A5100386343- Advanced ceramic materials synthesis
- Visual Attention and Saliency Detection
- Advanced Image and Video Retrieval Techniques
- Advanced Vision and Imaging
- Image Enhancement Techniques
- Parallel Computing and Optimization Techniques
- Video Surveillance and Tracking Methods
- Olfactory and Sensory Function Studies
- Aluminum Alloys Composites Properties
- Advanced materials and composites
- Advanced Image Fusion Techniques
- Computer Graphics and Visualization Techniques
- Advanced Neural Network Applications
- Soil Moisture and Remote Sensing
- Diamond and Carbon-based Materials Research
- Remote Sensing and Land Use
- Infrared Target Detection Methodologies
- Medical Image Segmentation Techniques
- Image Processing Techniques and Applications
- Robotics and Sensor-Based Localization
- Mechanical Behavior of Composites
- Green IT and Sustainability
- Automated Road and Building Extraction
- Surgical Simulation and Training
- Soil and Unsaturated Flow
Beihang University
2016-2025
Wuhan University
2020-2025
Renmin Hospital of Wuhan University
2020-2025
Sichuan University
2025
Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)
2024
Sun Yat-sen University
2024
Zhongnan Hospital of Wuhan University
2023
Beijing Institute of Technology
2023
Xi'an Technological University
2023
Suzhou University of Science and Technology
2023
Stroke is an acute cerebral vascular disease that likely to cause long-term disabilities and death. Immediate emergency care with accurate diagnosis of computed tomographic (CT) images crucial for dealing a hemorrhagic stroke. However, due the high variability stroke's location, contrast, shape, it challenging time-consuming even experienced radiologists locate them. In this paper, we propose U-net based deep learning framework automatically detect segment hemorrhage strokes in CT brain...
The segmentation and interpretation of the Martian surface play a pivotal role in Mars exploration, providing essential data for trajectory planning obstacle avoidance rovers. However, complex topography, self-similar features, lack extensive annotated pose significant challenges to high-precision semantic surface. To address these challenges, we propose novel encoder-decoder-based network, termed MarsSeg. facilitate high-level understanding across multi-level feature maps, introduce...
In this article we present SkePU 2, the next generation of C++ skeleton programming framework for heterogeneous parallel systems. We critically examine design and limitations 1 interface. a new, flexible type-safe, interface in source-to-source transformation tool which knows about 2 constructs such as skeletons user functions. demonstrate how compiler transforms programs to enable efficient execution on show enables new use-cases applications by increasing flexibility from 1, errors can be...
The unsteady flow inside a large centrifugal pump with stay vanes was analyzed in this study. static performance and pressure fluctuations the were numerically predicted compared experimental data. Considering relative positions of impeller to volute tongue vanes, which obtained using full calculation traditional steady results. A comparison results data showed that operation condition farther from design resulted larger differences between simulation results, errors beyond reasonable...
The conventional methods for target detection and discrimination in high-resolution synthetic aperture radar (SAR) images usually have low accuracy slow speed, especially large complex scenes. To overcome these drawbacks, this paper, we propose a method based on visual attention model. In the stage, to pop out targets suppress background clutter saliency map, select task-dependent scales from Gaussian pyramid of original SAR image. Moreover, adopt clustering algorithm remerge several...
The aircraft system has recently gained its reputation as a reliable and efficient tool for sensing parsing aerial scenes. However, accurate fast semantic segmentation of high-resolution images remote applications is still facing three challenges: the requirements limited processing resources low-latency operations based on platforms, balance between high accuracy real-time efficiency model performance, confusing objects with large intra-class variations small inter-class differences in...
Rhegmatogenous retinal detachment associated with choroidal (RRDCD) is known for its rapid progression and poor prognosis, making it a subject of significant clinical interest due to complex pathogenesis. This study aims utilize mass spectrometry proteomic analysis vitreous humor identify proteins biomarkers critical the pathophysiology RRDCD. Data-independent acquisition (DIA) was employed analyze samples from RRDCD (RRD) patients. The focused on identifying differentially expressed (DEPs)...
Mortality prediction is critical in clinical care, particularly intensive care units (ICUs), where early identification of high-risk patients can inform treatment decisions. While deep learning (DL) models have demonstrated significant potential this task, most suffer from limited generalizability, which hinders their widespread application. Additionally, the class imbalance electronic health records (EHRs) complicates model training. This study aims to develop a causally-informed that...
The rotating stall is an unstable flow phenomenon of pump turbines in mode, which increasing concern to scientists and engineers working on turbines. However, at present, various studies are carried out based CFD (computational fluid dynamics) simulation, while directly measured data experimental research fields seldom reported. By utilizing PIV (particle image velocimetry) measuring equipment, the field within guide vane zone a low specific speed turbine mode was measured. analyzing...
Digital soil mapping relies on statistical relationships between profile observations and environmental covariates at the sample locations. However, inherent limitations of legacy profiles, such as inaccurate georeferencing, could frequently introduce location errors into these profiles that affect quality digital mapping. To address this challenge, study focuses reducing error evaluating resulting impact We improved agreement detailed descriptive information relatively accurate (such...
Understanding and predicting global soil moisture (SM) is crucial for water resource management agricultural production. While deep learning methods (DL) have shown strong performance in SM prediction, imbalances training samples with different characteristics pose a significant challenge. We propose that improving the diversity balance of batch during gradient descent can help address this issue. To test hypothesis, we developed Cluster-Averaged Sampling (CAS) strategy utilizing...