A5100639567- Video Coding and Compression Technologies
- Advanced Vision and Imaging
- Advanced Image Processing Techniques
- Numerical methods in engineering
- Model Reduction and Neural Networks
- Image and Video Quality Assessment
- Advanced Data Compression Techniques
- Image and Signal Denoising Methods
- Composite Structure Analysis and Optimization
- Infrared Target Detection Methodologies
- Advanced Measurement and Detection Methods
- Recycling and utilization of industrial and municipal waste in materials production
- Image Processing Techniques and Applications
- Telecommunications and Broadcasting Technologies
- Structural Health Monitoring Techniques
- Groundwater flow and contamination studies
- Neural Networks and Applications
- Geotechnical Engineering and Analysis
- Landslides and related hazards
- Image and Video Stabilization
- Optical Systems and Laser Technology
- Hydraulic Fracturing and Reservoir Analysis
- Rock Mechanics and Modeling
- Glass properties and applications
- Vibration and Dynamic Analysis
University of Electronic Science and Technology of China
2017-2025
Honghe University
2012-2025
Guangxi Medical University
2025
Beijing University of Technology
2023-2024
Hong Kong Polytechnic University
2023-2024
University of Chinese Academy of Sciences
2017-2023
Beijing Institute of Technology
2023
Leibniz University Hannover
2020-2022
Soochow University
2022
PLA Information Engineering University
2021
Abstract We present a stochastic deep collocation method (DCM) based on neural architecture search (NAS) and transfer learning for heterogeneous porous media. first carry out sensitivity analysis to determine the key hyper-parameters of network reduce space subsequently employ hyper-parameter optimization finally obtain parameter values. The presented NAS DCM also saves weights biases most favorable architectures, which is then used in fine-tuning process. techniques drastically...
Abstract In this work, we present a deep collocation method (DCM) for three-dimensional potential problems in non-homogeneous media. This approach utilizes physics-informed neural network with material transfer learning reducing the solution of partial differential equations to an optimization problem. We tested different configurations including smooth activation functions, sampling methods points generation and combined optimizers. A technique is utilized media gradations parameters, which...
We conducted a study to evaluate the potential and robustness of gradient boosting algorithms in rock burst assessment, established variational autoencoder (VAE) address imbalance dataset, proposed multilevel explainable artificial intelligence (XAI) tailored for tree-based ensemble learning. collected 537 data from real-world records selected four critical features contributing occurrences. Initially, we employed visualization gain insight into data's structure performed correlation...
Rate control plays an important role in video coding systems, which makes the output bitrate of a encoder equal to target while minimizing distortion compressed video. However, most existing rate schemes achieve accurate at loss rate-distortion (R-D) performance. This paper proposes effective frame level bit allocation method improve R-D performance whilst maintaining high accuracy HEVC. First, improved model is presented level, which, by making use information encoded frames more...
Although high efficiency video coding (HEVC) has achieved performance, it been shown that dependent rate-distortion optimization (RDO) can still further improve the performance at encoder side. Inspired by our previous work on temporal-dependent RDO, this paper proposes a rate control method tree unit (CTU) level to obtain both higher (R-D) and lower bitrate errors. We first formulate global problem in hybrid present general solution framework based weighted Lagrange multiplier, where...