Accession Number : AD1022600


Title :   Learning and Visualizing Modulation Discriminative Radio Signal Features


Descriptive Note : Technical Report


Corporate Author : Space and Naval Warfare Systems Center Pacific San Diego United States


Personal Author(s) : Walton,Michael ; Gebhardt,Daniel ; Migliori,Benjamin ; Straatemeier,Logan


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/1022600.pdf


Report Date : 01 Sep 2016


Pagination or Media Count : 24


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.


Descriptors :   semisupervised learning , signal processing , radio signals , coders , automation , artificial neural networks


Subject Categories : Operations Research
      Computer Systems Management and Standards
      Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE