Evaluation of Damage Level for Ground Settlement Using the Convolutional Neural Network

Sung Sik Park, Van Than Tran, Nhat Phi Doan, Keum Bee Hwang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

In this study, a convolutional neural network (CNN)-based deep learning was applied to evaluate settlement of the ground. Firstly, the database of 1200 images was captured and labeled for three classes of damage levels. Seven CNN architectures were then selected for the transfer learning, in which the highest accuracy of approximately 96.11% for the testing set was observed from the DenseNet121 architecture. Herein, a comparison in terms of accuracy with various optimizers-algorithms for optimizing the loss function in machine learning-have been implemented in the DenseNet121 architecture. The goal of this study is to propose a better architecture with higher accuracy for practical applications in geotechnical engineering using the CNN technique. The results indicated that the DenseNet121 architecture using the Adam optimizer performed the most effectively with accuracies of 97.59%, 95.00%, and 96.11% on training, validation, and testing sets, respectively.

Original languageEnglish
Title of host publicationCIGOS 2021, Emerging Technologies and Applications for Green Infrastructure - Proceedings of the 6th International Conference on Geotechnics, Civil Engineering and Structures
EditorsCuong Ha-Minh, Anh Minh Tang, Tinh Quoc Bui, Xuan Hong Vu, Dat Vu Khoa Huynh
PublisherSpringer Science and Business Media Deutschland GmbH
Pages1261-1268
Number of pages8
ISBN (Print)9789811671593
DOIs
StatePublished - 2022
Event6th International Conference on Geotechnics, Civil Engineering and Structures, CIGOS 2021 - Hạ Long Bay, Viet Nam
Duration: 28 Oct 202129 Oct 2021

Publication series

NameLecture Notes in Civil Engineering
Volume203
ISSN (Print)2366-2557
ISSN (Electronic)2366-2565

Conference

Conference6th International Conference on Geotechnics, Civil Engineering and Structures, CIGOS 2021
Country/TerritoryViet Nam
CityHạ Long Bay
Period28/10/2129/10/21

Keywords

  • Convolutional neural network (CNN)
  • Damage classification
  • Deep learning
  • Ground settlement

Fingerprint

Dive into the research topics of 'Evaluation of Damage Level for Ground Settlement Using the Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this