A5100371573- Rock Mechanics and Modeling
- Landslides and related hazards
- Advanced Computational Techniques and Applications
- Seismic Imaging and Inversion Techniques
- Geophysical Methods and Applications
- Image and Signal Denoising Methods
- Adaptive Dynamic Programming Control
- Advanced Algorithms and Applications
- Geological and Geophysical Studies
- Reinforcement Learning in Robotics
- Geotechnical and Geomechanical Engineering
- Energy Load and Power Forecasting
- Air Quality Monitoring and Forecasting
- High-pressure geophysics and materials
- Tunneling and Rock Mechanics
- Advanced Decision-Making Techniques
- Infrastructure Maintenance and Monitoring
- Seismic Waves and Analysis
- Chaos-based Image/Signal Encryption
- Drilling and Well Engineering
- Advanced Steganography and Watermarking Techniques
- Machine Fault Diagnosis Techniques
- Medical Image Segmentation Techniques
- Fuzzy Logic and Control Systems
- earthquake and tectonic studies
Taiyuan University of Technology
2018-2024
Xi'an Jiaotong University
2014-2021
Northeastern University
2019-2021
China Electronics Technology Group Corporation
2020
Computer Network Information Center
2018
Chinese Academy of Sciences
2008-2018
University of Chinese Academy of Sciences
2018
China University of Geosciences (Beijing)
2016-2017
Beijing University of Technology
2016
National University of Defense Technology
2013
This paper presents a unique approach for wavelet-based MRI brain image de-noising. Adaptive soft and hard threshold functions are first proposed to improve the results of standard de-noising in wavelet domain. Then, we applied newly emerged improved adaptive generalized Gaussian distributed oriented function (improved AGGD) on images also display, this non-linear data-driven can work promisingly even medical images. The most important characteristic is that it dependent since combined with...
Visual-Spatial Systems has become increasingly essential in concrete crack inspection. However, existing methods often lacks adaptability to diverse scenarios, exhibits limited robustness image-based approaches, and struggles with curved or complex geometries. To address these limitations, an innovative framework for two-dimensional (2D) detection, three-dimensional (3D) reconstruction, 3D automatic measurement was proposed by integrating computer vision technologies multi-modal Simultaneous...
Abstract In geothermal mining, the mechanical properties and micro‐structure of rock under different temperature or cooling modes are highly relevant to stability artificial reservoir. For reflect actual working conditions, an experimental study is carried out on high‐temperature granite that has been cooled both naturally rapidly with water. The following conclusions reached. (a) wave velocity, elastic modulus, uniaxial compressive strength test specimen decrease increase in its heating...
Abstract The mechanism and fracture aperture of thick hard roof failure were theoretically analyzed from the perspective elastoplastic mechanics. A uniform load cantilever beam was established by considering voussoir structure stress condition. According to inverse principle in solving plane strain problem, internal component analytic solution deduced. Considering lateral thrust shear force applying Mohr‐Coulomb criterion, plastic zone boundary equation obtained. Further analysis equivalent...
Semi-Fragile watermark has attracted attention due to its important role in content authentication for multimedia. In order differentiate incidental attacks and malicious attacks, semi-fragile must be robust against content-protection image processing. Semi-fragile resisting JPEG compression while maintaining high detection ability tamper been the emphasis this area. paper, a watermarking algorithm resist is proposed based on fact that most of coefficients frequency have same relative energy...
The fracture network of a deep geothermal reservoir forms the place for heat exchange between injected fluid and rock mass with high temperature. resistance ability rocks will affect formation fracture-network structure, transmission characteristics, mechanical stability. However, there are few reports on toughness trajectory prediction reservoirs different depths. In this paper, modified maximum tangential stress criterion (MMTS) is analyzed. results show that experimental data...
As a novel recursion neural network, Echo State Networks (ESN) are characterized by strong nonlinear prediction capability and effective straightforward training algorithms. However, conventional ESN predictions require large volume of samples. Meanwhile, the time sequence data complicated unstable, resulting in insufficient learning this network difficult training. result, accuracies limited. Aimed at issue, series model Grey Wolf optimized has been proposed. W<sup>out</sup> was using...
In this study, we present a practical implementation of prestack Kirchhoff time migration (PSTM) on general purpose graphic processing unit. First, consider the three main optimizations PSTM GPU code, i.e., designing configuration based reasonable execution, using texture memory for velocity interpolation, and application an intrinsic function in device code. This approach can achieve speedup nearly 45 times NVIDIA GTX 680 compared with CPU code when larger imaging space is used, where...
<p class="p1">Shapelet classification algorithms are an accurate method for time series data. Existing shapelet classifying processes relatively inefficient and slow due to the large amount of necessary complex distance computations. This paper therefore introduces piecewise aggregate approximation(PAA) representation efficient subsequence matching algorithm algorithms; also proposes transformation based on matching. First, proposed took PAA appropriate dimension reduction, then used a...
ABSTRACT Background and Objectives: In this article, we propose an image segmentation model based on Chan-Vese (CV) for segmentation. By taking into account the local features of image, new proposed can successfully segment images with intensity nonuniformity. Materials Methods: We quantitatively compare our method other two state-of-the-art algorithms, namely, CV binary fitting (LBF) in segmenting synthetic MR ground truth from BrainWeb; data be available at:...