FH-Prof. DI Dr. techn.
Stefan Schrunner
- Professor for Artificial Intelligence
Kontakt:
+43 (0)5 90500-2251
s.schrunner[at]fh-kaernten[dot]at
Standort:
Europastraße 4
9524 Villach
| Lecture | Type | SPPS | ECTS-Credits | Course number |
|---|---|---|---|---|
| Artificial Neural Networks and Deep Learning (I) | ILV | 3,5 | 5,0 | M2.08760.11.131 |
| Master Thesis | MT | 0,5 | 20,0 | M2.08760.11.211 |
| Project (II) Frameworks and Concept Study | ILV | 3,5 | 5,0 | M2.08760.11.091 |
| Lecture | Type | SPPS | ECTS-Credits | Course number |
|---|---|---|---|---|
| Advanced Topics | ILV | 3,5 | 5,0 | M2.08760.11.151 |
| Artificial Neural Networks and Deep Learning (II) | ILV | 3,5 | 5,0 | M2.08760.11.141 |
| Information& Probability Theory | ILV | 3,5 | 5,0 | M2.08760.11.011 |
| Project (III) Practical Implementation | PA | 3,5 | 5,0 | M2.08760.11.101 |
| Lecture | Type | SPPS | ECTS-Credits | Course number |
|---|---|---|---|---|
| Information& Probability Theory | ILV | 3,5 | 5,0 | M2.08760.11.011 |
| Titel | Autor | Jahr |
|---|---|---|
| Advancing Alveolar Ridge Augmentation | Niloofar Rajabi | 2026 |
| MODELING HOLIDAY EFFECTS FOR DAILY FORECASTING: MULTI-DOMAIN WINDOW-BASED EVALUATION | Saksham Pratap Shah | 2026 |
| THE IMPACT OF SEASONAL VEGETATION ON GAUSSIAN SLIDING WINDOWS REGRESSION FOR HYDROLOGICAL INFERENCE | Farid Musayev | 2026 |
| Automated Detection and Counting of Dislocations in Scanning Electron Microscopy Images Using Classical and Machine Learning-Based Image Segmentation | Eva Sarah Schwarzl | 2025 |
| Machine learning approaches for anomaly detection in the energy market. | Priscilla Zannier | 2025 |
| Titel | Autor | Jahr |
|---|---|---|
| Advancing Alveolar Ridge Augmentation | Niloofar Rajabi | 2026 |
| MODELING HOLIDAY EFFECTS FOR DAILY FORECASTING: MULTI-DOMAIN WINDOW-BASED EVALUATION | Saksham Pratap Shah | 2026 |
| THE IMPACT OF SEASONAL VEGETATION ON GAUSSIAN SLIDING WINDOWS REGRESSION FOR HYDROLOGICAL INFERENCE | Farid Musayev | 2026 |
| Titel | Autor | Jahr |
|---|---|---|
| Automated Detection and Counting of Dislocations in Scanning Electron Microscopy Images Using Classical and Machine Learning-Based Image Segmentation | Eva Sarah Schwarzl | 2025 |
| Machine learning approaches for anomaly detection in the energy market. | Priscilla Zannier | 2025 |
| Titel | Autor | Jahr |
|---|
| Run-Time | April/2026 - December/2028 |
| Project management | |
| Project staff | |
| Forschungsschwerpunkt | Robotik |
| Studiengang | |
| Forschungsprogramm | Transfer.F&E.EFRE|JTF |
| Förderinstitution/Auftraggeber |
The Ready4Humanoids project is establishing an innovation hub for humanoid robot systems in Carinthia. The aim is to deploy humanoid robots in real-world production and service environments, thereby strengthening the competitiveness of regional businesses. The consortium comprises FH Carinthia (ADMiRE, Applied Data Science), JOANNEUM RESEARCH (Robotics, Digital Twin Lab) and Fraunhofer Austria (KI4Life), bringing together expertise in robotics, AI, digitalisation, sensor technology and human-robot interaction. Using state-of-the-art infrastructure, ranging from collaborative robots and mobile platforms to digital twin environments, novel solutions are being researched and demonstrated. The focus is on application areas such as assembly, logistics, quality assurance, internal transport, and service and tourism tasks. In doing so, the project addresses key challenges such as the shortage of skilled workers, rising labour costs and the automation of repetitive tasks. Through close cooperation between research and industry, Carinthia is being positioned as a pioneering region for humanoid robotics, bridging the gap between AI-based research and real-world operational applications.
