DMRF-UNet: A Two-Stage Deep Learning Scheme for GPR Data Inversion Under Heterogeneous Soil Conditions

Author:

Dai Qiqi1ORCID,Lee Yee Hui1ORCID,Sun Hai-Han1ORCID,Ow Genevieve2ORCID,Yusof Mohamed Lokman Mohd2ORCID,Yucel Abdulkadir C.1ORCID

Affiliation:

1. School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

2. National Parks Board, Singapore

Funder

Ministry of National Development Research Fund, National Parks Board, Singapore

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering

Reference36 articles.

1. A Machine Learning-Based Fast-Forward Solver for Ground Penetrating Radar With Application to Full-Waveform Inversion

2. Reinforced concrete mapping using full-waveform inversion of GPR data

3. Adam: A method for stochastic optimization;kingma;arXiv 1412 6980,2014

4. TensorFlow: A system for large-scale machine learning;abadi;Proc Second USENIX Symp Operating Systems Design and Implementation,2016

5. Gradient-based learning applied to document recognition

Cited by 21 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Tree Defect Reconstruction from Radar B-Scans via A Deep Learning Algorithm with Two-Stage Training;2024 IEEE INC-USNC-URSI Radio Science Meeting (Joint with AP-S Symposium);2024-07-14

2. A Deep Learning-Based Framework for Estimating Tree Defect Parameters via a Stand-Off Radar;2024 IEEE INC-USNC-URSI Radio Science Meeting (Joint with AP-S Symposium);2024-07-14

3. Real-time dual-parameter full-waveform inversion of GPR data based on robust deep learning;Geophysical Journal International;2024-07-08

4. Enhanced GPR Inversion Method in Complex Underground Environment;2024 Photonics & Electromagnetics Research Symposium (PIERS);2024-04-21

5. Advances in automatic identification of road subsurface distress using ground penetrating radar: State of the art and future trends;Automation in Construction;2024-02

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3