Viktoriya Degeler Computer scientist specializing in smart systems creation

I am Viktoriya Degeler, an Assistant Professor at the Bernoulli Institute for Mathematics, Computer Science, and Artificial Intelligence at the University of Groningen, the Netherlands. My research is focused on reasoning and decision making systems for smart environments, activity recognition, digital twins, pervasive systems and context modeling and representation, with particular interest in sustainable applications such as energy and water management.

My career, always at the edge of both academia and industry, included postdoc positions at the National University of Ireland in Galway and Delft University of Technology, a research engineer position at Airbus, Newport (UK), and the Lead AI engineer position in Cupenya, Amsterdam, where I was leading the AI department. I am active in promoting AI approaches in the industry, participate in Training in AI for SMEs program, and, earlier, acted as an AI technical mentor for startups of the AI Accelerator program at Rockstart Startup Accelerator, Amsterdam.

I am a patent holder and produced a number of peer-reviewed journal and conference publications, including receiving best demonstration and best student paper awards. I also acted as a program committee member on a number of conferences, such as ECML-PKDD, CIKM, CISSS, SOCA, ICSOC. I serve regularly as a reviewer and monitor for projects under the Horizon Europe (and, earlier, Horizon 2020) research framework, and coordinates research projects herself. I received several research grants, from funding agencies such as EIT Manufacturing, EIT Climate, AMS.

Home

News

[15.12.21] Two new PhD position vacancies related to the recently funded DiTEC project are opened in our group.

PhD position Digital Twin and reasoning system for water networks
PhD position Deep learning models for water network monitoring

[21.10.21] I am very honored to announce that our NWO project "DiTEC: Digital Twin for Evolutionary Changes in water networks" has been funded! I am the main applicant and coordinator of this €800,000 project, which has four partners in total: University of Groningen, Hanze University of Applied Sciences, Vitens, and Researchable, and will last four years. Our group will soon open two new PhD positions related to this project - stay tuned!

Read NWO's announcement

DiTEC proposes an evolutionary approach to real-time monitoring of water networks that detects inconsistency between measured sensor data and the expected situation, and performs real-time model update without needing additional calibration. Deep learning will be applied to create a data-driven simulation of the system. In case of leaks, valve degradation or sensor faults, the model is adapted to the degraded network until the maintenance takes place, which can take a long time. We will analyse the effect on data readings of different malfunctions, and construct a mitigating mechanism that allows to continue using the data, albeit in a limited capacity.

[20.10.21] Our new journal paper is published and is avalable open source:

Al-Saudi K, Degeler V, Medema M. Energy Consumption Patterns and Load Forecasting with Profiled CNN-LSTM Networks. Processes. 2021; 9(11):1870. https://doi.org/10.3390/pr9111870

Abstract: By virtue of the steady societal shift to the use of smart technologies built on the increasingly popular smart grid framework, we have noticed an increase in the need to analyze household electricity consumption at the individual level. In order to work efficiently, these technologies rely on load forecasting to optimize operations that are related to energy consumption (such as household appliance scheduling). This paper proposes a novel load forecasting method that utilizes a clustering step prior to the forecasting step to group together days that exhibit similar energy consumption patterns. Following that, we attempt to classify new days into pre-generated clusters by making use of the available context information (day of the week, month, predicted weather). Finally, using available historical data (with regard to energy consumption) alongside meteorological and temporal variables, we train a CNN-LSTM model on a per-cluster basis that specializes in forecasting based on the energy profiles present within each cluster. This method leads to improvements in forecasting performance (upwards of a 10% increase in mean absolute percentage error scores) and provides us with the added benefit of being able to easily highlight and extract information that allows us to identify which external variables have an effect on the energy consumption of any individual household.

[17.09.21] Our take on the emergence of Digital Twins is now published and is freely available to read as a book chapter! A supporting short explainer video is a good summary of what you can expect from the article. Read the full article here: rug.nl/gdbc/blog/digital-twins

[29.06.21] Proud to be a jury member in the GDBC Digital Thesis Award competition for the best Master Thesis related to Digital Business. On June 29 the finalists presented their thesis to the broad audience and received checks for 2000, 1000 and 500 euros. You can watch the whole live stream here: youtube.com/watch?v=aW1fG6TjPDA