Open Topics


The Workflow Systems and Technologies Group offers topics for bachelor and master theses as well as Master Praktikum. The following list contains a number of current suggestions for topics.

To discuss one of those or any other topic in this research field, please contact the particulary named supervisor.

» Jump to Bachelor thesis topics

» Jump to Master thesis topics

This list will be updated continuously!

Master thesis topics

 

At the moment there are no open Master thesis topics.

Bachelor theses topics


Supervision Univ.-Prof. Dr. Erich Schikuta

At the moment there are no open topics.


Supervision Marian Lux

Topic: Kernel k-means clustering framework in Python

Goal: Implementation of the Kernel k-means clustering algorithm for multiple dimensions
(including as well one dimensional data) in Python. The results are visualized in plots and

measured with quality metrics, (e.g., Silhouette Coefficient). The algorithm can be used
like a framework.

Recommended requirements: Implementation in Python.

Literature:
Dhillon, I. S., Guan, Y., & Kulis, B. (2004). Kernel k-means: spectral clustering and normalized cuts. In Proceedings of the tenth acm sigkdd international conference on knowledge discovery and data mining (pp. 551–556).

https://sites.google.com/site/dataclusteringalgorithms/kernel-k-means-clustering-algorithm

Supervisor: Marian LUX ((marian.lux@univie.ac.at))


Topic: Interactive Findings Visualization of Correlation Based Customer Journey Processes in the Tourism Domain

Goal: Implementing an interactive data visualization app (for iOS or Android or Desktop) which shows processes and findings based on correlations. Already trained models by using machine learning technologies (tourism domain and synthetic) are provided. The trained models contain correlations based on visited pages from a touristic web application and environmental data (weather) for a given period of time and location. The trained models have to be used for discovering process models and for showing findings by filtering weights, combining different features and post processing the weights and features (e.g., calculating probabilities). These discovered findings have to be visualized. There is a special focus on usability and interactive visualization methods.

Recommended/Required Competences: Advanced programming skills.

Supervisor: Marian LUX ((marian.lux@univie.ac.at))


Topic: Process Mining visualization with node and edge filters in Python

Goal: Implementation of a graphical user interface for importing event logs, mining and visualizing process models by using different algorithms (like alpha miner, heuristic miner, inductive miner, fuzzy miner) and metrics for filtering nodes and edges on mined process models. Mined process models can be exported as images.

This work consists of different stages:

  • defining criteria and choosing the best framework for the user interface
  • defining an open source architecture (capable to switch process mining algorithms and metrics for filtering)
  • the development of the application with unit tests
  • distribution and dissemination (GitHub and PyPi)

Recommended requirements: Implementation in Python.

Related Literature:

Van Der Aalst, Wil. Process mining: discovery, conformance and enhancement of business processes. Vol. 2. Heidelberg: Springer, 2011.

Lux, Marian, Stefanie Rinderle-Ma, and Andrei Preda. "Assessing the quality of search process models." Business Process Management: 16th International Conference, BPM 2018, Sydney, NSW, Australia, September 9–14, 2018, Proceedings 16. Springer International Publishing, 2018.

Supervisor: Marian LUX - marian.lux@univie.ac.at


Topic: Data Pre-Processing of Event-Logs and Environmental Weather Data

Goal: Implementation of a PostgreSQL data base for pre-processing event logs together with environmental data (e.g., OpenWeather) as basis for using machine learning technologies to train models and to use process mining technologies. The environmental data are time series data which have to be validated (e.g., missing data intervals, out of range values, wrong timestamps, units of measurements, etc.), enriched and merged (e.g, form different weather data providers and with event logs) by using different researched approches.

Recommended/Required Competences: Advanced database knowledge. Experience with PostgreSQL functions or Python.

Supervisor: Marian LUX (marian.lux@univie.ac.at)