Separation of Channel Coefficients with Deep Neural Networks

Bachelor Thesis

in progress

Analysis: 5
Empiricism: 3
Implementation: 8
Literature Research: 3


The separation of channel coefficients is a time-consuming operation. In this thesis project, we are going to explore the suitability of deep neural networks (DNNs) to speed up a specific PHY-related optimization task.


The goal of this project is to explore the suitability of DNNs to separate channel coefficients. The project main goals are:

  • Research the literature about uses of DNNs in other optimization problems
  • Explore suitable DNN configurations for the envisioned task
  • Evaluate the DNN's performance in terms of accuracy and speed

Start: 01.05.2018


Student: Vladimir Roskin

Research Areas: Sichere Mobile Netze



Prof. Dr.-Ing. Matthias Hollick

Technische Universität Darmstadt
Department of Computer Science
Secure Mobile Networking Lab 

Mornewegstr. 32 (S4/14)
64293 Darmstadt, Germany

Phone: +49 6151 16-25472
Fax: +49 6151 16-25471


A A A | Drucken Drucken | Impressum Impressum | Sitemap Sitemap | Suche Suche | Kontakt Kontakt | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang