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

Master thesis topics

 

Supervision Univ.-Prof. Dr. Maria Leitner

Topic: Visualizations in business simulation games

Goal: Business simulation games/cyber exercises are a method to convey and test competencies and skills. The goal of the thesis to develop visualizations for cyber exercises that support organizers, observers and participants throughout the exercise.

Number of students: 1

Recommended requirements: Advanced programming skills.

Supervisor: Maria Leitner (maria.leitner@univie.ac.at)  

 

 

Bachelor theses topics


Supervision Univ.-Prof. Dr. Erich Schikuta

Topic: Predicting the disruptive effect of football passes using positional data

Goal: Design and implement an algorithm that predicts for a given pass in a football game how the defending players adapt their positions in reaction to the pass. Knowing how passes disrupt the defensive shape of a team is essential to rate the quality of a pass, as well as the quality of off-the-ball positioning and other performance indicators in football.

The available data (per game) consists of a list of passes and the XY positions of the players and the ball during the game. The algorithm can either be based on machine learning or on manually defined rules. Simple baselines to improve upon would be, for example, to assume that all players remain still while the pass rolls, or that all players move towards the target location of the pass. The procedure has to be implemented in Python and validated against real-world data in the end

Number of students: 1

Recommended requirements: Python (+ some affinity for football may be helpful.

Co-supervisor: Jonas Bischofberger (Department of Sport Science, University of Vienna)

Supervisor: Erich Schikuta (erich.schikuta@univie.ac.at)  

Resources:
Dick, U., & Brefeld, U. (2019). Learning to Rate Player Positioning in Soccer. Big data, 7(1), 71–82. doi.org/10.1089/big.2018.0054
Goes, F. R., Kempe, M., Meerhoff, L. A., & Lemmink, K. A. (2019). Not every pass can be an assist: a data-driven model to measure pass effectiveness in professional soccer matches. Big data, 7(1), 57-70.


Topic: Determining factors of success of football dribbles using positional data

Goal: Design and implement a model that predicts the success of dribbles in a football game based on meaningful features derived from positional data (e.g angle, number of opponents in vicinity, starting position, etc.). Such an algorithm leads to valuable performance indicators and insight into dribbles in football.

The available data per game consists of the XY positions of the players and the ball during the game as well as a list of dribbles. An important part of the task is to define and compute useful features from the positional data. Both machine learning and rule-based approaches are possible, but a simple, inspectable algorithm is generally preferred over a black-box model because it more easily leads to insights about the effect of the various features on successful dribbles. Also, some additional work may be needed to detect the dribbles in the game correctly. In the end, the implemented model has to be validated against real-world data.

Number of students: 1

Recommended requirements: Python (+ some affinity for football may be helpful.

Co-supervisor: Jonas Bischofberger (Department of Sport Science, University of Vienna)

Supervisor: Erich Schikuta (erich.schikuta@univie.ac.at)  

Resources:
Barbon Junior, S., Pinto, A., Barroso, J.V. et al. Sport action mining: Dribbling recognition in soccer. Multimed Tools Appl (2021). doi.org/10.1007/s11042-021-11784-1
Leal, K., Pinto, A., Torres, R., Elferink-Gemser, M.,  & Cunha, S. (2022). Characterization and analyses of dribbling actions in soccer: a novel definition and effectiveness of dribbles in the 2018 FIFA World Cup RussiaTM. Human Movement, 23(1), 10-17. doi.org/10.5114/hm.2021.104182
Van Roy, M., Robberechts, P., Decroos, T., & Davis, J. (2020). Valuing On-the-Ball Actions in Soccer: A Critical Comparison of xT and VAEP. Proceedings of the AAAI-20 Workshop on Artifical Intelligence in Team Sports, 1–8. https://ai-teamsports.weebly.com/


Topic: WineCellar As A Service

Goal: The goal of this project is to design and develop an information system for the administration and the management of a wine cellar.

Hereby a thorough market analysis and comparison of available competing systems (also old Bachlor theses) has to be done. Based on these results and customer interviews a list of requirements has to be defined. Specific emphasis has to be laid on the system architecture allowing for a service oriented / cloud-based approach. The functionality of the application to be developed has to cover all important workflows for wine cellar management, as wine inventory and cellar location management, wine purchase, personal wine information handling, wine web resource (information and purchase options) crawling, etc. Specific focus has to be laid on usability and responsive design.
 

