In the research area Data Science, we focus on the development and application of data-driven methods for solving biological, medical, and technical problems. In close cooperation with our partners from research and industry, we develop algorithms for preprocessing and analyzing data using statistical methods and machine learning, as well as visualizing and interpreting the results. For example, within the project LeiVMed Online we develop a platform for benchmarking and visualizing data of treatments of patients in hospitals and developing prediction models for the outcome of treatments.
In many of our projects, we see the need for customized data processing pipelines due to the heterogeneity and complexity of data structures in real world processes and systems. We use applied statistics as well as numerous machine learning approaches, including black box methods (deep neural nets, random forests, gradient boosted trees, etc.) and white box methods (symbolic regression by genetic programming). We build our knowledge discovery pipelines on a variety of different frameworks, especially python scikit-learn, tensorflow, pytorch, MATLAB, and HeuristicLab.
|2021||Stefan Anlauf, Andreas Haghofer, Karl Dirnberger, Stephan M. Winkler:||Data-Based Prediction of Microbial Contamination in Herbs and Identification of Optimal Harvest Parameters||International Journal of Food Engineering (IJFE), DeGruyter|
|2019||Renate Haselgrübler, Peter Lanzerstorfer, Clemens Röhrl, Flora Stübl, Jonas Schurr, Bettina Schwarzinger, Clemens Schwarzinger, Mario Brameshuber, Stefan Wieser, Stephan M. Winkler, and Julian Weghuber:||Hypolipidemic effects of herbal extracts by reduction of adipocyte differentiation, intracellular neutral lipid content, lipolysis, fatty acid exchange and lipid droplet motility||Scientific Reports||View Article|
|2018||Stephan M. Winkler:||Evolutionary Computation and Symbolic Regression in Scientific Modeling||, Johannes Kepler University Linz, Computer Science, Habilitation Thesis|
|2016||Daniela Borgmann, Sandra Mayr, Helene Polin, Susanne Schaller, Viktoria Dorfer, Christian Gabriel, Stephan Winkler, and Jaroslaw Jacak:||Single Molecule Florescence Microscopy and Machine Learning for Rhesus D Antigen Classification||Scientific Reports 6||View Article|
In Austria there are currently around 573.000 to 645.000 people affected by Diabetes mellitus. This is about 8 to 9 percent of all Austrians. About 143.000 to 215.000 people do not know about their diabetes yet (2 to 3%). They have a higher risk for complications and long-term effects. Because of demographic developments and the rising prevalence of lifestyle related risk factors (overweight/obesity, physical inactivity, unfavourable nutrition, smoking, etc.) the number of diabetics and diabetes related diseases will rise further.
To counter these developments the consortium of Screening 2.0 aims at the development of a comprehensive concept of non-invasive diagnostic tools for individual, exhaustive, and user-friendly diabetes screening (diabetes as a first step) in combination with e-health applications. It involves a service innovation combined with a product innovation:
* Development of a printed qualitative diabetes-screening strip used in a trend analysis for early detection of diabetes
* Development of a comprehensive communication concept
Test strips and screening methods already exist in various ways. However, these are not printed but mostly dipped or coated. Through the development of the printing process in combination with the development of the suitable print varnish production cost and used resources should be reduced significantly. Furthermore the strip must be designed in a way to be easily included in a postal mailing which is the prerequisite for the service innovation.
To implement early detection successfully into the existing health system an innovative service must be developed. Current communication- and supply channels need to be considered while it needs to be carried out nationwide. Screening enables an addition to current supply and communication. Therefore the communication cycle can be closed for the first time during the screening process and not – as before – after the analysis of prescribed medication (therapy) through health insurances.
DI(FH) Dr. Viktoria Dorfer MSc
DI(FH) Viktoria Dorfer MSc
Susanne Schaller MMSc
Prof. (FH) DI Dr. Stephan Winkler
2015 - 2017
Research Center Hagenberg
University of Applied Sciences, Upper Austria, Hagenberg Campus
Software technology and application