DSpace Repository

High-Level Activity Abstraction Using Low-Level Event Logs Generated From Workstation Application

Show simple item record

dc.contributor.advisor Dailey, Matthew
dc.contributor.author Datta, Indrajeet
dc.contributor.other Anutariya, Chutiporn
dc.contributor.other Dailey, Matthew
dc.contributor.other Laga, Nassim
dc.date.accessioned 2021-01-22T08:53:40Z
dc.date.available 2021-01-22T08:53:40Z
dc.date.issued 2021-05
dc.identifier.issn AIT
dc.identifier.uri http://www.cs.ait.ac.th/xmlui/handle/123456789/1002
dc.description 75 p. en_US
dc.description.abstract Event data collected by information systems as business processes execute in organizations can be used to discover or reverse engineer business process models through a technique called process mining. Process mining uses data mining algorithms applied to event log data to discover process models, identify trends and patterns, and find bottlenecks in business processes for the aims of understanding and optimization. Process mining tools rely on well-structured event logs to mine business processes. These events are usually generated by information systems (IS) during execution of the business processes. However, execution of business processes often requires the use of additional tools, which are external to the IS, such as document editors and communication tools (emails, instant messaging, etc). For instance, actors may use a document editor to write a project objectives in the project management business process. These tools, in this research study, are referred as workstation applications or desktop applications. To be able to mine these processes, it is important to collect event logs from these workstation applications. Additional event-logging programs are required to collect data from the workstation applications. One such event logger is developed by Orange S.A., which collects user activity from workstation computers. Although the data collected by the event logger is detailed and useful, it is very low-level and does not associate event data with higher level business activity as needed for process mining. The global objective of my research study is to propose a process mining approach that takes into account the activities achieved using workstation applications in order to provide a consistent and comprehensive view of the business processes. My goal is to make a use case of the event log data collected from workstation applications by event loggers such as the one developed by Orange, to be able to be used in process mining by developing an algorithm to abstract the low-level event data it generates to obtain high-level business process activities which then can be used to discover and analyze business process models through process mining. en_US
dc.description.sponsorship Orange S.A., AIT Fellowship. en_US
dc.language.iso en en_US
dc.publisher AIT en_US
dc.subject process-mining en_US
dc.subject event-abstraction en_US
dc.subject supervised-learning en_US
dc.subject classification en_US
dc.subject event-logs en_US
dc.title High-Level Activity Abstraction Using Low-Level Event Logs Generated From Workstation Application en_US
dc.type Research report en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account