相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Engineering, Chemical
Chenjie Gong et al.
Summary: Steel fibers can improve the packing density of aggregates in concrete mixtures, but little research has been done on the packing of single and hybrid steel fiber-aggregate mixtures. This study measured the loosely-packed packing density of 36 SF-A mixtures and 36 HF-A mixtures using a high-rigidity container. The results showed that the packing density decreased with increasing fiber volume, and the size ratio of steel fiber to aggregate particle played a crucial role. A prediction model considering the relative size of fiber and aggregate was developed, and the synergistic effect of hybrid fibers was also incorporated into the model. The model parameters were calibrated, and the prediction errors were evaluated to be less than 1%.
Article
Engineering, Civil
Zhong Zhou et al.
Summary: A novel detection approach for tunnel lining crack based on pruned YOLOv4 and enhanced WGAN-RE was proposed to address the challenges of insufficient data samples and low detection efficiency. The results demonstrate significant improvements in storage space and detection speed with the pruned YOLOv4 model, which also outperforms other methods in terms of model accuracy and efficiency.
Article
Computer Science, Interdisciplinary Applications
Jun Chen et al.
Summary: This paper proposes a novel neural network for the detection and evaluation of road cracks at pixel level, which can accurately and efficiently extract crack pixels and successfully realize the quantitative estimation of crack geometry.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Zifeng Wang et al.
Summary: The research team tackled the challenge of visual understanding on construction sites by collecting and labeling a large number of images and utilizing deep learning models for segmentation. They employed various data augmentation techniques and fine-tuned the model on their actual dataset post pretraining. Additionally, they developed a robotic system integrated with an RGB-depth camera for detecting depth information and automated construction on sites, showing great potential in visual surveillance applications.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Yi-zhou Lin et al.
Summary: This paper addresses the cross-domain SDD problem by designing a feature-extractor to generate damage-sensitive and domain-invariant features, and training a domain adaptation neural network on both numerical model and real structure data. The proposed method outperforms the traditional convolutional neural network in numerical and laboratory experiments, providing a new methodology to learn better features for structural damage detection.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Mateusz Zarski et al.
Summary: This study proposes a novel method that combines pruning and transfer learning techniques, called "finicky transfer learning," which can reduce energy consumption and computing demands while ensuring accuracy. By utilizing the Jaccard similarity coefficient to calculate the relationship between activation maps and masks obtained from semantic segmentation, convolutional neural networks can perform well in crack classification tasks.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Chao Liu et al.
Summary: This paper proposes a method for normalizing pavement images taken at night, including steps such as image feature detection and matching, image-to-image translation model training, and convolutional neural network construction. The detection performance of the CNN model can be significantly improved by using the proposed method to convert night images into day images.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Firdes Celik et al.
Summary: This paper provides a concrete crack dataset and proposes two solutions for automatic recognition and segmentation of cracks. The first solution uses a special network architecture and enhances performance by improving the activation function. The second solution utilizes transfer learning for kernel initialization and improves model performance by generating semi-synthetic images.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Zhong Zhou et al.
Summary: This research proposes a deep learning-based model, YOLOv4-ED, to solve the challenges in traditional tunnel lining defect detection methods. By using EfficientNet as the backbone and introducing DSC, YOLOv4-ED achieves higher detection accuracy and efficiency. A tunnel lining defect detection platform (TLDDP) is built based on the robust and cost-effective YOLOv4-ED, enabling automated detection of various lining defects.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Engineering, Mechanical
Shuoshuo Xu et al.
Summary: This study investigates the characteristics and causes of tunnel failure in water-rich strata using radar scanning, drilling, and laser scanning methods. The results reveal that water-rich strata, expansive soil, and the development of surrounding rock joints are the main factors causing the failure of the Jizhao tunnel. A comprehensive set of solutions was proposed and applied successfully to address cracks, water seepage, and inverted uplift in the tunnel.
ENGINEERING FAILURE ANALYSIS
(2022)
Article
Mechanics
Stephane d'Ascoli et al.
Summary: In this paper, a new architecture called ConViT is introduced, which combines the advantages of convolutional networks and self-attention mechanisms, achieving better performance and sample efficiency in image classification tasks. The role of locality in learning is also investigated, and various ablations are performed to better understand the success of ConViT.
JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT
(2022)
Article
Construction & Building Technology
Elyas Asadi Shamsabadi et al.
Summary: This research proposes a ViT-based framework for crack detection on asphalt and concrete surfaces, achieving enhanced real-world crack segmentation performance through transfer learning and IoU loss function. Compared to CNN-based models, TransUNet with a CNN-ViT backbone shows better average IoU on small and multiscale crack semantics and ViT helps the encoder-decoder network exhibit robust performance against various noisy signals.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Construction & Building Technology
Wenjun Wang et al.
