A5100607251- Geotechnical Engineering and Underground Structures
- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Human Pose and Action Recognition
- Advanced Neural Network Applications
- Numerical methods in engineering
- Anomaly Detection Techniques and Applications
- Coastal and Marine Dynamics
- Electromagnetic Simulation and Numerical Methods
- Advanced Vision and Imaging
- Seismic Waves and Analysis
- Geotechnical Engineering and Soil Mechanics
- Multimodal Machine Learning Applications
- Advanced Algorithms and Applications
- Video Surveillance and Tracking Methods
- Fluid Dynamics Simulations and Interactions
- Smart Grid and Power Systems
- Image and Signal Denoising Methods
- Advanced Computing and Algorithms
- Geotechnical Engineering and Soil Stabilization
- Traditional Chinese Medicine Studies
- Advanced Steganography and Watermarking Techniques
- Metabolomics and Mass Spectrometry Studies
- Advanced Image Processing Techniques
- Advanced Image and Video Retrieval Techniques
China Electric Power Research Institute
2024-2025
North China Electric Power University
2025
Guangdong University of Technology
2024
Beijing University of Technology
2016-2024
Beijing Academy of Artificial Intelligence
2016-2024
State Grid Corporation of China (China)
2021-2024
Tsinghua University
2023
Huaqiao University
2013-2022
Shanghai University of Political Science and Law
2021
Wuhan University
2021
Abstract A novel artificial boundary method called the scaled perfectly matched layer (SBPML) is proposed for transient analysis of elastic wave propagation in unbounded domains. This constructs a generalized (PML) around finite interior subdomain based on coordinate transformation inspired by element (SBFEM). It can model infinite exterior subdomains heterogeneous materials, featuring both parallel and radial straight‐line physical surfaces interfaces. In addition, generally‐shaped (even...
Of great interest in recent years has been computationally predicting the novel polypharmacology of drug molecules. Here, we applied an "induced-fit" protocol to improve homology models 5-HT2A receptor, and assessed quality these retrospective virtual screening. Subsequently, screened FDA approved molecules against best induced-fit chose six top scoring hits for experimental assays. Surprisingly, one well-known kinase inhibitor, sorafenib, shown unexpected promiscuous 5-HTRs binding...
Abstract The paper aims to address the issue of insufficient fault samples in UHV converter equipment, which hinders their intelligent operation and inspection. For inspection this suggests a multimodal brain-like learning sample spatio-temporal correlation generation method. This method grabs typical from defect-fault development time sequence process creates using nearest-neighbor generating segment technique by fusing evolution law similarity adjacent samples. Based on physical model...
Purpose Accurate dose calculation is a critical step in proton therapy. A novel machine learning‐based approach was proposed to achieve comparable accuracy that of Monte Carlo simulation while reducing the computational time. Methods Computed tomography‐based patient phantoms were used and three treatment sites selected (thorax, head, abdomen), comprising different beam pathways energies. The training data generated using simulations. discovery cross‐domain generative adversarial network...
In this paper, an adaptive sliding mode controller is designed for the omnidirectional mobile robot with four Mecanum wheels to track trajectory. The wheel has been widely used in factories, hospitals, families and other workspaces because of its ability. Consider dynamic model based on uncertainties external disturbances, a neural network control (NNASMC) strategy proposed, which combines techniques Radial Basis Function (RBF) method method. Finally, some simulation experiments are...
Server consolidation is a useful solution aiming at cost-efficiency and high resource utilization of data centers clusters. Nowadays, as the data-intensive I/O intensive applications are widely used, more attention paid to local storage-based clouds which can offer much better performance relatively low price compared with shared storage. However, it will obviously increase migration cost (e.g., energy time). Meanwhile, there few suitable demand estimation method for present, plays an...
Intelligent Wheelchair Bed (IWB) is an important direction. And it also one of the most active research direction in robot field. In this work, obstacle avoidance algorithm based on Artificial Potential Field (APF) using ultrasonic sensors proposed and realized order to achieve real-time continuing for IWB. The IWB can keep detecting environment with eleven sensors. relative coordinates obtained by are used describe position obstacles. APF introduced compute repulsive speed determine next...