# Transmitter Classification With Supervised Deep Learning

## TL;DR

This paper demonstrates the use of supervised deep learning, specifically CNNs, to classify RF transmitters based on hardware imperfections using real-world datasets, addressing environmental variability and improving robustness.

## Contribution

It introduces a new dataset collection in a real testbed and shows how CNNs can be trained to identify transmitters with resilience to changing environments.

## Key findings

- CNN achieves high accuracy in transmitter identification
- Packet preamble is the most effective signal type for classification
- Datasets are publicly available for future research

## Abstract

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.