|
|
AI-based classification of RF signals
Turák, Samuel ; Ulovec, Karel (oponent) ; Polák, Ladislav (vedoucí práce)
This thesis focuses on Deep learning-based radio frequency (RF) signal classification. For this purpose, three neural networks are selected and introduced: Convolutional Neural Network (CNN), Gated Recurrent Unit Network (GRU) and Convolutional Gated Deep Neural Network (CGDNN). All are trained and evaluated on multiple datasets, influenced by different RF impairments, for wireless standard classification. The waveforms in these datasets have been created by the Wireless Waveform Generator app in MATLAB. One publicly available modulation classification dataset is also being tested on the models. The performed approaches of data preprocessing, model training and model evaluation are implemented in the programming environment Python, utilizing libraries such as Scikit-learn and Keras. The obtained results are evaluated and discussed.
|
|
|
RF Impairments: Estimation Compensation and Exploitation
Pospíšil, Martin ; Viščor, Ivo (oponent) ; Galajda, Pavol (oponent) ; Maršálek, Roman (vedoucí práce)
This thesis deals with the hardware imperfections of wireless transceivers – dominantly with the measurement setups and techniques for their compensation, but also with their exploitation providing the additional physical layer security. The first part of the thesis consists of brief introduction to the domain of research, formulation of research questions, and introductory part providing brief discussion of wireless front-end impairments, low-complexity digital predistorters, or basic classifiers. The most important section of this part then contains description of the state-of-the art mm-wave experimental setups. The core of the dissertation is composed as a selection of eight published papers complemented with the selected additional information on the hardware or experiments carried on. Three of the papers have dealt with RF impairments exploitation for transmitter authentication, two other focus on the implementation of low-complexity digital predistorters for power amplifier nonlinearity, and remaining three describe our millimeter-wave testbeds together with the achieved results of digital impairment compensation in 60 GHz band.
|
|
|
RF Impairments: Estimation Compensation and Exploitation
Pospíšil, Martin ; Viščor, Ivo (oponent) ; Galajda, Pavol (oponent) ; Maršálek, Roman (vedoucí práce)
This thesis deals with the hardware imperfections of wireless transceivers – dominantly with the measurement setups and techniques for their compensation, but also with their exploitation providing the additional physical layer security. The first part of the thesis consists of brief introduction to the domain of research, formulation of research questions, and introductory part providing brief discussion of wireless front-end impairments, low-complexity digital predistorters, or basic classifiers. The most important section of this part then contains description of the state-of-the art mm-wave experimental setups. The core of the dissertation is composed as a selection of eight published papers complemented with the selected additional information on the hardware or experiments carried on. Three of the papers have dealt with RF impairments exploitation for transmitter authentication, two other focus on the implementation of low-complexity digital predistorters for power amplifier nonlinearity, and remaining three describe our millimeter-wave testbeds together with the achieved results of digital impairment compensation in 60 GHz band.
|
host ::
RSS.