Date of Award:

8-2020

Document Type:

Dissertation

Degree Name:

Doctor of Philosophy (PhD)

Department:

Computer Science

Committee Chair(s)

Nicholas Flann

Committee

Nicholas Flann

Committee

Vicki Allan

Committee

Vladimir Kulyukin

Committee

Stephen Clyde

Committee

Tyler Brough

Abstract

Communications, bandwidth, security, and hardware simplicity are principles of interest to society at large. Recent advances in optics and in understanding properties of light, such as orbital angular momentum (OAM), have provided new potential mediums for communication.

Machine learning has wound its way into a broad range of fascinating areas. An emerging field of research is the use of a unique property of lasers called orbital angular momentum (OAM). With the proper hardware, a laser can go from a Gaussian shaped distribution to a doughnut shaped pattern, where the radius can be changed. Multiple OAM patterns, or modes, can be combined to create unique patterns. This research explores the use of machine learning to de-multiplex OAM patterns. The OAM patterns can be used to encode bits for communication.

This work explores ways to improve pattern recognition or classification in both underwater and free-space environments. Specifically, various approaches are applied to train convolutional neural networks to make them more robust to signal degradation through turbulence and attenuation. A new image transform is used to improve OAM pattern classification. Finally, some of the state of the art deep convolutional neural networks are explored to see which provide the most robust performance in free-space and underwater communications. A variety of methods are shown to improve the state of the art in pattern classification in OAM communications.

Checksum

d9742604d1589772511e5b6c9355cb88

Download

Share

COinS

Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .