Deep neural network goes lighter: A case study of deep compression techniques on automatic RF modulation recognition for Beyond 5G networks

TL;DR

This paper explores deep neural network compression techniques to enable efficient RF modulation recognition on resource-constrained edge devices for beyond 5G networks, focusing on model acceleration and deployment.

Contribution

It provides an in-depth analysis of deep compression and acceleration methods tailored for RF modulation recognition in beyond 5G, emphasizing edge deployment.

Findings

Deep compression techniques significantly reduce model size.

Acceleration approaches improve computational efficiency.

Case study demonstrates practical deployment on radar modulation classification.

Abstract

Automatic RF modulation recognition is a primary signal intelligence (SIGINT) technique that serves as a physical layer authentication enabler and automated signal processing scheme for the beyond 5G and military networks. Most existing works rely on adopting deep neural network architectures to enable RF modulation recognition. The application of deep compression for the wireless domain, especially automatic RF modulation classification, is still in its infancy. Lightweight neural networks are key to sustain edge computation capability on resource-constrained platforms. In this letter, we provide an in-depth view of the state-of-the-art deep compression and acceleration techniques with an emphasis on edge deployment for beyond 5G networks. Finally, we present an extensive analysis of the representative acceleration approaches as a case study on automatic radar modulation classification and evaluate them in terms of the computational metrics.