Balanced Semi-Supervised Generative Adversarial Network for Damage Assessment from Low-Data Imbalanced-Class Regime
This work addresses data and class imbalance issues in structural health monitoring, offering a domain-specific incremental improvement.
The paper tackled the problems of data deficiency and class imbalance in structural health monitoring by introducing a balanced semi-supervised GAN (BSS-GAN), which achieved better damage detection with improved recall and Fβ scores compared to conventional methods.
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, over-sampling, and under-sampling, 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 semi-supervised GAN (BSS-GAN). It adopts the semi-supervised 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.