Applying generative adversarial networks to intelligent subsurface imaging and identification

To augment training data for machine learning models in Ground Penetrating Radar (GPR) data classification and identification, this thesis focuses on the generation of realistic GPR data using Generative Adversarial Networks. An innovative GAN ar- chitecture is proposed for generating GPR B-scans, which is, to the author’s knowledge, the first successful application of GAN to GPR B-scans. As one of the major contri- butions, a novel loss function is formulated by merging frequency domain with time domain features. To test the efficacy of generated B-scans, a real time object classifier is proposed to measure the performance gain derived from augmented B-Scan images. The numerical experiment illustrated that, based on the augmented training data, the proposed GAN architecture demonstrated a significant increase (from 82% to 98%) in the accuracy of the object classifier.

Grantor dc:publisher

University of Tennessee at Chattanooga

Author dc:creator

• Rice, William

Contributors dc:contributor

• Wu, Dalei
• Liang, Yu; Yang, Li
• College of Engineering and Computer Science

• Ground penetrating radar
• Neural networks (Computer science)

Licence

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

Language dc:language

English, eng

Repository record dc:identifier

https://scholar.utc.edu/theses/595

OAI identifier oai:identifier

oai:scholar.utc.edu:theses-1756