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.

Open PDF

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

Tags

Communities of Interest

  • Autonomy
  • Sensors

DTIC Thesaurus Topics

  • Channel Estimation
  • Channel Models
  • Computer Programs
  • Failure Mode And Effect Analysis
  • Frequency
  • Information Operations
  • Information Processing
  • Information Science
  • Information Systems
  • Information Warfare
  • Learning
  • Machine Learning
  • Military Research
  • Modulation
  • Neural Networks
  • Radio Frequency
  • Signal Processing
  • Training

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Radio communications and signal processing.
  • Regression Analysis.