Applying Generative Adversarial Networks to Intelligent Subsurface Imaging and Identification

Abstract

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 architecture 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 contributions, 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.

arXiv commentMaster's thesis, Networked Intelligence lab in the University of Tennessee at Chattanooga’s Sim Center (2019)

References in corpus (7)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Conditional Generative Adversarial Nets
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Improved Techniques for Training GANs
• YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers
• Introduction to Optimal Transport Theory