A5029561060- Liver Disease Diagnosis and Treatment
- Autonomous Vehicle Technology and Safety
- Robot Manipulation and Learning
- Hepatitis B Virus Studies
- Video Analysis and Summarization
- Sports Analytics and Performance
- Network Security and Intrusion Detection
- Evacuation and Crowd Dynamics
- Video Surveillance and Tracking Methods
- Multimodal Machine Learning Applications
- Advanced Graph Neural Networks
- Hepatitis C virus research
- AI-based Problem Solving and Planning
- Educational Technology and Pedagogy
- Advanced Surface Polishing Techniques
- Regional Economic and Spatial Analysis
- Artificial Immune Systems Applications
- Cancer, Hypoxia, and Metabolism
- Human Motion and Animation
- Gaze Tracking and Assistive Technology
- Laser-induced spectroscopy and plasma
- Face recognition and analysis
- Human Pose and Action Recognition
- Generative Adversarial Networks and Image Synthesis
- Hand Gesture Recognition Systems
University of Science and Technology Beijing
2025
Harbin Engineering University
2024
Tsinghua University
2024
Shantou University
2024
First Affiliated Hospital of Shantou University Medical College
2024
Second Hospital of Yichang
2023
Nanjing University of Aeronautics and Astronautics
2022-2023
Minghsin University of Science and Technology
2023
Agency for Science, Technology and Research
2023
Institute of Microelectronics
2023
In some complicated tabletop object manipulation task for robotic system, demonstration based control is an efficient way to enhance the stability of execution. this paper, we use a new optical hand tracking sensor, LeapMotion, perform non-contact systems. A Multi-LeapMotion system developed. The setup two sensors analyzed gain optimal efficiently informations from sensors. Meanwhile, coordinate systems Mult-LeapMotion device and are With recognition element actions delay calibration, fusion...
Intraneuronal neurofibrillary tangles composed of Tau aggregates have been widely accepted as an important pathological hallmark Alzheimer's disease. A current therapeutic avenue for treating disease is aimed at inhibiting accumulation with small molecules such natural flavonoids. Liquid-liquid phase separation (LLPS) can lead to its aggregation, and then be degraded by autophagy. However, it unclear whether flavonoids modulate the formation phase-separated droplets or promote autophagy...
Abstract Hyperuricemia (HUA) is a metabolic syndrome caused by abnormal purine metabolism. Although recent studies have noted relationship between the gut microbiota and gout, whether could ameliorate HUA-associated systemic metabolism remains unclear. In this study, we constructed novel model of HUA in geese investigated mechanism which Lactobacillus rhamnosus GG (LGG) beneficial effects on HUA. The administration antibiotics fecal transplantation (FMT) experiments were used goose model....
Whole-body bone scan (WBS) is usually used as the effective diagnostic method for early-stage and comprehensive metastases of breast cancer. WBS images with cancer metastasis have characteristics low resolution, small foreground, multiple lesions, hindering widespread application deep learning-based models. Automatically detecting a large number densely lesions on low-resolution remains challenge. We aim to develop unified framework based images. propose novel detection detect Considering...
Based on area and color analyses, a cost-effective bi-directional people counter dedicated to the pedestrian flow passing through gate or door is proposed. Firstly, are roughly counted with of projected an image captured by zenithal video camera. The moving direction can be recognized tracking each people-pattern analysis its HSI histogram. To improve accuracy counting, vector extracted from quantized histograms intensity hue introduced refine early counting. Besides, inherent problems both...
Existing image aesthetics assessment methods mainly rely on the visual features of images but ignore their rich semantics. Nowadays, with widespread application social media, comments corresponding to in form texts can be easily accessed and provide semantic information, which utilized effectively complement features. This paper proposes a comment-guided semantics-aware method, is built upon multi-task learning framework for prediction semantics classification. To assist assessment, we first...
To determine the clinical course and perinatal transmission of chronic hepatitis B during pregnancy in a real life setting.A total 221 singleton pregnant women with detectable HBV-DNA levels (≥103 copies/mL) were enrolled January 2011 to June 2015. Forty-three high viraemic patients (≥106 received telbivudine 2nd or 3rd trimester according their intention, while 89 79 low <106 control cohorts. Primary endpoint was outcomes secondary including intrauterine infection, immunoprophylaxis failure...
Abstract Magnetic soft actuators and robots have attracted considerable attention in biomedical applications due to their speedy response, programmability, biocompatibility. Despite recent advancements, the fabrication process of magnetic reprogramming approach magnetization profiles continue pose challenges. Here, a facile strategy is reported based on arrangements distributions reusable pixels silicone substrates, allowing for various with customizable architectures, arbitrary profiles,...
For a mobile robot, navigation skills that are safe, efficient, and socially compliant in crowded, dynamic environments essential. This is particularly challenging problem as it requires the robot to accurately predict pedestrians’ movements, analyse developing traffic situations, plan its own path or trajectory accordingly. Previous approaches still exhibit low accuracy for pedestrian prediction, they prone generate infeasible trajectories under complex crowded conditions. In this paper, we...
The accurate prediction of the pedestrian trajectory is necessary to endow automatic guided vehicle with capabilities adjust velocity and path dynamically for navigation in real scenes. For this purpose, study presents a social conscious model considering two main factors that affect pedestrians' walking crowd – relative distance moving direction. To form an effective model, authors'conscious pooling layer added Long Shot Term Memory network (LTSM)model build relationship between...
Robot manipulation is one of prerequisites capability for service robot. However, autonomous remains a challenging problem robot to implement the task, where has physical interactions and mechanical contacts with its environment. To date, learning from demonstration (LFD) been successfully applied enable acquire new skill. Researches on LFD mainly focus representing movement trajectory then transferring reproduced In this paper, framework introduced learn compliant behavior human it...
Abstract Background Perinatal transmission is the main route of hepatitis B virus (HBV) transmission. While several measures have been attempted as means preventing perinatal HBV transmission, optimal strategy remains inconclusive. Methods We conducted a comprehensive search, through December 2016, for randomized controlled trials (RCTs) that compared following among pregnant women with infection: placebo/none, active immunoprophylaxis (hepatitis vaccine series starting at birth [HBVac]),...
Abstract Background China faces high burden of multidrug-resistant or rifampicin-resistant tuberculosis (MDR/RR-TB). We aimed to evaluate the impacts Vaccae vaccination and enhanced drug-resistant TB (DR-TB) management strategies. Methods Using a compartmental model calibrated with national data, we evaluated 9 interventions: DR-TB (S1); for those latent infection, targeting specific age groups (S2: adolescents, S3: adolescents young adults, S4: working-age S5: elderly); combined strategies...
Diabetic retinopathy (DR) is currently one of the severe complications leading to blindness, and computer-aided, diagnosis technology-assisted DR grading has become a popular research trend especially for development deep learning methods. However, most learning-based models require large number annotations provide data guidance, it laborious experts find subtle lesion areas from fundus images, making accurate annotation more expensive than other vision tasks. In contrast, large-scale...
Spectral Graph Neural Networks (GNNs) with various graph filters have received extensive affirmation due to their promising performance in learning problems. However, it is known that GNNs do not always perform well. Although provide theoretical foundations for model explanations, unclear when a spectral GNN will fail. In this paper, focusing on node classification problems, we conduct analysis of by investigating prediction error. With the aid indicators including homophily degree and...