Chair of Data Science (Informatik X)
University of Würzburg
Campus Hubland Nord
Phone: (+49 931) 31 - 87995
Office: Room 50.03.011
In July 2021 I joined the DMIR research group. My research focus lies on modelling complex end-to-end sensor networks in various application fields, reaching from smart infrastructure to smart health applications. Methodologically, my focus is on exploring the synergy effects between Graph Signal Processing (GSP) and Graph Neural Networks (GNN) as well as on integrating expert-informations out of physics and mechanics into complex graph structures.
When I joined the group, I started working on the classification of bee and bird audio data. The goal of this research was to learn more about the acoustic behavior of these protected animals in order to be able to monitor it.
In P-BIM project, I am working on the adaptation of civil engineering methods on modelling graph neural networks. Methodologically, I am combining Graph Signal Processing methods with the recent advances of Graph Neural Networks to detect anomalies within the mode shapes of structures.
At the same time I am working on the KI@FlowChief project, where the goal is to predict leakages in time and location within a water distribution network. In these networks only ten percent of the nodes contain sensor measurements of different types of sensors like flow sensors, pressure sensors and AMRs (smart meters). Therefore, I use heterogeneous graph neural networks to model the heterogeneous structure of sensor types.
- WDM Sprecherin der " Women for Datadriven mobility"
- Scientia Fellowship für Postdoktorandinnen
- Mitglied der Gleichstellungskommission der Fakultät für Informatik
Liquor-HGNN: A heterogeneous graph neural network for leakage detection in water distribution networks. . In LWDA’23: Lernen, Wissen, Daten, Analysen. October 09--11, 2023, Marburg, Germany, M. Leyer (ed.). 2023.
Swarming Detection in Smart Beehives Using Auto Encoders for Audio Data. . In 2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 1–5. 2023.
Vergleichende Untersuchung von Reifegradmodellen der Industrie 4.0 und deren Übertragbarkeit auf das Smart Health Fallbeispiel der nicht-invasiven Messung des intrakraniellen Drucks (ICP). . 2023.
Gaining a realistic fatigue load model using sensor-based measurements. . In Structural Engineering for Future Societal Needs, Ghent, Belgium, 22-24 September 2021., pp. 1258–1270. 2021.
Smart Health-ein anwendungsorientiertes Fallbeispiel für Design Science Research. . In Journal of Management Information Systems, 24(3), pp. 45–77. 2021.
Towards IoT Standards Interoperability: A Tool-Assisted Approach. . In Springer International Publishing, pp. 514–518. 2021.