Summary: In this study, a novel SegCrack model for pixel-level crack segmentation using deep learning methods is proposed. The model utilizes a hierarchically structured Transformer encoder to output multiscale features and incorporates a top-down pathway and lateral connections for progressive feature upsampling and fusion. An online hard example mining strategy is also adopted to improve model performance. Experimental results demonstrate SegCrack achieves high precision, recall, F1 score, and mean intersection over union on the test set.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Computer Science, Interdisciplinary Applications
Honghu Chu et al.
Summary: This study proposes a multiscale feature fusion network named Tiny-Crack-Net (TCN) to address the class imbalance and limited local receptive field issues in crack segmentation. By modifying the residual network, incorporating dual attention modules, and implementing multiscale fusion operations, the network's ability to segment tiny cracks is significantly enhanced. Evaluation on an open-source dataset and field test results validate the effectiveness and robustness of Tiny-Crack-Net.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Yang Liu et al.
Summary: A method based on the baseline model of the visual characteristics of images (BMVCI) is proposed to detect cracks in concrete structures. Compared with edge detection methods, BMVCI expands the quasi-distance between crack edges and image background, improving crack detection accuracy. Moreover, the method achieves higher computational efficiency and accuracy compared to deep learning methods.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Xiongyao Xie et al.
Summary: This study proposes a deep learning-based model called sparse-sensing and superpixel-based segmentation (SSSeg) for accurate and efficient crack segmentation. The SSSeg outperforms other models in accuracy and efficiency.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Shihao Dong et al.
Summary: This study proposes a method for reconstructing pavement macrotexture from monocular images using deep convolutional neural networks. A pavement texture RGB-D dataset is established from samples fabricated in the laboratory, and different training strategies are discussed. The results show that the proposed CNN can accurately reconstruct the macrotexture, and the reconstructed macrotexture has a high correlation with the benchmarks.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Yue Zheng et al.
Summary: This paper proposes an application-oriented multistage framework, CAL-ISM, for crack recognition and width measurement in bridge health monitoring. The performance of CAL-ISM is validated through practical applications, demonstrating its high potential for bridge health monitoring.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Construction & Building Technology
Chenjie Gong et al.
Summary: Water leakage in shield tunnels affects structural performance by changing load distribution and stress state. This study proposes a numerical approach to simulate localized leakage, finding that the seepage rate significantly affects internal forces, settlement, and ground settlement of tunnel structures.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2022)
Article
Geochemistry & Geophysics
Yaomin He et al.
Summary: This article proposes two ship target detection methods based on ESPRIT, using rotational invariance technique for the single-vector sensor model and spatial-invariant and time-invariant technique for the multivector sensor model. It also introduces the concept of polarization spectrum to estimate the polarization parameters when the number of scattering waves is unknown. The efficiency of the proposed methods is demonstrated through Monte Carlo simulation.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Wen Wang et al.
Summary: Detection transformers show competitive performance on the COCO dataset, but suffer from performance drops on small-size datasets. To address this issue, improvements are made to the model and a label augmentation method is introduced, resulting in improved performance on both small-size and sample-rich datasets.
COMPUTER VISION, ECCV 2022, PT IX
(2022)
Article
Remote Sensing
Zhengsen Xu et al.
Summary: This paper proposes a locally enhanced Transformer network (LETNet) for efficient detection of pavement cracks. By utilizing Transformer to model long-range dependencies, designing convolution stem and local enhancement modules to compensate both low-level and high-level local features, and using skip connection strategy and efficient upsampling module to restore detailed information, LETNet outperforms four advanced deep learning-based models in terms of both efficiency and effectiveness.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Computer Science, Artificial Intelligence
Rodrigo Naranjo et al.
Summary: A new method is proposed to measure the distance between fuzzy singletons (FSNs) by converting them into generalized trapezoidal fuzzy numbers (GTFNs) and applying an existing distance measure. This new measure demonstrates better performance in predicting trading outcomes and obtaining larger profits compared to traditional Euclidean distance measurement in a fuzzy forecasting trading system.
INTEGRATED COMPUTER-AIDED ENGINEERING
(2021)
Article
Construction & Building Technology
Shuai Zhao et al.
Summary: This paper presents a deep learning-based approach that extends the PANet model by adding a semantic branch to refine crack evaluation and reduce inaccuracies associated with crack discontinuities and image skeletonization. Experimental results show that the proposed approach outperforms other methods, demonstrating its superiority in mitigating crack disjoint problems and skeletonization error. The evaluation metrics indicate that the proposed model is an alternative approach for crack segmentation and quantification in the field.
