Committee Chair

Wu, Dalei

Committee Member

Liang, Yu; Yang, Li

Department

Dept. of Computer Science and Engineering

College

College of Engineering and Computer Science

Publisher

University of Tennessee at Chattanooga

Place of Publication

Chattanooga (Tenn.)

Abstract

This thesis focused on classifying GPR cylinders' B-scans according to their depth, size, material, and the dielectric constant of the underlying medium using four different architectures of convolutional neural networks. Two CNNs were newly proposed for this study, while the other two were used by other authors. These CNNs were trained using a couple of adjusted training options including initial learning rate, learn rate drop factor, and learn rate drop period; which had a positive impact on a part of the used models, while the option maximum number of epochs worked good with all of the used models. Results show that the first newly proposed CNN showed a superior performance due to the use of a deep network with a large amount of small filters. Using this model, it was found that the best results were carried out when GPR B-scans were classified according to the cylinders' materials.

Acknowledgments

I would like to thank Dr. Wu for his guidance and for giving me the chance to work under his supervision. It has been a great honor for me to work with him. My sincere appreciation also goes to my small family, siblings, friends, colleagues, and the staff of the Department of Computer Science and Engineering at the University of Tennessee at Chattanooga, who shared my enthusiasm and helped me go through disappointments. I also would like to thank the members of the committee Dr. Yu Liang, and Dr. Li Yang

Degree

M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science.

Date

5-2018

Subject

Ground penetrating radar; Neural networks (Computer science)

Keyword

Ground Penetrating Radar; GPR; Convolutional Neural Networks; CNN.

Document Type

Masters theses

DCMI Type

Text

Extent

xii, 50 leaves

Language

English

Rights

https://rightsstatements.org/page/InC/1.0/?language=en

License

http://creativecommons.org/licenses/by-nc/3.0/

Data.rar (520 kB)

Share

COinS