Over-the-Air Deep Learning Based Radio Signal Classification

By Tim O'Shea, Tamoghna Roy, T. Clancy. IEEE Journal on Selected Topics in Signal Processing, 2017

1,429 citations recorded by the source corpus.

We conduct an in  depth study on the performance of deep learning based radio signal classification for radio communications signals. We consider a rigorous baseline method using higher order moments and strong boosted gradient tree classification, and compare performance between the two approaches across a range of configurations and channel impairments. We consider the effects of carrier frequency offset, symbol rate, and multipath fading in simulation, and conduct over-the-air measurement of radio classification performance in the lab using software radios, and we compare performance and training strategies for both. Finally, we conclude with a discussion of remaining problems, and design considerations for using such techniques.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/612cc29c22b544fc329ed17c8d5e3b86a8fa1cd3

How researchers see this paper

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

In Artificial Intelligence

1. Zheng Dou
2. Yun Lin
3. Shiwen Mao
4. Erik G. Larsson
5. Meysam Sadeghi
6. Lei Chen
7. Ya Tu

In Signal Processing

1. Zheng Dou
2. Yun Lin
3. Shiwen Mao
4. Erik G. Larsson
5. Meysam Sadeghi
6. Lei Chen
7. Ya Tu

Citations in the corpus

• Adversarial Attacks on Deep-Learning Based Radio Signal Classification (2018, methodology): “For example, [3] uses a convolutional neural network (CNN) for channel decoding, [4] studies DL-based wireless resource allocation, and [5], [6] use DL for the classical task of radio signal (modulation) classification.”
• Modulation Classification Based on Signal Constellation Diagrams and Deep Learning (2019, neutral): “For modulation classification using the DL, there have been some reported work, including [6]–[12].”
• Contour Stella Image and Deep Learning for Signal Recognition in the Physical Layer (2020, background): “Moreover, wireless big data can be characterized by four major challenges: massive data, high dimension, rapid change, and quick response requirement [5]–[7].”