AUTOMATION IN CONSTRUCTION
(2021)
Article
Computer Science, Artificial Intelligence
Nadir Kamel Benamara et al.
Summary: This study proposes a facial emotion recognition system that achieves state-of-the-art performance by utilizing deep convolutional neural networks and label smoothing technique to handle miss-labelled training data. The system can recognize facial emotions in just 13.48 ms (GPU) and 141.97 ms (CPU).
INTEGRATED COMPUTER-AIDED ENGINEERING
(2021)
Article
Engineering, Mechanical
Chang Liu et al.
Summary: Lining damage in mountain tunnels affects the bearing capacity and service life, therefore, investigation and treatment of lining damage are crucial for safety and longevity. Through field investigation, numerical simulation, and in-situ monitoring, characteristics and treatment measures of lining damage can be understood to enhance tunnel performance.
ENGINEERING FAILURE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Naishi Feng et al.
Summary: Decoding brain intentions from noninvasively measured neural signals is a hot topic in brain-computer interface (BCI) research, with a proposed method achieving a decoding accuracy of up to 92.81% in a four-class task using a graph convolutional network based on functional connectivity.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2021)
Article
Construction & Building Technology
Zhenwei Yu et al.
Summary: The YOLOv4-FPM model improves accuracy and speed by using focal loss and pruning algorithm to optimize the loss function and accelerate detection speed. It expands the detection range and is able to effectively detect cracks in images of different sizes.
AUTOMATION IN CONSTRUCTION
(2021)
Article
Construction & Building Technology
Dimitris Dais et al.
Summary: This study explores deep learning techniques for crack detection on masonry walls, achieving an accuracy of 95.3%. Leveraging transfer learning, crack segmentation on masonry surfaces at the pixel level was successfully implemented. This represents the first application of deep learning for pixel-level crack segmentation on masonry surfaces.
AUTOMATION IN CONSTRUCTION
(2021)
Article
Computer Science, Artificial Intelligence
Peizhen Peng et al.
Summary: This paper introduces a novel patient-specific method for predicting epileptic seizures, combining Fourier Neural Network (FNN) and Convolutional Neural Network (CNN) for efficient and practical results. By utilizing multi-layer modules and a deep neural network, the prediction of epileptic signals achieves high accuracy and sensitivity.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Yu Xue et al.
Summary: This paper introduces a novel NAS algorithm based on multi-objective modeling for designing accurate CNNs with small structures. The proposed algorithm utilizes a graph-based representation of solutions, includes novel ad-hoc crossover and mutation operators, and introduces a mechanism to accelerate the evaluation of candidate solutions. Experimental results demonstrate that the proposed NAS approach can design accurate neural networks with limited size.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Liang Gao et al.
Summary: The STransFuse model is a new method that combines Transformer and CNN for remote sensing image segmentation, utilizing an adaptive fusion module to extract features at different scales and fuse semantic information, achieving higher overall accuracy compared to the baseline.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Construction & Building Technology
Baoxian Li et al.
INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING
(2020)
Article
Computer Science, Artificial Intelligence
Danilo R. Pereira et al.
NEURAL COMPUTING & APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Kazi Md Rokibul Alam et al.
NEURAL COMPUTING & APPLICATIONS
(2020)
Article
Computer Science, Interdisciplinary Applications
Jianghua Deng et al.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2020)
Article
Computer Science, Interdisciplinary Applications
Seyed Omid Sajedi et al.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2020)
Article
Construction & Building Technology
Jun S. Lee et al.
STRUCTURAL CONTROL & HEALTH MONITORING
(2020)
Review
Computer Science, Artificial Intelligence
Guilherme Brandao Martins et al.
Article
Construction & Building Technology
Cao Vu Dung et al.
AUTOMATION IN CONSTRUCTION
(2019)
Article
Computer Science, Artificial Intelligence
Qin Zou et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Computer Science, Artificial Intelligence
Yahui Liu et al.
Article
Engineering, Geological
Mohammad Hossein Rafiei et al.
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING
(2017)
Article
Construction & Building Technology
Chenjie Gong et al.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2017)
Article
Construction & Building Technology
Wenqi Ding et al.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2017)
Article
Computer Science, Artificial Intelligence
Mohammad Hossein Rafiei et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Francois Chollet
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Construction & Building Technology
Mohammad Hossein Rafiei et al.
JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT
(2016)
Article
Construction & Building Technology
Mohammad Hossein Rafiei et al.
JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT
(2016)
Article
Computer Science, Interdisciplinary Applications
Chun Liu et al.
COMPUTERS & GEOSCIENCES
(2013)
Article
Computer Science, Artificial Intelligence
Bryan C. Russell et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2008)