- Fraunhofer Austria Research GmbH (Lead Partner)
- FH Joanneum
- KWF - Kärntner Wirtschaftsförderungsfonds (Fördergeber/Auftraggeber)
| Run-Time | September/2025 - December/2025 |
| Project management | |
| Project staff | |
| Forschungsschwerpunkt | Gesundheitswissenschaften |
| Studiengang | |
| Forschungsprogramm | Wirtschaftliche Forschung |
| Förderinstitution/Auftraggeber |
The aim is to support MOVEVO in the development of a data-driven and AI-powered system for the personalization of health promotion. Central to this is the design and prototypical preparation of a scalable “Adaptive Health Engine” that identifies user profiles, dynamically delivers personalized content, and positively influences health behavior over the long term.
- MOVEVO Technologies GmbH (Fördergeber/Auftraggeber)
| Run-Time | April/2026 - December/2028 |
| Project management | |
| Project staff | |
| Forschungsschwerpunkt | Robotik |
| Studiengang | |
| Forschungsprogramm | Transfer.F&E.EFRE|JTF |
| Förderinstitution/Auftraggeber |
The Ready4Humanoids project is establishing an innovation hub for humanoid robot systems in Carinthia. The aim is to deploy humanoid robots in real-world production and service environments, thereby strengthening the competitiveness of regional businesses. The consortium comprises FH Carinthia (ADMiRE, Applied Data Science), JOANNEUM RESEARCH (Robotics, Digital Twin Lab) and Fraunhofer Austria (KI4Life), bringing together expertise in robotics, AI, digitalisation, sensor technology and human-robot interaction. Using state-of-the-art infrastructure, ranging from collaborative robots and mobile platforms to digital twin environments, novel solutions are being researched and demonstrated. The focus is on application areas such as assembly, logistics, quality assurance, internal transport, and service and tourism tasks. In doing so, the project addresses key challenges such as the shortage of skilled workers, rising labour costs and the automation of repetitive tasks. Through close cooperation between research and industry, Carinthia is being positioned as a pioneering region for humanoid robotics, bridging the gap between AI-based research and real-world operational applications.
- Fraunhofer Austria Research GmbH (Lead Partner)
- FH Joanneum
- KWF - Kärntner Wirtschaftsförderungsfonds (Fördergeber/Auftraggeber)
| Run-Time | April/2026 - December/2028 |
| Project management | |
| Project staff | |
| Forschungsschwerpunkt | Robotik |
| Studiengang | |
| Forschungsprogramm | Transfer.F&E.EFRE|JTF |
| Förderinstitution/Auftraggeber |
The Ready4Humanoids project is establishing an innovation hub for humanoid robot systems in Carinthia. The aim is to deploy humanoid robots in real-world production and service environments, thereby strengthening the competitiveness of regional businesses. The consortium comprises FH Carinthia (ADMiRE, Applied Data Science), JOANNEUM RESEARCH (Robotics, Digital Twin Lab) and Fraunhofer Austria (KI4Life), bringing together expertise in robotics, AI, digitalisation, sensor technology and human-robot interaction. Using state-of-the-art infrastructure, ranging from collaborative robots and mobile platforms to digital twin environments, novel solutions are being researched and demonstrated. The focus is on application areas such as assembly, logistics, quality assurance, internal transport, and service and tourism tasks. In doing so, the project addresses key challenges such as the shortage of skilled workers, rising labour costs and the automation of repetitive tasks. Through close cooperation between research and industry, Carinthia is being positioned as a pioneering region for humanoid robotics, bridging the gap between AI-based research and real-world operational applications.
