Table 5.

Methods for data augmentation in RFF identification

Methods Description Application scenarios Advantages Disadvantages
Traditional signal processing Use signal processing to simulate devicesamples in designed condition. Most in closed set problems
  • High explainability.

  • Low time consumption.

  • Easy to combine with other methods.

  • Narrow scope of application.

  • Dependence on prior information and expert knowledge.

GAN Train GAN model to generate device samples. Most in open set problems
  • The best sample quality.

  • Useful latent feature representation.

  • High complexity of design.

  • Unstable training results.

  • Low explainability.

Autoencoder Train Autoencoder model to generate device samples. Most in open set problems
  • Good sample quality.

  • Useful latent feature representation.

  • High complexity of design.

  • Low explainability.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.