#Machine Learning

In Machine Learning, artificial systems learn from experience – similar to humans. This technology can be used in various applications in research and practice, for example to analyse medical data or fend off IT attacks.

Projects

Applied Biomechanics in Rehabilitation Research

Endowed professorship of the province of Lower Austria to strengthen and expand the research focus on motor rehabilitation

SBA Research

K1 competence center for Information Security

FIVE - #Fitspiration Image VErification

Proof of Concept of an interdisciplinary online-course offering guidance on how to deal critically with information provided by social media sites.

IMREA - Intelligent Multimodal Real Estate Assessment

Multimodal information extraction and machine learning techniques for the extraction of real estate related attributes and parameters from heterogeneous input data

Scribe ID AI

Active Machine Learning for automatic identification of handwriting in 12th century manuscripts

Active deep learning for object detection

Developing novel strategies for integrating Active and Deep Learning for Artificial Intelligence

Plant Monitoring AI

Leveraging machine learning and predictive analytics for early detection of plant stress for the benefit of sustainability in farming

IntelliGait 3D- Gait Data Mining

Establishing advanced analysis methods for modelling, classification and similarity retrieval of gait patterns to enable novel data-driven ways to access 3D gait databases

ARmEO - Augmented Reality meets Earth Observation

Processing of earth observation data to increase accessibility and and reduce barriers for their use

LINK

Analysis and nowcasting of extreme weather events using data from radio links

Publications

Horsak, B., Simonlehner, M., Schöffer, L., Dumphart, B., Jalaeefar, A., & Husinsky, M. (2021). Overground walking in a fully immersive Virtual Reality: Preliminary results of a comprehensive study on the effects on walking biomechanics. Gait & Posture, 90, 100–101. https://doi.org/10.1016/j.gaitpost.2021.09.051
Krondorfer, P., Slijepčević, D., Unglaube, F., Kranzl, A., Breiteneder, C., Zeppelzauer, M., & Horsak, B. (2021). Deep learning-based similarity retrieval in clinical 3D gait analysis. Gait & Posture, 90, 127–128. https://doi.org/10.1016/j.gaitpost.2021.09.066
Koch, D., Despotovic, M., Döller, M., Leiber, S., & Zeppelzauer, M. (2020). Computer Vision in Building Research: An Application for Prediction of Condition and Costs of a Property. Building Research & Information, Submitted.
Eresheim, S. (2020). Reinforcement Learning for Incident Protection in IT. First Conference on Mathematics of Data Science (MDS20).
Horsak, B., Simonlehner, M., Schöffer, L., Maureder, J., Schwab, C., Raberger, A. M., Zeller, M., & Husinsky, M. (2020). Applicability and usability of an immersive virtual reality-based balance control exergame for prosthetic users: A pilot study with healthy individuals. Gait & Posture. ESMAC 29th Annual Meeting, Virtual Meeting. https://doi.org/10.1016/j.gaitpost.2020.07.113
Horsak, B., Dumphart, B., Slijepcevic, D., & Zeppelzauer, M. (2020). Explainable Artificial Intelligence (XAI) und ihre Anwendung auf Klassifikationsprobleme in der Ganganalyse. Abstractband Des 3. GAMMA Kongress. 3. GAMMA Kongress, München, Deutschland.
Horst, F., Slijepcevic, D., Zeppelzauer, M., Raberger, A. M., Lapuschkin, S., Samek, W., Schöllhorn, W. I., Breiteneder, C., & Horsak, B. (2020). Explaining automated gender classification of human gait. Gait & Posture, 81, 159–160. https://doi.org/10.1016/j.gaitpost.2020.07.114
Horsak, B., Slijepcevic, D., Raberger, A.-M., Schwab, C., Worisch, M., & Zeppelzauer, M. (2020). GaitRec, a large-scale ground reaction force dataset of healthy and impaired gait. Scientific Data, 7:143(1), 1–8. https://doi.org/10/gh372d
Oliveira, V. A. D. J., Stoiber, C., Grüblbauer, J., Musik, C., Ringot, A., & Gebesmair, A. (2020). SAMBAVis: Design Study of a Visual Analytics Tool for the Music Industry Powered by YouTube Comments. Eurovis 2020, Norrköping, Sweden. https://doi.org/https://doi.org/10.2312/evs.20201041
Slijepcevic, D., Zeppelzauer, M., Schwab, Caterine, Raberger, A.-M., Breitender, C., & Horsak, B. (2020). Input Representations and Classification Strategies for Automated Human Gait Analysis. Gait & Posture, 76, 198–203. https://doi.org/10/ghz24x

News

10/19/2021

Lower Austrian Innovation Award

08/31/2021

Predicting Extreme Weather Using Mobile Networks

07/02/2021

Digital Ideas for the Industries