Deep Neural Network Architectures for Modulation Classification

TL;DR

This paper explores various deep neural network architectures, including CNN, ResNet, DenseNet, and CLDNN, to improve wireless signal modulation classification accuracy beyond previous methods, achieving up to 88.5% accuracy at high SNR.

Contribution

It introduces and evaluates novel deep learning architectures for modulation classification, surpassing previous state-of-the-art accuracy levels.

Findings

ResNet and DenseNet architectures outperform CNN in accuracy.

The proposed CLDNN achieves the highest accuracy of 88.5%.

Deep learning models significantly improve modulation recognition performance.

Abstract

In this work, we investigate the value of employing deep learning for the task of wireless signal modulation recognition. Recently in [1], a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections in a real wireless channel, and uses 10 different modulation types. Further, a convolutional neural network (CNN) architecture was developed and shown to deliver performance that exceeds that of expert-based approaches. Here, we follow the framework of [1] and find deep neural network architectures that deliver higher accuracy than the state of the art. We tested the architecture of [1] and found it to achieve an accuracy of approximately 75% of correctly recognizing the modulation type. We first tune the CNN architecture of [1] and find a design with four convolutional layers and two dense layers that gives an accuracy of approximately 83.8% at high SNR. We then develop architectures based on the recently introduced ideas of Residual Networks (ResNet [2]) and Densely Connected Networks (DenseNet [3]) to achieve high SNR accuracies of approximately 83.5% and 86.6%, respectively. Finally, we introduce a Convolutional Long Short-term Deep Neural Network (CLDNN [4]) to achieve an accuracy of approximately 88.5% at high SNR.