Over the Air Deep Learning Based Radio Signal Classification

TL;DR

This paper compares deep learning and traditional methods for radio signal classification, evaluating their performance through simulations and real-world over-the-air experiments, highlighting challenges and design considerations.

Contribution

It provides a comprehensive comparison of deep learning and classical approaches for radio signal classification, including over-the-air measurements and analysis of channel impairments.

Findings

Deep learning approaches outperform traditional methods under certain conditions.

Channel impairments like frequency offset and fading significantly affect classification accuracy.

Over-the-air experiments validate simulation results and reveal practical challenges.

Abstract

We conduct an in depth study on the performance of deep learning based radio signal classification for radio communications signals. We consider a rigorous baseline method using higher order moments and strong boosted gradient tree classification and compare performance between the two approaches across a range of configurations and channel impairments. We consider the effects of carrier frequency offset, symbol rate, and multi-path fading in simulation and conduct over-the-air measurement of radio classification performance in the lab using software radios and compare performance and training strategies for both. Finally we conclude with a discussion of remaining problems, and design considerations for using such techniques.