Tutor: | Matthias Hummert |
Type of Thesis: | Master's thesis (MSc) |
date of end: | 09/2021 |
Student: | Emmanuel Aguboshim |
Status: | finished |
ANT-shelfmark: | |
Abstract: | Motivation: In advanced communication systems, latency and throughput are often key performance indicators. The idea of this thesis is to create a Machine Learning based algorithm that is capable of classifying incoming packets at the receiver side, whether the received package is decodable or not. Using this technique ARQ schemes could be enhanced and hence latency and throughtput is increased. Goal: The goal of this thesis is to implement a data-driven classification algorithm that should decide whether a received packet can be correctly decoded or not. Of course this problem depends on the chosen code and decoder and hence a full transmission chain needs to be implemented in order to train this classifier and generate the needed data. |