ReFormer: Generating Radio Fakes for Data Augmentation
This work addresses data scarcity for RF applications, but it is incremental as it applies existing transformer-based methods to a specific domain.
The paper tackles the problem of limited real-world radio-frequency (RF) data for applications like channel estimation by introducing ReFormer, a generative AI model that efficiently generates synthetic RF data for dataset augmentation, showing how design choices impact quality through metrics like precision, recall, and classification accuracy.
We present ReFormer, a generative AI (GAI) model that can efficiently generate synthetic radio-frequency (RF) data, or RF fakes, statistically similar to the data it was trained on, or with modified statistics, in order to augment datasets collected in real-world experiments. For applications like this, adaptability and scalability are important issues. This is why ReFormer leverages transformer-based autoregressive generation, trained on learned discrete representations of RF signals. By using prompts, such GAI can be made to generate the data which complies with specific constraints or conditions, particularly useful for training channel estimation and modeling. It may also leverage the data from a source system to generate training data for a target system. We show how different transformer architectures and other design choices affect the quality of generated RF fakes, evaluated using metrics such as precision and recall, classification accuracy and signal constellation diagrams.