Bülent Ündes is a data scientist and economist, currently pursuing his Ph.D. in the quantitative data analytics group at Vrije Universiteit Amsterdam under the supervision of Mark Hoogendoorn (Vrije Universiteit Amsterdam) and Bernard Veldkamp (University of Twente). His research focuses on trustworthy AI, efficient deep learning, and probabilistic machine learning, with a particular interest in the intersection of AI and healthcare. Previously, he worked as a junior lecturer at the Vrije Universiteit Amsterdam. He holds two master’s degrees, one in Economics from Lund University in Sweden, and one in Data Science from the Barcelona School of Economics in Spain.

“Can we detect and predict stress episodes using advanced deep learning techniques from real-time ECG Data?”

This study aims to harness the potential of modern deep learning approaches to real-time detection and prediction of stress episodes. Our methodology involves leveraging data from a comprehensive and controlled laboratory study featuring diverse mental stressors. To enhance the interpretability and efficiency of our model, we integrate techniques from both explainability and efficiency research. By combining cutting-edge deep learning methods with a rich dataset, we strive to contribute to the development of a robust and effective tool for identifying and predicting mental stress in daily life scenarios.

PhD student,
VU Amsterdam