Details
| Original language | English |
|---|---|
| Pages (from-to) | 1311-1320 |
| Number of pages | 10 |
| Journal | Frontiers of Structural and Civil Engineering |
| Volume | 18 |
| Issue number | 9 |
| Early online date | 13 Aug 2024 |
| Publication status | Published - Sept 2024 |
Abstract
This paper proposes an accurate, efficient and explainable method for the classification of the surrounding rock based on a convolutional neural network (CNN). The state-of-the-art robust CNN model (EfficientNet) is applied to tunnel wall image recognition. Gaussian filtering, data augmentation and other data pre-processing techniques are used to improve the data quality and quantity. Combined with transfer learning, the generality, accuracy and efficiency of the deep learning (DL) model are further improved, and finally we achieve 89.96% accuracy. Compared with other state-of-the-art CNN architectures, such as ResNet and Inception-ResNet-V2 (IRV2), the presented deep transfer learning model is more stable, accurate and efficient. To reveal the rock classification mechanism of the proposed model, Gradient-weight Class Activation Map (Grad-CAM) visualizations are integrated into the model to enable its explainability and accountability. The developed deep transfer learning model has been applied to support the tunneling of the Xingyi City Bypass in the high mountain area of Guizhou, China, with great results.
Keywords
- convolutional neural network, EfficientNet, Gradient-weight Class Activation Map, surrounding rock classification
ASJC Scopus subject areas
- Engineering(all)
- Civil and Structural Engineering
- Engineering(all)
- Architecture
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Frontiers of Structural and Civil Engineering, Vol. 18, No. 9, 09.2024, p. 1311-1320.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Surrounding rock classification from onsite images with deep transfer learning based on EfficientNet
AU - Zhuang, Xiaoying
AU - Fan, Wenjie
AU - Guo, Hongwei
AU - Chen, Xuefeng
AU - Wang, Qimin
N1 - Publisher Copyright: © Higher Education Press 2024.
PY - 2024/9
Y1 - 2024/9
N2 - This paper proposes an accurate, efficient and explainable method for the classification of the surrounding rock based on a convolutional neural network (CNN). The state-of-the-art robust CNN model (EfficientNet) is applied to tunnel wall image recognition. Gaussian filtering, data augmentation and other data pre-processing techniques are used to improve the data quality and quantity. Combined with transfer learning, the generality, accuracy and efficiency of the deep learning (DL) model are further improved, and finally we achieve 89.96% accuracy. Compared with other state-of-the-art CNN architectures, such as ResNet and Inception-ResNet-V2 (IRV2), the presented deep transfer learning model is more stable, accurate and efficient. To reveal the rock classification mechanism of the proposed model, Gradient-weight Class Activation Map (Grad-CAM) visualizations are integrated into the model to enable its explainability and accountability. The developed deep transfer learning model has been applied to support the tunneling of the Xingyi City Bypass in the high mountain area of Guizhou, China, with great results.
AB - This paper proposes an accurate, efficient and explainable method for the classification of the surrounding rock based on a convolutional neural network (CNN). The state-of-the-art robust CNN model (EfficientNet) is applied to tunnel wall image recognition. Gaussian filtering, data augmentation and other data pre-processing techniques are used to improve the data quality and quantity. Combined with transfer learning, the generality, accuracy and efficiency of the deep learning (DL) model are further improved, and finally we achieve 89.96% accuracy. Compared with other state-of-the-art CNN architectures, such as ResNet and Inception-ResNet-V2 (IRV2), the presented deep transfer learning model is more stable, accurate and efficient. To reveal the rock classification mechanism of the proposed model, Gradient-weight Class Activation Map (Grad-CAM) visualizations are integrated into the model to enable its explainability and accountability. The developed deep transfer learning model has been applied to support the tunneling of the Xingyi City Bypass in the high mountain area of Guizhou, China, with great results.
KW - convolutional neural network
KW - EfficientNet
KW - Gradient-weight Class Activation Map
KW - surrounding rock classification
UR - http://www.scopus.com/inward/record.url?scp=85201303623&partnerID=8YFLogxK
U2 - 10.1007/s11709-024-1134-7
DO - 10.1007/s11709-024-1134-7
M3 - Article
AN - SCOPUS:85201303623
VL - 18
SP - 1311
EP - 1320
JO - Frontiers of Structural and Civil Engineering
JF - Frontiers of Structural and Civil Engineering
SN - 2095-2430
IS - 9
ER -