English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

High-quality recordings of radio frequency (RF) emissions from commercialcommunication hardware in realistic environments are often needed to developand assess spectrum-sharing technologies and practices, e.g., for training andtesting spectrum sensing algorithms and for interference testing.Unfortunately, the time-consuming, expensive nature of such data collectionstogether with data-sharing restrictions pose significant challenges that limitdata set availability. Furthermore, developing accurate models of real-world RFemissions from first principles is often very difficult because systemparameters and implementation details are at best only partially known, andcomplex system dynamics are difficult to characterize. Hence, there is a needfor flexible, data-driven methods that can leverage existing data sets tosynthesize additional similar waveforms. One promising machine-learningapproach is unsupervised deep generative modeling with generative adversarialnetworks (GANs). To date, GANs for RF communication signals have not beenstudied thoroughly. In this paper, we present the first in-depth investigationof generated signal fidelity for GANs trained with baseband orthogonalfrequency-division multiplexing (OFDM) signals, where each subcarrier isdigitally modulated with quadrature amplitude modulation (QAM). Building onprior GAN methods, we developed two novel GAN models and evaluated theirperformance using simulated data sets with known ground truth. Specifically, weinvestigated model performance with respect to increasing data set complexityover a range of OFDM parameters and conditions, including fading channels. Thefindings presented here inform the feasibility of use cases and provide afoundation for further investigations into deep generative models for RFcommunication signals.

Feasibility of Modeling Orthogonal Frequency-Division Multiplexing Communication Signals with Unsupervised Generative Adversarial Networks