Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 태성호 | - |
dc.date.accessioned | 2022-04-10T23:50:11Z | - |
dc.date.available | 2022-04-10T23:50:11Z | - |
dc.date.issued | 2021-11 | - |
dc.identifier.citation | SUSTAINABILITY; NOV 2021, 13 22, p12682 13p. | en_US |
dc.identifier.issn | 20711050 | - |
dc.identifier.uri | https://www.proquest.com/docview/2602263594?accountid=11283 | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/169819 | - |
dc.description.abstract | 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. | en_US |
dc.description.sponsorship | This work is supported by the Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport (Grant 21CTAP-C163951-01). | en_US |
dc.language.iso | en | en_US |
dc.publisher | MDPI | en_US |
dc.subject | generative adversarial network | en_US |
dc.subject | data augmentation | en_US |
dc.subject | defect recognition | en_US |
dc.subject | deep learning | en_US |
dc.subject | convolutional neural network | en_US |
dc.title | Enhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network | en_US |
dc.type | Article | en_US |
dc.relation.volume | 13 | - |
dc.identifier.doi | 10.3390/su132212682 | - |
dc.relation.page | 12682-12694 | - |
dc.relation.journal | SUSTAINABILITY | - |
dc.contributor.googleauthor | Shin, Hyunkyu | - |
dc.contributor.googleauthor | Ahn, Yonghan | - |
dc.contributor.googleauthor | Tae, Sungho | - |
dc.contributor.googleauthor | Gil, Heungbae | - |
dc.contributor.googleauthor | Song, Mihwa | - |
dc.contributor.googleauthor | Lee, Sanghyo | - |
dc.relation.code | 2021008680 | - |
dc.sector.campus | E | - |
dc.sector.daehak | COLLEGE OF ENGINEERING SCIENCES[E] | - |
dc.sector.department | SCHOOL OF ARCHITECTURE | - |
dc.identifier.pid | jnb55 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.