Page Content

Daniel Külzer, M.Sc. (TUM)

: © private

Daniel Külzer was born in Munich, Germany, in 1994. He received his B.Sc. and M.Sc. in Electrical Engineering and Information Technology in 2016 and 2018, respectively, from the Technical University of Munich, Germany. In 2018, he was also awarded an engineer’s degree (similar to an M.Sc. in Engineering) from Télécom Paris as part of a double degree program. Besides a one-year stay in France, he studied for one semester at the University of Illinois at Urbana-Champaign, United States, in 2015.

Since 2018, he is working at BMW Group in Munich, Germany, developing connectivity solutions for autonomous driving. There he is involved in national and international research projects for vehicle-to-vehicle and vehicle-to-infrastructure communication.

He is currently working towards the Ph.D. degree under the supervision of Prof. Sławomir Stańczak. His research interests include network optimization techniques, particularly predictive resource allocation, and machine learning for Quality of Service prediction and provisioning in the context of vehicular communication.

Projects

AI4Mobile

Find me also on

Publications

On Latency Prediction with Deep Learning and Passive Probing at High Mobility
Citation key	Kuel2021ICC
Author	D.F. Külzer, F. Debbichi, S. Stanczak and M. Botsov
Year	2021
Journal	IEEE International Conference on Communications (ICC) 2021, Montreal, Canada (virtual conference), in June 14-23, 2021
Month	June
Abstract	In autonomous driving, several applications like teleoperated driving, back-end status verification, or online gaming for customer infotainment rely on low-latency communication. Ideally, we can select a route that best supports the applications' requirements before the journey. Therefore, route selection for autonomous vehicles might require in-advance latency predictions. End-to-end (E2E) latency prediction is a difficult task, especially when considering that it needs to be achieved with limited active probing due to cost constraints. We study continuous latency prediction and application feasibility assessment (in terms of meeting the applications' E2E latency requirements), using a custom-designed deep learning model that leverages feature engineering for prediction error reduction. We provide insights into the model behavior utilizing recent advances in explainable artificial intelligence. Moreover, we present a novel model-agnostic approach based on active learning to leverage passive probing data. A pre-trained model performs certainty sampling, predicts artificial labels to enlarge the training dataset, and trains iteratively on the augmented set. The results show a 5 % reduction in mean average error for continuous latency prediction and an increase of up to 2.8 % in macro F1 score due to the use of passive probing data.