A5100711694- Rock Mechanics and Modeling
- Tunneling and Rock Mechanics
- Industrial Vision Systems and Defect Detection
- Geotechnical Engineering and Analysis
- Advanced Neural Network Applications
- Geotechnical Engineering and Underground Structures
- Drilling and Well Engineering
- Gear and Bearing Dynamics Analysis
- Image and Signal Denoising Methods
- Advanced Measurement and Metrology Techniques
- Manufacturing Process and Optimization
- Domain Adaptation and Few-Shot Learning
- Concrete and Cement Materials Research
- Advanced Image Fusion Techniques
- Non-Destructive Testing Techniques
- Advanced Materials Characterization Techniques
- Image Processing and 3D Reconstruction
- Image and Object Detection Techniques
- Industrial Technology and Control Systems
- Mineral Processing and Grinding
- Machine Fault Diagnosis Techniques
- Surface Roughness and Optical Measurements
- Evaluation Methods in Various Fields
- Infrastructure Maintenance and Monitoring
- Geoscience and Mining Technology
Beijing Jiaotong University
2023-2024
Zhejiang University
2022-2024
Dalian University
2024
Dalian University of Technology
2024
Aviation Industry Corporation of China (China)
2012-2024
Beijing Research Institute of Uranium Geology
2018-2023
China Atomic Energy Authority
2023
Shanghai Jiao Tong University
2005-2023
State Key Laboratory of Industrial Control Technology
2020-2023
The University of Tokyo
2017-2023
Abstract Human limbs emerge during the fourth post-conception week as mesenchymal buds, which develop into fully formed over subsequent months 1 . This process is orchestrated by numerous temporally and spatially restricted gene expression programmes, making congenital alterations in phenotype common 2 Decades of work with model organisms have defined fundamental mechanisms underlying vertebrate limb development, but an in-depth characterization this humans has yet to be performed. Here we...
Blockchain has attracted an increasing amount of researches, and there are lots refreshing implementations in different fields. Cryptocurrency as its representative implementation, suffers the economic loss due to phishing scams. In our work, accounts transactions treated nodes edges, thus detection can be modeled a node classification problem. Correspondingly, we propose detecting method based on Graph Convolutional Network autoencoder precisely distinguish accounts. Experiments large-scale...
Abductive reasoning seeks the likeliest possible explanation for partial observations. Although abduction is frequently employed in human daily reasoning, it rarely explored computer vision literature. In this paper, we propose a new task and dataset, Visual Reasoning (VAR), examining abductive ability of machine intelligence everyday visual situations. Given an incomplete set events, AI systems are required to not only describe what observed, but also infer hypothesis that can best explain...
With the development of satellite load technology and very large scale integrated (VLSI) circuit technology, onboard real-time synthetic aperture radar (SAR) imaging systems have become a solution for allowing rapid response to disasters. A key goal SAR system design is achieve high processing performance with severe size, weight, power consumption constraints. In this paper, we analyse computational burden commonly used chirp scaling (CS) algorithm. To reduce hardware cost, propose partial...
Rock mass condition assessment during tunnel excavation is a critical step for the intelligent control of boring machine (TBM). To address this and achieve automatic detection, visual system installed to TBM lager in-situ rock image dataset collected from water conveyance channel project. The task transformed into fine-grain classification task. fulfill task, self-convolution based attention fusion network (SAFN) designed in paper. core our method discovery object map within deep neural...
The real-time prediction of tunnel boring machine (TBM) driving parameters is a critical step during the process excavation. To obtain dynamic characteristics and approximate range TBM parameters, hybrid <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in situ</i> dataset collected from water conveyance channel project, which consists operation data geological data. parameter task transformed into multiperiod multivariate time series according...
The problem of large deformation is very prominent in deep-buried tunnel excavation soft rock, which brings serious potential safety hazards and economic losses to projects. knowledge law support measures the key ensure rational design safe construction a rock. This paper describes rock physical mechanical tests field monitoring employed investigate cause development process Dongsong hydropower station Sichuan Province, China. results show that free expansion rate sample 20.0%, average...
Protein films are an important class of materials for applications in biomedicine and biotechnology. The rational design protein polymer sequence selection customized cross-linking offers unique opportunities to engineer desirable functionalities into these materials. Here we report the fabrication a series with tunable physiochemical properties from genetically engineered silk-elastin-like proteins (SELPs). SELPs were recombinantly biosynthesized different ratios silk-to-elastin blocks...
Rail corrugation impacts the riding quality and safety of railway systems. The chord-based method is one common methods for rail dynamic measurement. However, during process continuous operation, it hard to ensure that measuring points on surface can trace railhead centerline well whole time. This introduces position deviations system, leads measurement results not reflecting true irregularity state. To solve problem, an automated system monitoring correction constructed in this paper....
The accurate measurement of rail wear is critical in track quality inspection. Usually, by matching the measured profile with standard one based on unworn waist double circle segment (DCS), and comparing their railhead differences, we obtain wear. However, complex field environment, this task becomes tricky. For registration, that location difficult lots outliers mixed profile, other obtained could be polluted or incomplete. measurement, scattered cause serious errors. This paper devoted to...
Purpose This paper aims to present a bio-inspired neural network for improvement of information processing capability the existing artificial networks. Design/methodology/approach In network, authors introduce property often found in biological system – hysteresis as neuron activation function and bionic algorithm extreme learning machine (ELM) scheme. The give gradient descent procedure optimize parameters hysteretic develop an online select ELM parameters, including number hidden-layer...
Abstract Human limbs emerge during the fourth post-conception week as mesenchymal buds which develop into fully-formed over subsequent months. Limb development is orchestrated by numerous temporally and spatially restricted gene expression programmes, making congenital alterations in phenotype common. Decades of work with model organisms has outlined fundamental processes underlying vertebrate limb development, but an in-depth characterisation this process humans yet to be performed. Here we...
Piping is the results of soil internal erosion by seepage. In this paper, a mathematic model for development piping formulated based on principle mass conservation and consideration solid-fluid interactions. Soil particles are divided into three types, i.e., framework particles, movable moving particles. The derived from after its statical balancing broken caused drag force water flow. transforming to ones considered as source item particle transporting model. A mechanical proposed determine...
With the coal mining depth increasing, both stress and gas pressure rapidly enhance, causing outburst risk to become more complex severe. The conventional method for prediction of adopts one index corresponding critical value forecast cannot reflect all factors impacting outburst, thus it is characteristic false missing forecasts poor accuracy. For reason, based on analyses indicators at test site, this work carefully selected 6 such as desorption from drill cuttings delta-h2, amount S,...