Comparative Analysis of Attention Mechanisms for Automatic Modulation Classification in Radio Frequency Signals

TL;DR

This paper compares various attention mechanisms integrated with CNNs for automatic modulation classification of RF signals, highlighting trade-offs between accuracy and computational efficiency.

Contribution

It introduces a CNN-Transformer hybrid architecture and provides a detailed comparison of attention patterns for RF signal classification.

Findings

Baseline attention achieves 85.05% accuracy.

Causal and sparse attention reduce inference time by over 75%.

Different attention patterns are preferred for various modulation schemes.

Abstract

Automatic Modulation Classification (AMC) is a critical component in cognitive radio systems and spectrum management applications. This study presents a comprehensive comparative analysis of three attention mechanisms (i.e., baseline multi-head attention, causal attention, and sparse attention) integrated with Convolutional Neural Networks (CNNs) for radio frequency (RF) signal classification. It proposes a novel CNN-Transformer hybrid architecture that leverages different attention patterns to capture temporal dependencies in I/Q samples from the RML2016.10a dataset. The experimental results demonstrate that while baseline attention achieves the highest accuracy of 85.05\%, causal and sparse attention mechanisms offer significant computational advantages with inference times reduced by 83\% and 75\% respectively, while maintaining competitive classification performance above 84\%. The analysis reveals distinct attention pattern preferences across different modulation schemes, providing insights for designing efficient attention mechanisms for real-time radio signal processing applications.