Hardware imperfections in RF transmitters introduce features that can be used to identify a specific transmitter amongst others. Supervised deep learning has shown good performance in this task but using datasets not applicable to real world situations where topologies evolve over time. To remedy this, the work rests on a series of datasets gathered in the FIT/Cortexlab platform to train a CNN, where focus has been given to reduce channel bias that has plagued previous works and constrained them to a constant environment or to simulations. The most challenging scenarios provide the trained neural network with resilience and show insight on the best signal type to use for identification.
Leonardo S. Cardoso is an Associate Professor at INSA, Université de Lyon, and he is a research member of the Institut National de Recherche en Informatique et en Automatique (INRIA). He received his Ph.D. degree in 2011 at Supe?lec, France, on Cognitive Radio and Dynamic Spectrum Access. He has worked extensively in resource allocation, interference management for heterogeneous networks, real-time MIMO channel sounding, interference management, and he co-designed and developed FIT/CorteXlab, a testbed for multi-node cognitive radio experimentation. His research interests include wireless communications, heterogeneous networks, interference management and signal processing.
CTTC Auditorium / 10:00hDr. Leonardo S. Cardoso