A5034489653- Water Systems and Optimization
- Geotechnical Engineering and Underground Structures
- Advanced Image Processing Techniques
- Image Processing Techniques and Applications
- Infrastructure Resilience and Vulnerability Analysis
- Image and Signal Denoising Methods
- Structural Integrity and Reliability Analysis
- Advanced Vision and Imaging
- Infrastructure Maintenance and Monitoring
- Water Treatment and Disinfection
- Urban Stormwater Management Solutions
- Advanced Image Fusion Techniques
- Smart Grid Security and Resilience
- Image Enhancement Techniques
- Fish biology, ecology, and behavior
- Water Quality Monitoring Technologies
- Probabilistic and Robust Engineering Design
- Geoscience and Mining Technology
- Crustacean biology and ecology
- Seismic Waves and Analysis
- Geomechanics and Mining Engineering
- Soil, Finite Element Methods
- Remote Sensing in Agriculture
- Remote Sensing and Land Use
- Geotechnical and Geomechanical Engineering
Lanzhou University of Technology
2020-2023
Shanghai Chengtou (China)
2023
China Agricultural University
2021
National Engineering Research Center for Information Technology in Agriculture
2021
Tongji University
2017-2020
Deep neural networks with different filters or multiple branches have achieved good performance for single superresolution (SR) in recent years. However, they ignore the high-frequency components of multiscale context information low-resolution image. To solve this problem, we propose a fusing attention network based on dilated convolution (DFAN) SR. Specifically, first convolutional module (DCAM), which captures contextual from regions LR images by locking sizes receptive fields. Then,...
With the increase in operation risks of water distribution networks (WDNs), prediction pipe failures is great significance developing efficient maintenance strategies. This study used a residual network (ResNet), newly proposed deep learning (DL) algorithm, to predict failure, and its effectiveness was compared with that classic convolution neural (CNN) algorithm. Network structure ResNet classification one-dimensional vectors built. The synthetic minority oversampling technique (SMOTE)...
Water distribution systems (WDSs) are crucial urban infrastructures playing major roles in maintaining the social and economic functions of modern cities. Understanding operation condition contributes to daily maintenance, asset management, future planning for decision makers. This study statistically analyzes WDSs a large city China by using pipe basic failure databases collected from local sectors. For database, rules attributes, including region, material, depth, diameter, joint type,...
The Fast Super-Resolution Convolutional Neural Network algorithm (FSRCNN) is difficult to extract deep image information due the small number of convolution layers and correlation lack between feature adjacent convolutional layers. To solve this problem, a residual network super-resolution reconstruction method with multi-level skip connections proposed. Firstly, block designed problem that characteristic lacks relevance. A constructed on basis block. Then, connected trained by using...
Seismic analysis of buried pipes has been one study focus during the last decades, but systematic seismic research pipe connections, especially its relationship with connected straight pipe, is nearly blank. On basis, influence connections on joint deformations (JDs) segmented analyzed in detail by considering different parameters, namely, connection shapes, ground conditions, diameters, branch angles, incident and input motions. Moreover, an coefficient, which measures JDs, calculated....