Kaplagoglu, Erkan; Kandah, Farah
College of Engineering and Computer Science
University of Tennessee at Chattanooga
Place of Publication
The purpose of this study is to conduct in-depth experiments that analyze the effects on Deep Learning (DL) based Specific Emitter Identification (SEI) and address three issues facing the field. SEI is targeted as a physical-layer security measure that can identify radios within an Internet of Things (IoT) deployment without the need of digital credentials. In the current space, DL SEI is still in its infancy, and has not had the incubation time for a tailor-suited approach to solve issues facing SEI. This thesis introduces methods of improving DL SEI using transforms to allow the networks to learn features that reduce computational cost and improve security. Overall, this thesis highlights the introduction of (i) the natural logarithm as a computationally inexpensive transform of preamble-based waveforms, (ii) assessment of the impacts signal energy has on DL SEI, and (iii) an approach to improving the multi-day classification performance of IEEE 802.11a OFDM emitters.
I want to acknowledge Dr. Donald R. Reising for accepting me as a masters candidate and ensuring that I had the guidance and tools to realize this work. I want to thank my other thesis committee members, Dr. Erkan Kapaglonu and Dr. Farah Kandah for taking the time to serve on the committee. I would like to thank Dr. Mohammed K. Fadul for being an invaluable resource for understanding deep learning. I want to acknowledge those at the UTC SimCenter for work- ing closely with me on the compute hardware to make the level of analysis in this study possible. I would like to acknowledge the wonderful UTC professors Dr. Christopher Cox, Dr. Lakmali Weerasena, Dr. Yu Liang, and Dr. Dalei Wu. I want to acknowledge Math Works, Nvidia, Intel, and Ettus Research for making the tools that allow for engineers to learn, experiment, and research in a widely accessible manner. I want to acknowledge the giants of science that have come before, mainly Pythagoras and Nikola Tesla. Their vision and intellect have yet to be fully understood.
M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science.
Deep learning (Machine learning); Radio frequency identification systems
x, 80 leaves
Tyler, Joshua, "Addressing the challenges facing deep learning based Specific Emitter Identification via preamble based waveforms" (2022). Masters Theses and Doctoral Dissertations.