Toward Channel Estimation with Conditional Generative Adversarial Networks
Abstract
The focus of this paper is to train Generative Adversarial Networks (GANs) on radio frequency (RF) datasets to learn the complex channel effects that can occur during RF transmission. Two different GANs were trained on paired and unpaired RF datasets with varying modulation schemes and channel effects to investigate the different GANs potential to learn the complex channel effects that can occur during RF transmission. An expert feature-based system, GNU Radio (physics-based modelling), was used to generate the synthetic RF transmit and receive dataset pairs. After training on the synthetic data, the conditional GANs produced output that qualitatively fit the training data. This is a first step toward training a GAN that can qualitatively and quantitatively reproduce the transformation between the transmitted RF data and the received RF signal. Ultimately this approach can be applied to a paired dataset recorded in real-world conditions.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2023
- Accession Number
- AD1210529
Entities
People
- Erich C. Walter
- Tanya G. Cheung
Organizations
- Naval Information Warfare Center Pacific