Complex-Valued Networks for Automatic Modulation Classification

doi:10.1109/TVT.2020.3005707

Complex-Valued Networks for Automatic Modulation Classification

2020-09-01

139

PRE

AI

DOI：10.1109/TVT.2020.3005707

Original

Original request for help

Save

Abstract

En 中文

Deep learning (DL) has been recognized as an effective solution for automatic modulation classification (AMC). However, most recent DL based AMC works are based on real-valued operations and representations. In this correspondence, we aim to demonstrate the high potential of complex-valued networks for AMC. We present the design of several key building blocks for complex-valued networks, such as complex convolution, complex batch-normalization, complex weight initialization, and complex dense strategies. We then provide a comparison study of three different neural network models and their complex-valued counterparts using the RadioML 2016.10 A dataset. Our results validate the superior performance in AMC achieved by the complex-valued networks.

Keywords:

Convolution

Neural networks

Modulation

Kernel

Wireless communication

Computer architecture

Signal to noise ratio

Automatic modulation classification

deep learning

complex-valued networks

Complex-Valued Networks for Automatic Modulation Classification

Abstract

Journal

Organization