- Fraunhofer Austria Research GmbH (Lead Partner)
- FH Joanneum
- KWF - Kärntner Wirtschaftsförderungsfonds (Fördergeber/Auftraggeber)
| Run-Time | April/2026 - December/2028 |
| Project management | |
| Project staff | |
| Forschungsschwerpunkt | Robotik |
| Studiengang | |
| Forschungsprogramm | Transfer.F&E.EFRE|JTF |
| Förderinstitution/Auftraggeber |
The Ready4Humanoids project is establishing an innovation hub for humanoid robot systems in Carinthia. The aim is to deploy humanoid robots in real-world production and service environments, thereby strengthening the competitiveness of regional businesses. The consortium comprises FH Carinthia (ADMiRE, Applied Data Science), JOANNEUM RESEARCH (Robotics, Digital Twin Lab) and Fraunhofer Austria (KI4Life), bringing together expertise in robotics, AI, digitalisation, sensor technology and human-robot interaction. Using state-of-the-art infrastructure, ranging from collaborative robots and mobile platforms to digital twin environments, novel solutions are being researched and demonstrated. The focus is on application areas such as assembly, logistics, quality assurance, internal transport, and service and tourism tasks. In doing so, the project addresses key challenges such as the shortage of skilled workers, rising labour costs and the automation of repetitive tasks. Through close cooperation between research and industry, Carinthia is being positioned as a pioneering region for humanoid robotics, bridging the gap between AI-based research and real-world operational applications.
- Fraunhofer Austria Research GmbH (Lead Partner)
- FH Joanneum
- KWF - Kärntner Wirtschaftsförderungsfonds (Fördergeber/Auftraggeber)
| Run-Time | September/2025 - December/2025 |
| Project management | |
| Project staff | |
| Forschungsschwerpunkt | Gesundheitswissenschaften |
| Studiengang | |
| Forschungsprogramm | Wirtschaftliche Forschung |
| Förderinstitution/Auftraggeber |
The aim is to support MOVEVO in the development of a data-driven and AI-powered system for the personalization of health promotion. Central to this is the design and prototypical preparation of a scalable “Adaptive Health Engine” that identifies user profiles, dynamically delivers personalized content, and positively influences health behavior over the long term.
- MOVEVO Technologies GmbH (Fördergeber/Auftraggeber)
| Articles in Journals | ||
|---|---|---|
| Title | Author | Year |
| Learning From Limited Temporal Data: Dynamically Sparse Historical Functional Linear Models With Applications to Earth Science Environmetrics, 36(4) | Janssen, J., Meng, S., Haris, A., Schrunner, S., Cao, J., Welch, W., Kunz, N., Ameli, A. | 2025 |
| A Gaussian sliding windows regression model for hydrological inference Journal of the Royal Statistical Society, Series C: Applied Statistics | Schrunner, S., Pishrobat, P., Janssen, J., Jenul, A., Cao, J., Ameli, A., Welch, W. | 2025 |
| Novel Ensemble Feature Selection Techniques Applied to High-Grade Gastroenteropancreatic Neuroendocrine Neoplasms for the Prediction of Survival Computer Methods and Programs in Biomedicine, 244 | Jenul, A., Stokmo, H., Schrunner, S., Hjortland, G., Revheim, M., Tomic, O. | 2024 |
| UBayFS: An R Package for User Guided Feature Selection Journal of Open Source Software, 8 | Jenul, A., Schrunner, S. | 2023 |
| Principal component-based image segmentation: a new approach to outline in vitro cell colonies Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 11:18-30 | Arous, D., Schrunner, S., Hanson, I., Edin, N., Malinen, E. | 2022 |
