Modern high-frequency systems benefit massively from machine learning methods. In applications where rule-based algorithms reach their limits, these data-driven approaches enable a significant increase in resolution and accuracy. This is exemplified by current research challenges, namely for the classification of targets in autonomous driving radar systems, radar-based gesture recognition for smart home applications and device control as well as in the field of medical technology for the contactless monitoring of human vital signs.
Performance accreditation:
m1785-2022 - Machine Learning in Electrical Engineering and Information Technology<ul><li>p1778-2022 - Machine Learning in Electrical Engineering and Information Technology: mündlich</li></ul>
Ahmed, Taha (2024). Development of an iterative multi-agent coordination framework for congestion prevention in low voltage grids.
Busch, Marcel (2024). Entwicklung eines Netzmodells zur szenarienbasierten Untersuchung von Engpässen in heutigen und zukünftigen städtischen Verteilnetzen.
Lindner, Joost (2024). Entwicklung einer probabilistischen Lastprognose für die Niederspannungsebene elektrischer Verteilnetze.
Möller, Julius (2024). Untersuchung von Kennzahlen zur Bewertung der Diskriminierungsfreiheit von Engpassmanagementmaßnahmen.
Wilke, Jan Jakob (2024). Definition leistungsbasierter Netzregeln zur Engpassvermeidung in elektrischen Verteilnetzen.
beendete
2024
Ming, Zhao (2024). Conceptual Design for a grid demonstrator for teaching purposes and development of a suitable distribution grid simulation.
2023
Kock am Brink, Jonas (2023). Entwicklung einer Engpassprognose für elektrische Verteilnetze mittels probabilistischer Verfahren.