Number of students: 1

Required Competences (mandatory technology stack): Electron, Typescript/Javascript, node.js, SQLite, Cloud service (e.g. u:cloud)

Supervisor: Erich Schikuta (erich.schikuta@univie.ac.at)  

Resources:
Old Bachelortheses on the same topic with different technology stack
Competing systems as CellarTracker, Vivino, VinoCell, Wine Notes, Kellermeister, Delectable, etc.


Supervision Univ.-Prof. Dr. Maria Leitner

Topic: Digital Twins in Industry 4.0

Goal: Automation is essential in many business processes in manufacturing and others. The goal of the thesis is to implement realistic digital twins for business process automation that can be managed by workflow systems.

Number of students: N

Recommended requirements: Advanced programming skills.

Supervisor: Maria Leitner (maria.leitner@univie.ac.at)  

 


Topic: Diversity management in cyber exercises 

Goal: The goal of the thesis is to assess how diversity management can be integrated into cyber security exercises. This includes the design and enactment of business processes but also the definition of key performance indicators. 

Number of students: 1

Recommended requirements: Advanced programming skills.

Supervisor: Maria Leitner (maria.leitner@univie.ac.at)  


Topic: Privacy in business processes 

Goal: The goal of the thesis is to develop an perspective-view and approach to privacy in business processes. The results are implemented in an available workflow system

Number of students: 1

Recommended requirements: Advanced programming skills.

Supervisor: Maria Leitner (maria.leitner@univie.ac.at)  


Topic: Privacy for end users 

Goal: The goal of the thesis is to develop a qualitative study on privacy for end users for a specific use case (e.g. health care apps).  .

Number of students: 1

Recommended requirements: Advanced programming skills.

Supervisor: Maria Leitner (maria.leitner@univie.ac.at)  


Topic: Systematic Literature Reviews

Goal: While systematic literature reviews have become a common method in academia, the software to support this method is still missing. The goal of the thesis is to develop a proof of concept that supports the process.

Number of students: 1

Recommended requirements: Advanced programming skills.

Kitchenham, B., Brereton, O. P., Budgen, D., Turner, M., Bailey, J., & Linkman, S. (2009). Systematic literature reviews in software engineering–a systematic literature review. Information and software technology, 51(1), 7-15.

Supervisor: Maria Leitner (maria.leitner@univie.ac.at)  


Supervision Marian Lux

Topic: Fuzzy miner visualization tool for process
models based on event logs as input data

Goal: Development of a visualization tool for process models based on the fuzzy miner.
Users can set different parameters (e.g., filters) for visualizing the process models. The
process model nodes and edges are visualized by using different colors, sizes and
thicknesses, based on their importance in the process model. Also synthetic start and end
nodes are planned to improve the usability for end users. The visualization tool should be
able to import the event logs from an SQL data base and as well from a CSV file.


Number of students: max. 2


Recommended requirements: The frontend for setting parameters and importing data is
implemented by using Python or a web framework. The process model visualization
(colors, synthetic start- and end nodes etc.) is implemented by using Graphviz or an
interactive web framework
The backend (algorithm and business logic for import service) is implemented in Python or
PostgreSQL


Günther, C. W., & Van Der Aalst, W. M. (2007, September). Fuzzy mining–adaptive
process simplification based on multi-perspective metrics. In International conference on
business process management (pp. 328-343). Springer, Berlin, Heidelberg.


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


Topic: Trimmed k-means clustering framework in
Python

Goal: Implementation of the Trimmed 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.
Inspiration from R implementation: https://rdrr.io/cran/trimcluster/man/trimkmeans.html)

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


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.


Number of Students: 2


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 Process Visualization of Correlation
Based Customer Journey Processes in the Tourism
Domain

Goal: Implementing an interactive data visualization tool 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 processes and findings
have to be visualized. There is a special focus on usability and interactive visualization
methods.
Recommended/Required Competences: Advanced programming skills.


Number of Students: 2

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