Robust Classification of Digitally Modulated Signals Using Capsule Networks and Cyclic Cumulant Features
Signal Processing
2023-07-06 v1
Abstract
The paper studies the problem of robust classification of digitally modulated signals using capsule networks and cyclic cumulant (CC) features extracted by cyclostationary signal processing (CSP). Two distinct datasets that contain similar classes of digitally modulated signals but that have been generated independently are used in the study, which reveals that capsule networks trained using CCs achieve high classification accuracy while also outperforming other deep learning-based approaches in terms of classification accuracy as well as generalization abilities.
Keywords
Cite
@article{arxiv.2211.00232,
title = {Robust Classification of Digitally Modulated Signals Using Capsule Networks and Cyclic Cumulant Features},
author = {John A. Snoap and James A. Latshaw and Dimitrie C. Popescu and Chad M. Spooner},
journal= {arXiv preprint arXiv:2211.00232},
year = {2023}
}
Comments
6 pages, 5 figures, to be published in IEEE MILCOM 2022: IEEE Military Communications Conference 2022