Enhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network

Recently, in the building and infrastructure fields, studies on defect detection methods using deep learning have been widely implemented. For robust automatic recognition of defects in buildings, a sufficiently large training dataset is required for the target defects. However, it is challenging to...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hyunkyu Shin, Yonghan Ahn, Sungho Tae, Heungbae Gil, Mihwa Song, Sanghyo Lee
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	generative adversarial network data augmentation defect recognition deep learning convolutional neural network Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/b9565b511d28407abd376d9ce7a1744d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b9565b511d28407abd376d9ce7a1744d
record_format	dspace
spelling	oai:doaj.org-article:b9565b511d28407abd376d9ce7a1744d2021-11-25T19:03:18ZEnhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network10.3390/su1322126822071-1050https://doaj.org/article/b9565b511d28407abd376d9ce7a1744d2021-11-01T00:00:00Zhttps://www.mdpi.com/2071-1050/13/22/12682https://doaj.org/toc/2071-1050Recently, in the building and infrastructure fields, studies on defect detection methods using deep learning have been widely implemented. For robust automatic recognition of defects in buildings, a sufficiently large training dataset is required for the target defects. However, it is challenging to collect sufficient data from degrading building structures. To address the data shortage and imbalance problem, in this study, a data augmentation method was developed using a generative adversarial network (GAN). To confirm the effect of data augmentation in the defect dataset of old structures, two scenarios were compared and experiments were conducted. As a result, in the models that applied the GAN-based data augmentation experimentally, the average performance increased by approximately 0.16 compared to the model trained using a small dataset. Based on the results of the experiments, the GAN-based data augmentation strategy is expected to be a reliable alternative to complement defect datasets with an unbalanced number of objects.Hyunkyu ShinYonghan AhnSungho TaeHeungbae GilMihwa SongSanghyo LeeMDPI AGarticlegenerative adversarial networkdata augmentationdefect recognitiondeep learningconvolutional neural networkEnvironmental effects of industries and plantsTD194-195Renewable energy sourcesTJ807-830Environmental sciencesGE1-350ENSustainability, Vol 13, Iss 12682, p 12682 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	generative adversarial network data augmentation defect recognition deep learning convolutional neural network Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
spellingShingle	generative adversarial network data augmentation defect recognition deep learning convolutional neural network Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350 Hyunkyu Shin Yonghan Ahn Sungho Tae Heungbae Gil Mihwa Song Sanghyo Lee Enhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network
description	Recently, in the building and infrastructure fields, studies on defect detection methods using deep learning have been widely implemented. For robust automatic recognition of defects in buildings, a sufficiently large training dataset is required for the target defects. However, it is challenging to collect sufficient data from degrading building structures. To address the data shortage and imbalance problem, in this study, a data augmentation method was developed using a generative adversarial network (GAN). To confirm the effect of data augmentation in the defect dataset of old structures, two scenarios were compared and experiments were conducted. As a result, in the models that applied the GAN-based data augmentation experimentally, the average performance increased by approximately 0.16 compared to the model trained using a small dataset. Based on the results of the experiments, the GAN-based data augmentation strategy is expected to be a reliable alternative to complement defect datasets with an unbalanced number of objects.
format	article
author	Hyunkyu Shin Yonghan Ahn Sungho Tae Heungbae Gil Mihwa Song Sanghyo Lee
author_facet	Hyunkyu Shin Yonghan Ahn Sungho Tae Heungbae Gil Mihwa Song Sanghyo Lee
author_sort	Hyunkyu Shin
title	Enhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network
title_short	Enhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network
title_full	Enhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network
title_fullStr	Enhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network
title_full_unstemmed	Enhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network
title_sort	enhancement of multi-class structural defect recognition using generative adversarial network
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b9565b511d28407abd376d9ce7a1744d
work_keys_str_mv	AT hyunkyushin enhancementofmulticlassstructuraldefectrecognitionusinggenerativeadversarialnetwork AT yonghanahn enhancementofmulticlassstructuraldefectrecognitionusinggenerativeadversarialnetwork AT sunghotae enhancementofmulticlassstructuraldefectrecognitionusinggenerativeadversarialnetwork AT heungbaegil enhancementofmulticlassstructuraldefectrecognitionusinggenerativeadversarialnetwork AT mihwasong enhancementofmulticlassstructuraldefectrecognitionusinggenerativeadversarialnetwork AT sanghyolee enhancementofmulticlassstructuraldefectrecognitionusinggenerativeadversarialnetwork
_version_	1718410360544821248

Enhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network

Ejemplares similares