare | |
| dc.type | Thesis |
Files
Original bundle
1 - 1 of 1