Learning and Visualizing Modulation Discriminative Radio Signal Features

Abstract

In this work we explore the adaptation of convolutional autoencoders to complex-valued temporal domain radio signals. We propose a method for accomplishing online semi-supervised learning with a tied-weight convolutional autoencoder applied to a modulation classification task and provide some initial results. We also demonstrate a novel application of class activation maps (CAMs) to obtain interpretable visualizations of modulation-discriminative temporal structure in input signals. Finally, we show that our visualization method may be successfully applied to pre-trained models with negligible impact on classification performance on an automated modulation classification (AMC) task. This work was done as part of the BIAS (Biologically Inspired Autonomous Sensing) project, funded from the Naval Innovative Science and Engineering (NISE) Program.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2016
Accession Number
AD1022600

Entities

People

  • Benjamin Migliori
  • Daniel Gebhardt
  • Logan Straatemeier
  • Michael Walton

Organizations

  • Naval Information Warfare Systems Command

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Computer Languages
  • Computer Vision
  • Convolutional Neural Networks
  • Dimensionality Reduction
  • Governments
  • Information Processing
  • Information Science
  • Information Systems
  • Machine Learning
  • Modulation
  • Neural Networks
  • Orthogonal Frequency Division Multiplexing
  • Semi-Supervised Learning
  • Signal Processing
  • Supervised Machine Learning
  • United States Government

Fields of Study

  • Computer science

Readers

  • Military Science and Technology Research and Modernization.
  • Neural Network Machine Learning.
  • Radio communications and signal processing.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks