Open AccessModulation classification based on denoising autoencoder and convolutional neural network with GNU radio
Author(s) -
Wang Jun,
Wang Wenfeng,
Luo Feixiang,
Wei Shaoming
Publication year - 2019
Publication title -
the journal of engineering
Language(s) - English
Resource type - Journals
ISSN - 2051-3305
DOI - 10.1049/joe.2019.0203
Subject(s) - autoencoder , noise reduction , convolutional neural network , computer science , artificial intelligence , pattern recognition (psychology) , signal (programming language) , artificial neural network , noise (video) , encoder , modulation (music) , feature (linguistics) , deep learning , physics , acoustics , linguistics , philosophy , image (mathematics) , programming language , operating system
In this article, a machine learning method to classify signal with Gaussian noise based on denoising auto encoder (DAE) and convolutional neural network (CNN) is proposed. We combine denoising autoencoder's denoising ability with CNN's feature extraction capability. First, a six‐layer neural network is built, including three CNN layers. Then a dataset containing noiseless signal of 11 modulation is generated. In the simulation, we apply this dataset to train neural network and achieve an accuracy of 94%, which is much higher than performance with noisy signal, meaning that noise can greatly influence the accuracy of neural network. Next, we build a denoising autoencoder and train it with signal of 5 dB signal‐to‐noise ratio (SNR). Compared with neural network without denoising autoencoder, adding a denoising autoencoder can achieve an accuracy of 84% at signal of 18 dB SNR, improved by 58%.