# RF Signal Classification with Synthetic Training Data and its Real-World Performance

arXiv: https://arxiv.org/abs/2206.12967 · HTML: https://mlsanity.com/paper/2206.12967/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 26 Jun 2022.

## Builds on (most cited first, 7 of 7)

- [Over the Air Deep Learning Based Radio Signal Classification](https://mlsanity.com/paper/1712.04578/) (2017)
- [Convolutional Radio Modulation Recognition Networks](https://mlsanity.com/paper/1602.04105/) (2016)
- [Fast Deep Learning for Automatic Modulation Classification](https://mlsanity.com/paper/1901.05850/) (2019)
- [Wireless Interference Identification with Convolutional Neural Networks](https://mlsanity.com/paper/1703.00737/) (2017)
- [Classification of Radio Signals and HF Transmission Modes with Deep Learning](https://mlsanity.com/paper/1906.04459/) (2019)
- [The RFML Ecosystem: A Look at the Unique Challenges of Applying Deep Learning to Radio Frequency Applications](https://mlsanity.com/paper/2010.00432/) (2020)
- [Training Data Augmentation for Deep Learning Radio Frequency Systems](https://mlsanity.com/paper/2010.00178/) (2020)

## Built on by (most cited first, 2 of 2)

- [Large Scale Radio Frequency Wideband Signal Detection & Recognition](https://mlsanity.com/paper/2211.10335/) (2022)
- [Large-Scale Classification of Shortwave Communication Signals with Machine Learning](https://mlsanity.com/paper/2504.05455/) (2025)

## Abstract (arXiv)

Neural nets are a powerful method for the classification of radio signals in the electromagnetic spectrum. These neural nets are often trained with synthetically generated data due to the lack of diverse and plentiful real RF data. However, it is often unclear how neural nets trained on synthetic data perform in real-world applications. This paper investigates the impact of different RF signal impairments (such as phase, frequency and sample rate offsets, receiver filters, noise and channel models) modeled in synthetic training data with respect to the real-world performance. For that purpose, this paper trains neural nets with various synthetic training datasets with different signal impairments. After training, the neural nets are evaluated against real-world RF data collected by a software defined radio receiver in the field. This approach reveals which modeled signal impairments should be included in carefully designed synthetic datasets. The investigated showcase example can classify RF signals into one of 20 different radio signal types from the shortwave bands. It achieves an accuracy of up to 95 % in real-world operation by using carefully designed synthetic training data only.