A5041350681- Transportation and Mobility Innovations
- Human Mobility and Location-Based Analysis
- Glaucoma and retinal disorders
- Computational Drug Discovery Methods
- Retinal Diseases and Treatments
- Infrared Target Detection Methodologies
- Text and Document Classification Technologies
- Advanced Image and Video Retrieval Techniques
- Advanced Measurement and Detection Methods
- Machine Learning in Bioinformatics
- Retinal Imaging and Analysis
- Transportation Planning and Optimization
- Medical Image Segmentation Techniques
- Forest, Soil, and Plant Ecology in China
- Corneal surgery and disorders
- Optical Systems and Laser Technology
- Sharing Economy and Platforms
- Traffic Prediction and Management Techniques
- Autophagy in Disease and Therapy
- Robotics and Sensor-Based Localization
- Artificial Immune Systems Applications
- Advanced Image Fusion Techniques
- Electric Vehicles and Infrastructure
- Image and Object Detection Techniques
- Vehicular Ad Hoc Networks (VANETs)
Sun Yat-sen Memorial Hospital
2022-2025
Sun Yat-sen University
2006-2025
Peking University
2023-2025
Shaanxi Normal University
2021-2024
The Alan Turing Institute
2020-2023
University of Exeter
2021-2023
State Key Laboratory of Ophthalmology
2022-2023
Key Laboratory of Guangdong Province
2022
University of Warwick
2019-2021
Third Affiliated Hospital of Sun Yat-sen University
2020
The electrification of shared mobility has become popular across the globe. Many cities have their new e-mobility systems deployed, with continuously expanding coverage from central areas to city edges. A key challenge in operation these is fleet rebalancing, i.e., how EVs should be repositioned better satisfy future demand. This particularly challenging context systems, because i) range limited while charging time typically long, which constrain viable rebalancing operations; and ii) EV...
High myopia (HM) is a major risk factor for glaucoma. However, glaucomatous optic neuropathy often undiagnosed owing to atypical structural alterations with axial elongation. Moreover, an algorithm detect glaucoma in highly myopic eyes has not yet been reported. We recruited 2643 colour fundus photographs train ResNet-50 network discriminating (HMG) from HM or alone. employed 10-fold cross-validation strategy evaluate the model's performance and applicability across diverse patient groups....
The future of urban mobility is expected to be shared and electric. It not only a more sustainable paradigm that can reduce emissions, but also bring societal benefits by offering affordable on-demand option the general public. Many car sharing service providers as well automobile manufacturers are entering competition expanding both their EV fleets renting/returning station networks, aiming seize share market zero emissions level. During fast expansion, one determinant for success ability...
Electric Vehicle (EV) sharing systems have recently experienced unprecedented growth across the world. One of key challenges in their operation is vehicle rebalancing, i.e., repositioning EVs stations to better satisfy future user demand. This particularly challenging shared EV context, because i) range limited while charging time substantial, which constrains rebalancing options; and ii) as a new mobility trend, most current are still continuously expanding station networks, targets for can...
Macroautophagy/autophagy, a eukaryotic homeostatic process that sequesters cytoplasmic constituents for lysosomal degradation, is orchestrated by number of autophagy-related (ATG) proteins tightly controlled post-translational modifications. However, the involvement reversible ubiquitination in regulation autophagy remains largely unclear. Here, we performed single-guide RNA-based screening assay to investigate functions deubiquitinating enzymes (DUBs) regulating autophagy. We identified...
Anterior segment optical coherence tomography angiography (AS-OCTA) has superior advantages in objective assessment of anterior (AS) vessels. Resolving noise interference image is necessary to optimize the application AS-OCTA. The study aimed explore an automated denoising algorithm based on deep learning (DL). was built through 21,000 pairs images, and tested with 30 healthy eyes, 47 preoperative eyes glaucoma, undergone trabeculectomy (Trab). real pure images were acquired by artificial...
This study aimed to analyze the quantitative vascular biomarkers of filtering bleb function at different depths using anterior segment optical coherence tomography angiography (AS-OCTA). cross-sectional is registered on Clinicaltrails.gov (NCT04515017). Forty-six eyes with primary open-angle glaucoma that had undergone trabeculectomy mitomycin-C for more than six months were included. Vessel density (VD) and vessel diameter index (VDI) in superficial layer (SL), Tenon's (TL), deep (DL)...
Characteristic marks on the cartridge can be viewed as a ¿fingerprint¿ for identification of firearm. Sometimes, however, not all information obtained from just one image due to limitations microscope and unsmoothed specimen surface in case detection. Image mosaic that refers combination two or more images into single composite is precisely solve this problem. This paper proposes new approach by using automatic registration fusion techniques. In stage, scale invariant feature transform...
The nature of immune algorithm is to distinguish between self and non-self. On the basis algorithm, we propose a new method text categorization called Clonal Selection Algorithm Based on Antibody Density (CSABAD). According clonal selection principle density control mechanism, only those cells that have higher affinity lower are selected proliferate. ultimate classifier composed with many memory cells. Because CSABAD two-class discuss main approaches how apply it multi-class problem, such as...
Shared e-mobility services have been widely tested and piloted in cities across the globe, already woven into fabric of modern urban planning. This paper studies a practical yet important problem those systems: how to deploy manage their infrastructure space time, so that are <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ubiquitous</i> users while xmlns:xlink="http://www.w3.org/1999/xlink">sustainable</i> profitability. However, real-world...
In the process of cartridge case marks detection, due to limitations microscope and unsmoothed specimen surface, not all information can be obtained from just one image. Therefore, two kinds images first then supplemented by image mosaic method which facilitates experts’ analysis following computer recognition. This paper proposes a new using registration fusion techniques. stage, initial matching is scale invariant feature transform (SIFT), but some incorrect matches greatly affect...
According to signal characteristic of Unified S-band (USB) measurement and control system, a method spectrum sensing based on artificial neural network (ANN) is introduced in this paper. Spectrum classifier designed by the independent learning ability ANN. The information collected departed studied stored accurately judge that whether master exists or not. With comparison analysis, it can be proved ANN possesses higher accuracy.
Deep-learning based traffic prediction models require vast amounts of data to learn embedded spatial and temporal dependencies. The inherent privacy commercial sensitivity such has encouraged a shift towards decentralised data-driven methods, as Federated Learning (FL). Under traditional Machine paradigm, flow can capture relationships within centralised data. In reality, is likely distributed across separate silos owned by multiple stakeholders. this work, cross-silo FL setting motivated...
This paper proposes a new method of text categorization called the clonal selection algorithm based on antibody density (CSABAD). In this method, antigen, B cell and are respectively corresponded with training texts, possible individual classifier affinity between texts. cells consist general cells, fresh memory cells. General used to store various individuals, replace degraded record best individuals. According principle control mechanism, only those that have higher lower selected...
Purpose: The purpose of this study was to explore a quantitative grading system the filtering bleb combined anterior segment optical coherence tomography angiography (AS-OCTA) vascular features and (OCT) morphological features. Methods: One hundred three eyes 103 patients diagnosed with primary open-angle glaucoma undergone trabeculectomy over 6 months were divided into success failure groups according postoperative intraocular pressure (IOP) level. Vessel density (VD) vessel diameter index...
Image matching is the process of corresponding features same scene taken at different viewpoints, times or by sensors. In multi-viewpoint image matching, there are significantly geometric deformations and difference content between reference sensed images in scene. So, they increase much more difficulties for matching. Generally, feature-based methods applied field, because sufficiently stable when have various complex deformations. However, it not enough to represent one local region using...