Tim Kreuzer PhD Student
Contact
Name and title: Tim KreuzerPhD Student
ORCID0000-0002-0813-9555 Länk till annan webbplats.
Workplace: Department of Computer and Systems Sciences Länk till annan webbplats.
Visiting address Nodhuset, Borgarfjordsgatan 12
Postal address Institutionen för data- och systemvetenskap164 25 Kista
Research group
About me
I'm a PhD student at DSV, working on a project about integrating time series forecasting, explainability, and digital twins. In my research, I develop and propose new methods for both forecasting and explainability, focusing on performance and understanding of the human end-user of the machine learning application. Further, I work on the modeling side of digital twins, and I have designed system architectures and a meta-model for digital twins that integrate forecasting and explainability functionality.
I have received my Master's from the University of Bolzano and my Bachelor's from Hof University. Previously, I have worked as a Data Scientist on various industrial projects, focusing on anomaly detection within textual data. Before starting my PhD, I worked at the Okinawa Institute of Science and Technology in the Computational Neuroscience group on classifying tetrahedral models of Purkinje cells as dendritic or spine parts.
My research centers on time series forecasting and explainability in digital twins. The work advances algorithms and system designs that make forecasts accurate, interpretable, and actionable in real time. My projects include an interpretable forecasting method that links predictions to characteristic historical patterns, enabling traceable, sample-level reasoning about outputs. Further, I have designed a model-agnostic post-hoc technique that provides multi-granular explanations down to the time-step level and reveals cross-channel dependencies in multivariate settings. I have also investigated decomposition-driven forecasting approaches to improve both predictive accuracy and interpretability across families of forecasting models. My research also proposes conceptual and architectural models for integrating explainable AI into digital twins, together with a real-time demonstration on an industrial manufacturing line.