Balanced semisupervised generative adversarial network for damage assessment from low‐data imbalanced‐class regime: Fid-Bau Portal

Fachinformationsdienst BAUdigital

A platform for research: civil engineering, architecture and urbanism

Balanced semisupervised generative adversarial network for damage assessment from low‐data imbalanced‐class regime

Gao, Yuqing / Zhai, Pengyuan / Mosalam, Khalid M.

In recent years, applying deep learning (DL) to assess structural damages has gained growing popularity in vision‐based structural health monitoring (SHM). However, both data deficiency and class imbalance hinder the wide adoption of DL in practical applications of SHM. Common mitigation strategies include transfer learning, oversampling, and undersampling, yet these ad hoc methods only provide limited performance boost that varies from one case to another. In this work, we introduce one variant of the generative adversarial network (GAN), named the balanced semisupervised GAN (BSS‐GAN). It adopts the semisupervised learning concept and applies balanced‐batch sampling in training to resolve low‐data and imbalanced‐class problems. A series of computer experiments on concrete cracking and spalling classification were conducted under the low‐data imbalanced‐class regime with limited computing power. The results show that the BSS‐GAN is able to achieve better damage detection in terms of recall and $F_{β}$ score than other conventional methods, indicating its state‐of‐the‐art performance.

Access

Check availability in my library

Order at Subito €

Page navigation

Document information

Export, share and cite

Balanced semisupervised generative adversarial network for damage assessment from low‐data imbalanced‐class regime

Gao, Yuqing / Zhai, Pengyuan / Mosalam, Khalid M.

In recent years, applying deep learning (DL) to assess structural damages has gained growing popularity in vision‐based structural health monitoring (SHM). However, both data deficiency and class imbalance hinder the wide adoption of DL in practical applications of SHM. Common mitigation strategies include transfer learning, oversampling, and undersampling, yet these ad hoc methods only provide limited performance boost that varies from one case to another. In this work, we introduce one variant of the generative adversarial network (GAN), named the balanced semisupervised GAN (BSS‐GAN). It adopts the semisupervised learning concept and applies balanced‐batch sampling in training to resolve low‐data and imbalanced‐class problems. A series of computer experiments on concrete cracking and spalling classification were conducted under the low‐data imbalanced‐class regime with limited computing power. The results show that the BSS‐GAN is able to achieve better damage detection in terms of recall and $F_{β}$ score than other conventional methods, indicating its state‐of‐the‐art performance.

Balanced semisupervised generative adversarial network for damage assessment from low‐data imbalanced‐class regime

Gao, Yuqing / Zhai, Pengyuan / Mosalam, Khalid M.

In recent years, applying deep learning (DL) to assess structural damages has gained growing popularity in vision‐based structural health monitoring (SHM). However, both data deficiency and class imbalance hinder the wide adoption of DL in practical applications of SHM. Common mitigation strategies include transfer learning, oversampling, and undersampling, yet these ad hoc methods only provide limited performance boost that varies from one case to another. In this work, we introduce one variant of the generative adversarial network (GAN), named the balanced semisupervised GAN (BSS‐GAN). It adopts the semisupervised learning concept and applies balanced‐batch sampling in training to resolve low‐data and imbalanced‐class problems. A series of computer experiments on concrete cracking and spalling classification were conducted under the low‐data imbalanced‐class regime with limited computing power. The results show that the BSS‐GAN is able to achieve better damage detection in terms of recall and $F_{β}$ score than other conventional methods, indicating its state‐of‐the‐art performance.

Access

Check availability in my library

Order at Subito €

Page navigation

Document information

Export, share and cite

Document information

Title:

Balanced semisupervised generative adversarial network for damage assessment from low‐data imbalanced‐class regime

Contributors:

Gao, Yuqing (author) / Zhai, Pengyuan (author) / Mosalam, Khalid M. (author)

Published in:

Computer‐Aided Civil and Infrastructure Engineering ; 36 ; 1094-1113

Publication date:

2021-09-01

Size:

20 pages

ISSN:

1093-9687 , 1467-8667

DOI:

https://doi.org/10.1111/mice.12741

Type of media:

Article (Journal)

Type of material:

Electronic Resource

Language:

English

Similar titles

Generative adversarial network for road damage detection

Maeda, Hiroya / Kashiyama, Takehiro / Sekimoto, Yoshihide et al. | Wiley | 2021

An improved bidirectional generative adversarial network model for multivariate estimation of correlated and imbalanced tunnel construction parameters

Yao Xiao / Jia Yu / Guoxin Xu et al. | DOAJ | 2023

Free access

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

Hyunkyu Shin / Yonghan Ahn / Sungho Tae et al. | DOAJ | 2021

Free access

Data-augmented landslide displacement prediction using generative adversarial network

Qi Ge / Jin Li / Suzanne Lacasse et al. | DOAJ | 2024

Free access

Conditional Generative Adversarial Networks with Adversarial Attack and Defense for Generative Data Augmentation

Baek, Francis / Kim, Daeho / Park, Somin et al. | ASCE | 2022