| A user-guided Bayesian framework for ensemble feature selection in life science applications (UBayFS) Machine Learning, 111:3897-3923 | Jenul, A., Schrunner, S., Pilz, J., Tomic, O. | 2022 |
| RENT: A Python Package for Repeated Elastic Net Feature Selection Journal of Open Source Software, 6 | Jenul, A., Schrunner, S., Huynh, B., Tomic, O. | 2021 |
| RENT - repeated elastic net technique for feature selection IEEE Access, 9 | Jenul, A., Schrunner, S., Liland, K., Indahl, U., Futsaether, C., Tomic, O. | 2021 |
| An explicit solution for image restoration using Markov Random Fields Journal of Signal Processing Systems, 92:257-267 | Pleschberger, M., Schrunner, S., Pilz, J. | 2019 |
| Feature extraction from analog wafermaps: a comparison of classical image processing and a deep generative model IEEE Transactions on Semiconductor Manufacturing, 32:190-198 | Santos, T., Schrunner, S., Geiger, B., Pfeiler, O., Zernig, A., Kästner, A., Kern, R. | 2019 |
| Conference contributions | ||
|---|---|---|
| Title | Author | Year |
| Component Based Pre-filtering of Noisy Data for Improved Tsetlin Machine Modelling in: IEEE (Hrsg.), International Symposium on the Tsetlin Machine (ISTM), 20-21 Jun 2022, Grimstad, Norway | Jenul, A., Bhattarai, B., Liland, K., Jiao, L., Schrunner, S., Futsaether, C., Granmo, O., Tomic, O. | 2022 |
| Ranking Feature-Block Importance in Artificial Multiblock Neural Networks in: Springer Lecture Notes in Computer Science (Hrsg.), International Conference on Artificial Neural Networks 2022, 06-09 Sep 2022, Bristol, UK, S. 163-175 | Jenul, A., Schrunner, S., Huynh, B., Helin, R., Futsaether, C., Liland, K., Tomic, O. | 2022 |
| A generative semi-supervised classifier for datasets with unknown classes in: Association for Computing Machinery (Hrsg.), SAC '20: ACM Symposium on Applied Computing 2020, 30 Mar-03 Apr 2020, Brno, Czech Republic, S. 1066-1074 | Schrunner, S., Geiger, B., Zernig, A., Kern, R. | 2020 |
| A health factor for process patterns - enhancing semiconductor manufacturing by pattern recognition in analog wafermaps in: IEEE (Hrsg.), IEEE International Conference on Systems, Man and Cybernetics (SMC 2019), 06-09 Oct 2019, Bari, Italy | Schrunner, S., Jenul, A., Scheiber, M., Zernig, A., Kästner, A., Kern, R. | 2019 |
| A comparison of supervised approaches for process pattern recognition in analog semiconductor wafer test data in: IEEE (Hrsg.), IEEE International Conference on Machine Learning and Applications (ICMLA 2018), 17-20 Dec 2018, Orlando, FL, USA | Schrunner, S., Pfeiler, O., Zernig, A., Kästner, A., Kern, R. | 2018 |
| Markov random fields for pattern extraction in analog wafer test data in: IEEE (Hrsg.), International Conference on Image Processing Theory, Tools and Applications (IPTA 2017), 28 Nov-01 Dec 2017, Montreal, Canada | Schrunner, S., Pfeiler, O., Zernig, A., Kästner, A., Kern, R. | 2017 |
| Articles in Journals | ||
|---|---|---|
| Title | Author | Year |
| Learning From Limited Temporal Data: Dynamically Sparse Historical Functional Linear Models With Applications to Earth Science Environmetrics, 36(4) | Janssen, J., Meng, S., Haris, A., Schrunner, S., Cao, J., Welch, W., Kunz, N., Ameli, A. | 2025 |
| A Gaussian sliding windows regression model for hydrological inference Journal of the Royal Statistical Society, Series C: Applied Statistics | Schrunner, S., Pishrobat, P., Janssen, J., Jenul, A., Cao, J., Ameli, A., Welch, W. | 2025 |
| Articles in Journals | ||
|---|---|---|
| Title | Author | Year |
| Novel Ensemble Feature Selection Techniques Applied to High-Grade Gastroenteropancreatic Neuroendocrine Neoplasms for the Prediction of Survival Computer Methods and Programs in Biomedicine, 244 | Jenul, A., Stokmo, H., Schrunner, S., Hjortland, G., Revheim, M., Tomic, O. | 2024 |
