Transfer Learning for Automatic Modulation Recognition Using a Few Modulated Signal Samples

doi:10.1109/TVT.2023.3267270

Transfer Learning for Automatic Modulation Recognition Using a Few Modulated Signal Samples

2023-09-01

14

PRE

AI

DOI：10.1109/TVT.2023.3267270

Original

Original request for help

Save

Abstract

En 中文

This letter proposes a transfer learning model for automatic modulation recognition (AMR) with only a few modulated signal samples. The transfer model is trained with the audio signal UrbanSound8K as the source domain, and then fine-tuned with a few modulated signal samples as the target domain. For improving the classification performance, the signal-to-noise ratio (SNR) is utilized as a feature to facilitate the classification of signals. Simulation results indicate that the transfer model has a significant superiority in terms of classification accuracy.

Keywords:

Transfer learning

few-shot learning

automatic modulation recognition

convolutional neural network

deep learning

Transfer Learning for Automatic Modulation Recognition Using a Few Modulated Signal Samples

Abstract

Journal

Organization