Automatic modulation recognition based on CNN and GRU

Fugang Liu

doi:10.26599/TST.2020.9010057

Automatic modulation recognition based on CNN and GRU

2022-04-01

35

OA

AI

DOI：10.26599/TST.2020.9010057

原文链接

原文求助

摘要

En 中文

Based on a comparative analysis of the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, we optimize the structure of the GRU network and propose a new modulation recognition method based on feature extraction and a deep learning algorithm. High-order cumulant, Signal-to-Noise Ratio (SNR), instantaneous feature, and the cyclic spectrum of signals are extracted firstly, and then input into the Convolutional Neural Network (CNN) and the parallel network of GRU for recognition. Eight modulation modes of communication signals are recognized automatically. Simulation results show that the proposed method can achieve high recognition rate at low SNR.

Keyword:

modulation recognition

deep learning

Gated Recurrent Unit (GRU)

Convolutional Neural Network (CNN)

Automatic modulation recognition based on CNN and GRU

摘要

期刊

机构

引用论文