Deep architectures for modulation recognition

By Nathan E. West, Tim O'Shea. International Symposium on Dynamic Spectrum Access Networks, 2017

516 citations recorded by the source corpus.

We survey the latest advances in machine learning with deep neural networks by applying them to the task of radio modulation recognition. Results show that ratio modulation recognition is not limited by network depth and further work should focus on improving learned synchronization and equalization. Advances in these areas will likely come from novel architectures designed for these tasks or through novel training methods.

Subfields: Aerospace Engineering, Artificial Intelligence, Genetics

View Paper: https://www.semanticscholar.org/paper/e9253bf2ff09858a0dc07293071225e9a1d1d534

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Artificial Intelligence

In Genetics

Citations in the corpus

Over-the-Air Deep Learning Based Radio Signal Classification (2017, background): “In [34], RNs for timeseries radio classification is investigated, and seen to train in fewer epochs, but not to provide significant performance improvements in terms of accuracy.”
Deep Learning in Mobile and Wireless Networking: A Survey (2018, background): “Deep learning was also employed in [217], [233], [468] and [77], where the authors employ CNNs and LSTMs to perform mobile traffic forecasting.”
Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors (2017, methodology): “The two layer CNN 8 tap model presented in [15] is used”
A Spatiotemporal Multi-Channel Learning Framework for Automatic Modulation Recognition (2020, methodology): “In the ﬁrst experiment, we compared the MCLDNN against six SoA algorithms from [5], [6], [7], [9], [12], [13] named as CNN-IQ, LSTM2, CLDNN, 1DCNN-PF, CNN4, and GRU2, respectively.”