We investigate sequence machine learning techniques on raw radio signal time-series data. By applying deep recurrent neural networks we learn to discriminate between several application layer traffic types on top of a constant envelope modulation without using an expert demodulation algorithm. We show that complex protocol sequences can be learned and used for both classification and generation tasks using this approach.
@article{arxiv.1610.00564,
title = {End-to-End Radio Traffic Sequence Recognition with Deep Recurrent Neural Networks},
author = {Timothy J. O'Shea and Seth Hitefield and Johnathan Corgan},
journal= {arXiv preprint arXiv:1610.00564},
year = {2016}
}