A5065602518- Retinal Imaging and Analysis
- Glaucoma and retinal disorders
- Remote-Sensing Image Classification
- Retinal Diseases and Treatments
- Groundwater flow and contamination studies
- Acute Ischemic Stroke Management
- Robotics and Sensor-Based Localization
- Medical Imaging and Analysis
- Adaptive Control of Nonlinear Systems
- Catalytic Processes in Materials Science
- Radar Systems and Signal Processing
- Advanced Neural Network Applications
- Analytical chemistry methods development
- Multilevel Inverters and Converters
- Infrared Target Detection Methodologies
- Mercury impact and mitigation studies
- Ultrasonics and Acoustic Wave Propagation
- Retinal and Optic Conditions
- Water Systems and Optimization
- Flexible and Reconfigurable Manufacturing Systems
- Radioactivity and Radon Measurements
- Thermography and Photoacoustic Techniques
- Photonic and Optical Devices
- Nanofabrication and Lithography Techniques
- AI in cancer detection
Beijing Normal University
2023-2024
Beijing Institute of Technology
2018-2024
Florida International University
2024
Chongqing University of Technology
2024
Foshan University
2023
Xidian University
2021
Shanghai University
2001-2020
University of Technology Sydney
2020
Xijing University
2017
Xi'an High Tech University
2006-2010
Automatic diabetic retinopathy (DR) lesions segmentation makes great sense of assisting ophthalmologists in diagnosis. Although many researches have been conducted on this task, most prior works paid too much attention to the designs networks instead considering pathological association for lesions. Through investigating pathogenic causes DR advance, we found that certain are closed specific vessels and present relative patterns each other. Motivated by observation, propose a relation...
Analysis of electromagnetic vibration and acoustic noise assessment methods to minimize resultant sound power level for low motor design is presented in this paper. The linear model the exciting force wave derived evaluate optimize stator winding, rotor PM shape skew angle minimization design. Mode number frequency wave, natural frequency, maximum velocity displacement main source are introduced machine vibration. Resultant levels cylindrical plane models analyze both axial radial flux...
Automatic subcutaneous vessel imaging with near-infrared (NIR) optical apparatus can promote the accuracy of locating blood vessels, thus significantly contributing to clinical venipuncture research. Though deep learning models have achieved remarkable success in medical image segmentation, they still struggle subfield segmentation due scarcity and low-quality annotated data. To relieve it, this work presents a novel semi-supervised framework, SCANet, that achieves accurate through an...
The existing few-shot medical segmentation networks share the same practice that more prototypes, better performance. This phenomenon can be theoretically interpreted in Vector Quantization (VQ) view: clusters are separated from pixel-wise feature points distributed over full space. However, as we further think about with this perspective, it is found clusterization of and adaptation to unseen tasks have not received enough attention. Motivated by observation, propose a learning VQ mechanism...
Improvement in detection accuracy is an important and hot topic for laser induced breakdown spectroscopy (LIBS). Discharged-pulse assisted (DPA) plasma has been investigated as effective way to enhance analytical capabilities of LIBS. Most reported DPA experiments have performed using high voltage power comprehend spectrum enhancement. For safety concerns maneuverability LIBS equipment; low small current discharge are viable industrial application. In this paper, the enhanced spectra with...
Mineral segmentation of satellite imagery is crucial to mining surveying and monitoring. Conventional deep networks extract features at every position with a fixed field-of-view. Nevertheless, the rich content in large mineral scenes, which causes dramatically different local characteristics across regions, may require spatially varying field-of-view achieve accurate segmentation. In light this, we propose novel Pixel-Adaptive Field-of-View (PA-FoV) module adjust given feature map pixel-wise...
In medical image analysis, blood vessel segmentation is of considerable clinical value for diagnosis and surgery. The predicaments complex vascular structures obstruct the development field. Despite many algorithms have emerged to get off tight corners, they rely excessively on careful annotations tubular extraction. A practical solution excavate feature information distribution from unlabeled data. This work proposes a novel semi-supervised framework, named EXP-Net, navigate through finite...
Instance segmentation algorithms in remote sensing are typically based on conventional methods, limiting their application to seen scenarios and closed-set predictions. In this work, we propose a novel task called zero-shot instance segmentation, aimed at identifying aerial objects that absent from training data. Challenges arise when classifying categories with high inter-class similarity intra-class variance. Besides, the domain gap between vision-language models' pretraining datasets...
Pulsed thermography (PT) is a widely used non-destructive testing (NDT) technique for defect detection in carbon fiber reinforced polymers (CFRP) structures. Thermographic signal reconstruction (TSR) often employed to process thermographic data due its excellent performance enhancing the contrast between defects and background. However, TSR does not reduce noise of effectively. To solve this problem, thesis proposes an image denoising method based on wavelet transform. The experiment results...
Diabetic Retinopathy (DR) is a multiply occurring complication induced by prolonged course of diabetes. Macular Edema (DME) the most common DR which major threat vision loss. Hence, it urgently needed to expand early screening and diagnosis via computer-assisted therapy. However, prior works mainly focus on investigating DME in isolation, largely ignoring their inherent relationships. Besides, fundus data distribution typically long-tailed, with tail classes concentrating critical levels...
Abstract A better understanding of the distribution nonaqueous phase liquid (NAPL) plumes is great importance to groundwater pollution remediation and control. However, efficiency surrogate models in simulating transport still not well addressed. Selecting a leakage problem as an example, 50 sets random permeability distributions are generated using Monte Carlo method, numerical model used obtain benchmark data NAPL transport. Four machine learning methods employed simulate dense under point...
Synthetic aperture radar (SAR) image change detection is a very complex problem like SAR imaging mechanism. Every method has its advantage and disadvantage there are no optimal approaches. If general methods directly perform detection, it can not obtain the satisfied results. Sometimes, for pair of multi-temporal images, different detected results; what's more, results contrary. In order to improve precision, this paper studies mechanism in detail represents types images. The new integrative...
The harmonic pollution of power electronic equipment has a strong negative effect on the quality supply and efficiency.In order to improve factor, we designed three-phase two-level active factor correction (APFC) circuit.The former Boost converter connected with input side rectifier realized (PFC).The post Buck function adjusting output voltage quickly corresponding control circuit.We carried out simulation in Matlab/simulink software environment.The results showed that current waveform is...
Abstract The development level of port logistics partly reflects the comprehensive competitiveness port. Based on latest data Ningbo Zhoushan port, combined with literature research, this paper analyses status in terms infrastructure construction, collection and distribution network, information application, service scope policy environment. In view limitation developing puts forward some countermeasures, such as optimizing structure distribution, speeding up construction information, system...
The directional feature of Earth’s geomagnetic field has been contributing to the technological development and prosperity humankind since invention magnetic compass navigation centuries ago. Today, for instance, magnetoresistance sensors are commonly used in nanosatellites unmanned aerial vehicles high accuracy field-based mineral survey exploration.