Robust Classification of Digitally Modulated Signals Using Capsule Networks and Cyclic Cumulant Features

TL;DR

This paper presents a method for classifying digitally modulated signals robustly by combining cyclic cumulant features with capsule networks, demonstrating superior accuracy and generalization over other deep learning methods.

Contribution

The study introduces a novel approach integrating cyclic cumulant features with capsule networks for improved signal classification robustness.

Findings

Capsule networks with cyclic cumulant features outperform other deep learning methods.

The approach achieves high classification accuracy across independent datasets.

The method demonstrates strong generalization capabilities.

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.