Self-Supervised RF Signal Representation Learning for NextG Signal Classification With Deep Learning

Deep learning (DL) finds rich applications in the wireless domain to improve spectrum awareness. Typically, DL models are either randomly initialized following a statistical distribution or pretrained on tasks from other domains in the form of transfer learning without accounting for the unique char...

Full description

Saved in:
Bibliographic Details
Published in:IEEE wireless communications letters 2023-01, Vol.12 (1), p.65-69
Main Authors: Davaslioglu, Kemal, Boztas, Serdar, Ertem, Mehmet Can, Sagduyu, Yalin E., Ayanoglu, Ender
Format: Article
Language:English
Subjects:
Automatic modulation recognition
contrastive learning
Deep learning
Domains
Machine learning
Model accuracy
Modulation
Radio frequency
Radio signals
Representations
self-supervised learning
Semantics
Signal classification
Signal to noise ratio
spectrum awareness
Task analysis
Training
Wireless communication
Wireless sensor networks
wireless signal classification
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning (DL) finds rich applications in the wireless domain to improve spectrum awareness. Typically, DL models are either randomly initialized following a statistical distribution or pretrained on tasks from other domains in the form of transfer learning without accounting for the unique characteristics of wireless signals. Self-supervised learning (SSL) enables the learning of useful representations from Radio Frequency (RF) signals themselves even when only limited training data samples with labels are available. We present a self-supervised RF signal representation learning method and apply it to the automatic modulation recognition (AMR) task by specifically formulating a set of transformations to capture the wireless signal characteristics. We show that the sample efficiency (the number of labeled samples needed to achieve a certain performance) of AMR can be significantly increased (almost an order of magnitude) by learning signal representations with SSL. This translates to substantial time and cost savings. Furthermore, SSL increases the model accuracy compared to the state-of-the-art DL methods and maintains high accuracy when limited training data is available.
ISSN:2162-2337
2162-2345
DOI:10.1109/LWC.2022.3217292