SORTING OF RADIO SIGNALS USING ADVERSARIAL MACHINE LEARNING
Loading...
Authors
Valeske, Jessica M.
Subjects
generative adversarial networks
GAN
identification and classification of signals
radio frequency
RF
GAN
identification and classification of signals
radio frequency
RF
Advisors
Kragh, Frank E.
Scrofani, James W.
Date of Issue
2022-12
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
Signals Intelligence depends on signal classification accuracy. Artificial intelligence is a tool that allows for the fast and accurate identification of communications signals. Neural networks utilize a set of training data to learn patterns in datasets for recognition and classification. This learning is pivotal to the performance of the neural network and is dependent on the accuracy of the training data used to train. In this thesis, a strong and realistic communications training dataset is developed using MATLAB. It incorporates realistic and real-world factors that more accurately represent a radio frequency (RF) communication signal, then tests the neural network against the newly developed signals to prove the accuracy of the technology. The dataset is also varied in modulation type to fully represent the spectrum of signals to be analyzed by the neural networks.
Type
Thesis
Description
Series/Report No
Department
Electrical and Computer Engineering (ECE)
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Approved for public release. Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.