A Deep Generative Model for Synthesizing Labeled Wireless Signals

Yuxiao Li, Keke Hu, Santiago Mazuelas, Yuan Shen|September 4, 2026arXiv

Key Takeaway

Synthetic wireless signals generated by GANs can effectively replace expensive real-world data collection for training wireless sensing models, reducing labeling costs while maintaining physical realism.

Summary

This paper introduces IIns-GAN, a deep learning method that generates realistic labeled wireless signals for training machine learning models.

data training applications

Key Terms

generative-adversarial-network synthetic-data wireless-sensing ultra-wideband