direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Matthias Mehlhose, M.Sc.

Lupe

Research

Matthias Mehlhose received his diploma degree from university of applied sciences (FHTW Berlin, now HTW) in 2008 and his master of science in 2012 from Technische Universität Berlin. He started his scientific career at Fraunhofer Heinrich Hertz Institute in 2007 with an internship. After he worked as a Research Assistant and Research Associate he is now working toward his Ph.D..

His current research interests focused on modern wireless communication system like LTE (4G) and NR (5G) on the physical layer signal processing. Especially using software-defined radio with massive MIMO antennas on different radio bands to examine beamforming, user localization algorithms and channel fingerprints.

Current Projects

Profiles

Publications

Journal and Magazine Articles

T. Wirth, K.-J. Friederichs, R. Halfmann, T. Haustein, B. Holfeld, M. Mehlhose, J. Pilz and D. Wieruch (2016). Real-time demonstration of optimized spectrum usage with LSA carrier aggregation. Frequenz, Journal of RF-Engineering and Telecommunications, vol. 70, no. 7, pp. 301-308, July 2016, doi: 10.1515/freq-2015-0215


Conference, Symposium, and Workshop Papers

Machine Learning-Based Adaptive Receive Filtering: Proof-of-Concept on an SDR Platform
Citation key Mehl2020ICC
Author M. Mehlhose, D. A. Awan, R. L.G. Cavalcante, M. Kurras and S. Stanczak
Year 2020
Journal accepted, IEEE International Conference on Communications (ICC), Dublin, Ireland, 2020
Abstract Conventional multiuser detection techniques either require a large number of antennas at the receiver for a desired performance, or they are too complex for practical implementation. Moreover, many of these techniques, such as successive interference cancellation (SIC), suffer from errors in parameter estimation (user channels, covariance matrix, noise variance, etc.) that is performed before detection of user data symbols. As an alternative to conventional methods, this paper proposes and demonstrates a low-complexity practical Machine Learning (ML) based receiver that achieves similar (and at times better) performance to the SIC receiver. The proposed receiver does not require parameter estimation; instead it uses supervised learning to detect the user modulation symbols directly. We perform comparisons with minimum mean square error (MMSE) and SIC receivers in terms of symbol error rate (SER) and complexity.
Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions

This site uses Matomo for anonymized web analytics. More information and opt-out options under data protection.

Contact

Matthias Mehlhose, M.Sc.
Fraunhofer Heinrich-Hertz-Institut
Einsteinufer 37
10587 Berlin