# An Automatic Modulation Recognition Method Based on the Multimodal Kernel Harmonic Feature Fusion Network

## TL;DR

This paper introduces a new method for recognizing signal modulations in noisy environments using a fusion network that improves accuracy.

## Contribution

A novel multimodal kernel harmonic feature fusion network is proposed for robust modulation recognition in impulse noise.

## Key findings

- A time–frequency analysis method based on kernel space mapping improves feature distinguishability under impulse noise.
- The fusion network combines CNNs and GCNs to extract and fuse features from three modalities.
- Simulation results show a 93.5% modulation recognition rate at a −2 dB signal-to-noise ratio.

## Abstract

In increasingly complex electromagnetic environments, wireless communication systems face the severe challenge of non-Gaussian impulse noise. The moments of impulse noise tend toward infinity, reducing the distinguishability of signal features and thereby limiting improvements in signal modulation recognition rates. First, a time–frequency analysis method based on kernel space mapping is proposed to improve the distinguishability of time–frequency features in signals under impulse noise. On this basis, a multimodal kernel harmonic feature fusion network is constructed, combining convolutional neural networks and graph convolutional networks to extract and fuse kernel harmonic features from three modalities to achieve robust and accurate modulation recognition. The simulation results show a generalized signal-to-noise ratio of −2 dB, and the modulation recognition rate reaches 93.5%.