Dissertation/Thesis Abstract

Machine Learning Demodulator Architectures for Power-Limited Communications
by Gorday, Paul E., Ph.D., Florida Atlantic University, 2020, 185; 28023894
Abstract (Summary)

The success of deep learning has renewed interest in applying neural networks and other machine learning techniques to most fields of data and signal processing, including communications. Advances in architecture and training lead us to consider new modem architectures that allow flexibility in design, continued learning in the field, and improved waveform coding. This dissertation examines neural network architectures and training methods suitable for demodulation in power-limited communication systems, such as those found in wireless sensor networks. Such networks will provide greater connection to the world around us and are expected to contain orders of magnitude more devices than cellular networks. A number of standard and proprietary protocols span this space, with modulations such as frequency-shift-keying (FSK), Gaussian FSK (GFSK), minimum shift keying (MSK), on-off-keying (OOK), and M-ary orthogonal modulation (M-orth). These modulations enable low-cost radio hardware with efficient nonlinear amplification in the transmitter and noncoherent demodulation in the receiver.

The dissertation proposes a novel complex neural network demodulator architecture suitable for such systems. Mathematical derivation of the backpropagation equations for the proposed architecture provides insights into its applicability to either coherent or noncoherent demodulation, and experimental results demonstrate its performance and suitability for a variety of modulation formats. When trained in nominal AWGN channel conditions, the proposed architecture learns comparable, and in some cases better, performance than traditional demodulators. It is also flexible enough to learn improved tolerance to radio or channel impairments that are difficult or intractable to include in mathematical derivations. When combined with a trainable modulator, the proposed demodulator can also learn new, spectrally efficient waveform coding tailored to a specific channel. An added benefit of the proposed architecture is continued learning in the field, and we examine the challenges of incremental learning and identify areas of future research. It is hoped that this work will lead to a future common demodulator architecture that can support the wide range of modulation formats in this space and realize the additional benefits offered by machine learning.

Indexing (document details)
Advisor: Erdol, Nurgun
Commitee: Zhuang, Hanqi, Aalo, Valentine, Zhu, Xingquan
School: Florida Atlantic University
Department: Electrical Engineering
School Location: United States -- Florida
Source: DAI-B 82/2(E), Dissertation Abstracts International
Subjects: Electrical engineering, Operations research, Computer science
Keywords: Communication theory, Complex-valued, Demodulation, Machine learning, Neural networks, Signal processing
Publication Number: 28023894
ISBN: 9798664729627
Copyright © 2020 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy