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 Future Internet of Things / Cognitive Radio Testbed [4] (FIT/CorteXlab) to train a convolutional neural network (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, namely packet preamble. The generated datasets are published on the Machine Learning For Communications Emerging Technologies Initiatives web site 4 in the hope that they serve as stepping stones for future progress in the area. The community is also invited to reproduce the studied scenarios and results by generating new datasets in FIT/CorteXlab.

No abstract

No abstract

Active user detection is a standard problem that concerns many applications using random access channels in cellular or ad hoc networks. Despite being known for a long time, such a detection problem is complex, and standard algorithms for blind detection have to trade between high computational complexity and detection error probability. Traditional algorithms rely on various theoretical frameworks, including compressive sensing and bayesian detection, and lead to iterative algorithms, e.g. orthogonal matching pursuit (OMP). However, none of these algorithms have been proven to achieve optimal performance. This paper proposes a deep learning based algorithm (NN-MAP) able to improve on the performance of state-of-the-art algorithm while reducing detection time, with a codebook known at training time.