University of Twente Student Theses

Login

Tracing Data Utility for Noise Adding Plugins in Process Mining

Samy, Omar (2023) Tracing Data Utility for Noise Adding Plugins in Process Mining.

[img] PDF
10MB
Abstract:This bachelor thesis project explores the implementation of simulation, anonymization techniques, and process mining tools in the healthcare sector for event log analysis. The main objective is to gain insights into the Privacy-Utility Trade-off by evaluating the impact of anonymization on the utility of simulated event logs. The simulation part utilizes discrete event simulation to model a radiology department using AnyLogic. Afterwards an event log with synthetic patient data is extracted from the simulated model which will then goes through an anonymization process. For anonymization, the k-anonymity technique in the ARX tool is applied to the event logs, ensuring the protection of private patient data while balancing data utility. Process mining, specifically process discovery using ProM, is then used for further analysis to compare the unanonymized and anonymized event logs. This analysis discover insights and assesses whether data utility was impacted by anonymization. The results in ProM reveal a loss of utility in the anonymized log, due to the presence of unnecessary paths. This finding highlights the importance of using process mining for analysis of sensitive healthcare data and proves that process mining is an effective approach in understanding event log utility and uncovering hidden insights. Insights gained from process mining contribute to more informed decisions and overall improved patient care.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Creative Technology BSc (50447)
Link to this item:https://purl.utwente.nl/essays/96559
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page