| Articles in Journals | ||
|---|---|---|
| Title | Author | Year |
| UBayFS: An R Package for User Guided Feature Selection Journal of Open Source Software, 8 | Jenul, A., Schrunner, S. | 2023 |
| Articles in Journals | ||
|---|---|---|
| Title | Author | Year |
| Principal component-based image segmentation: a new approach to outline in vitro cell colonies Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 11:18-30 | Arous, D., Schrunner, S., Hanson, I., Edin, N., Malinen, E. | 2022 |
| A user-guided Bayesian framework for ensemble feature selection in life science applications (UBayFS) Machine Learning, 111:3897-3923 | Jenul, A., Schrunner, S., Pilz, J., Tomic, O. | 2022 |
| Conference contributions | ||
|---|---|---|
| Title | Author | Year |
| Component Based Pre-filtering of Noisy Data for Improved Tsetlin Machine Modelling in: IEEE (Hrsg.), International Symposium on the Tsetlin Machine (ISTM), 20-21 Jun 2022, Grimstad, Norway | Jenul, A., Bhattarai, B., Liland, K., Jiao, L., Schrunner, S., Futsaether, C., Granmo, O., Tomic, O. | 2022 |
| Ranking Feature-Block Importance in Artificial Multiblock Neural Networks in: Springer Lecture Notes in Computer Science (Hrsg.), International Conference on Artificial Neural Networks 2022, 06-09 Sep 2022, Bristol, UK, S. 163-175 | Jenul, A., Schrunner, S., Huynh, B., Helin, R., Futsaether, C., Liland, K., Tomic, O. | 2022 |
| Articles in Journals | ||
|---|---|---|
| Title | Author | Year |
| RENT: A Python Package for Repeated Elastic Net Feature Selection Journal of Open Source Software, 6 | Jenul, A., Schrunner, S., Huynh, B., Tomic, O. | 2021 |
| RENT - repeated elastic net technique for feature selection IEEE Access, 9 | Jenul, A., Schrunner, S., Liland, K., Indahl, U., Futsaether, C., Tomic, O. | 2021 |
| Articles in Journals | ||
|---|---|---|
| Title | Author | Year |
| An explicit solution for image restoration using Markov Random Fields Journal of Signal Processing Systems, 92:257-267 | Pleschberger, M., Schrunner, S., Pilz, J. | 2019 |
| Feature extraction from analog wafermaps: a comparison of classical image processing and a deep generative model IEEE Transactions on Semiconductor Manufacturing, 32:190-198 | Santos, T., Schrunner, S., Geiger, B., Pfeiler, O., Zernig, A., Kästner, A., Kern, R. | 2019 |
| Conference contributions | ||
|---|---|---|
| Title | Author | Year |
| A generative semi-supervised classifier for datasets with unknown classes in: Association for Computing Machinery (Hrsg.), SAC '20: ACM Symposium on Applied Computing 2020, 30 Mar-03 Apr 2020, Brno, Czech Republic, S. 1066-1074 | Schrunner, S., Geiger, B., Zernig, A., Kern, R. | 2020 |
| A health factor for process patterns - enhancing semiconductor manufacturing by pattern recognition in analog wafermaps in: IEEE (Hrsg.), IEEE International Conference on Systems, Man and Cybernetics (SMC 2019), 06-09 Oct 2019, Bari, Italy | Schrunner, S., Jenul, A., Scheiber, M., Zernig, A., Kästner, A., Kern, R. | 2019 |
| A comparison of supervised approaches for process pattern recognition in analog semiconductor wafer test data in: IEEE (Hrsg.), IEEE International Conference on Machine Learning and Applications (ICMLA 2018), 17-20 Dec 2018, Orlando, FL, USA | Schrunner, S., Pfeiler, O., Zernig, A., Kästner, A., Kern, R. | 2018 |
| Markov random fields for pattern extraction in analog wafer test data in: IEEE (Hrsg.), International Conference on Image Processing Theory, Tools and Applications (IPTA 2017), 28 Nov-01 Dec 2017, Montreal, Canada | Schrunner, S., Pfeiler, O., Zernig, A., Kästner, A., Kern, R. | 2017 |
