Automated extraction and evaluation of fracture trace maps from rock tunnel face images via deep learning

Author(s):  
Jiayao Chen ◽  
Mingliang Zhou ◽  
Hongwei Huang ◽  
Dongming Zhang ◽  
Zhicheng Peng
2020 ◽  
Vol 120 ◽  
pp. 103371 ◽  
Author(s):  
Jiayao Chen ◽  
Dongming Zhang ◽  
Hongwei Huang ◽  
Mahdi Shadabfar ◽  
Mingliang Zhou ◽  
...  

Author(s):  
Amal A. Moustafa ◽  
Ahmed Elnakib ◽  
Nihal F. F. Areed

This paper presents a methodology for Age-Invariant Face Recognition (AIFR), based on the optimization of deep learning features. The proposed method extracts deep learning features using transfer deep learning, extracted from the unprocessed face images. To optimize the extracted features, a Genetic Algorithm (GA) procedure is designed in order to select the most relevant features to the problem of identifying a person based on his/her facial images over different ages. For classification, K-Nearest Neighbor (KNN) classifiers with different distance metrics are investigated, i.e., Correlation, Euclidian, Cosine, and Manhattan distance metrics. Experimental results using a Manhattan distance KNN classifier achieves the best Rank-1 recognition rate of 86.2% and 96% on the standard FGNET and MORPH datasets, respectively. Compared to the state-of-the-art methods, our proposed method needs no preprocessing stages. In addition, the experiments show its privilege over other related methods.


Author(s):  
Thomas E. Tavolara ◽  
Metin N. Gurcan ◽  
Scott Segal ◽  
Muhammad Khalid Khan Niazi
Keyword(s):  

2020 ◽  
Vol 10 (19) ◽  
pp. 6764
Author(s):  
Chunde Ma ◽  
Weibin Xie ◽  
Zelin Liu ◽  
Qiyue Li ◽  
Jiaqing Xu ◽  
...  

In this paper, the aim is to achieve safe, rapid excavation of an extra-long, large-cross-section highway tunnel in Eastern Tianshan, as well as to reduce production costs, simplify production processes, reduce cycle time, and improve production efficiency. In this study, we explored a new technology for smooth blasting without a detonating cord. A series of sympathetic detonation experiments were conducted in the tunnel face to determine critical distances. The critical distance for No. 2 rock emulsion explosive under blasthole constraints was successfully measured to be approximately 1.0–1.1 m. Based on the critical distance, a new charging structure was designed for tunnel excavation. To assess the influence of the new charging structure on blasting performance, its economic benefits, and its feasibility, full-section tests were performed in the East Tianshan Tunnel. The application of the new charging structure produced good smooth blasting results. It not only simplified the charging process and produced smooth blasting without detonating cord in peripheral holes, but also guaranteed normal excavation, an appropriate tunnel profile, and reasonable overbreak and underbreak volumes. This had remarkable economic benefits and possesses better promotional value.


2021 ◽  
Vol 12 (1) ◽  
pp. 395-404 ◽  
Author(s):  
Jiayao Chen ◽  
Tongjun Yang ◽  
Dongming Zhang ◽  
Hongwei Huang ◽  
Yu Tian

2011 ◽  
Vol 80-81 ◽  
pp. 506-510
Author(s):  
Jun Lu ◽  
Shao Wei Hu ◽  
Xiang Qian Fan ◽  
Zhi Guo Niu

In combination with a certain road tunnel instance Ningwu Highway,a working face rock ahead of forecast model is established. The prediction criterions include the Working face of rock radar images coefficient factor rock tunnel face conditions and the tunnel observation and analysis of geological factors are determined in the article. Their evaluation indexes are determined by the principle of which degree comes close and judged by experts. Finally the prediction results are came up through the fuzzy comprehensive evaluation and compared with the indexes of the degree of stability. Then it can make the prediction conclusion. The result shows that the model is convenient to use in practice very well. So it is proved that this prediction model is reliable.


2019 ◽  
Author(s):  
Lucas Fontes Buzuti ◽  
Carlos Eduardo Thomaz

The goal of this paper is to implement and compare two unsupervised models of deep learning: Autoencoder and Convolutional Autoencoder. These neural network models have been trained to learn regularities in well-framed face images with different facial expressions. The Autoencoder's basic topology is addressed here, composed of encoding and decoding multilayers. This paper approaches these automatic codings using multivariate statistics to visually understand the bottleneck differences between the fully-connected and convolutional layers and the corresponding importance of the dropout strategy when applied in a model.


Sign in / Sign up

Export Citation Format

Share Document