A5101910181- Graph Theory and Algorithms
- Radiomics and Machine Learning in Medical Imaging
- Complex Network Analysis Techniques
- AI in cancer detection
- Energy Load and Power Forecasting
- Air Quality Monitoring and Forecasting
- Machine Learning and ELM
- Head and Neck Cancer Studies
- Neural Networks and Applications
- Sentiment Analysis and Opinion Mining
- Advanced Graph Neural Networks
- Building Energy and Comfort Optimization
- Tissue Engineering and Regenerative Medicine
- Planarian Biology and Electrostimulation
- Rough Sets and Fuzzy Logic
- Lung Cancer Diagnosis and Treatment
- Data Visualization and Analytics
- Privacy-Preserving Technologies in Data
- Digital Marketing and Social Media
- Peer-to-Peer Network Technologies
- Opinion Dynamics and Social Influence
- Evolutionary Algorithms and Applications
- Smart Systems and Machine Learning
- Colorectal Cancer Screening and Detection
- Metaheuristic Optimization Algorithms Research
Foshan University
2024-2025
National University of Singapore
2024
Southern University of Science and Technology
2021-2024
Northeastern University
2023
Jinan University
2021
The incidence of occult cervical lymph node metastases (OCLNM) is reported to be 20-30% in early-stage oral cancer and oropharyngeal cancer. There a lack an accurate diagnostic method predict metastasis help surgeons make precise treatment decisions.
The accurate identification of molecular subtypes in digestive tract cancer (DTC) is crucial for making informed treatment decisions and selecting potential biomarkers. With the rapid advancement artificial intelligence, various machine learning algorithms have been successfully applied this field. However, complexity high dimensionality data features may lead to overlapping ambiguous during clustering. In study, we propose GDEC, a multi-task generative deep neural network designed precise...
Graph-RAG constructs a knowledge graph from text chunks to improve retrieval in Large Language Model (LLM)-based question answering. It is particularly useful domains such as biomedicine, law, and political science, where often requires multi-hop reasoning over proprietary documents. Some existing systems construct KNN graphs based on chunk relevance, but this coarse-grained approach fails capture entity relationships within texts, leading sub-par generation quality. To address this, recent...
The dissemination of information is a complex process that plays crucial role in real-world applications, especially when intertwined with friend invitations and their ensuing responses. Traditional diffusion models, however, often do not adequately capture this invitation-aware (IAD), rendering inferior results. These models typically focus on describing the social influence process, i.e., how user informed by friends, but tend to overlook subsequent behavioral changes might precipitate. To...
Influence maximization (IM) aims to identify a small number of influential individuals maximize the information spread and finds applications in various fields. It was first introduced context viral marketing, where company pays few influencers promote product. However, apart from cost factor, capacity consume content poses challenges for implementing IM real-world scenarios. For example, players on online gaming platforms can only interact with limited friends. In addition, we observe that...
Influence maximization (IM) is a classic problem that aims to identify small group of critical individuals, known as seeds, who can influence the largest number users in social network through word-of-mouth. This finds important applications including viral marketing, infection detection, and misinformation containment. The conventional IM typically studied with oversimplified goal selecting single seed set. Many real-world scenarios call for multiple sets particularly on media platforms...
BackgroundSurvival prediction is one of the crucial goals in precision medicine, as accurate survival assessment can aid physicians selecting appropriate treatment for individual patients. To achieve this aim, extensive data must be utilized to train model and prevent overfitting. However, collection patient disease challenging due potential variations sources across institutions concerns regarding privacy ownership issues sharing. facilitate integration cancer from different without...
Influence maximization (IM) is a classic problem that aims to identify small group of critical individuals, known as seeds, who can influence the largest number users in social network through word-of-mouth. This finds important applications including viral marketing, infection detection, and misinformation containment. The conventional IM typically studied with oversimplified goal selecting single seed set. Many real-world scenarios call for multiple sets particularly on media platforms...
The core problem of wound treatment is how to speed up healing. In recent years, the impact microenvironment on healing has received increasing attention. Among many factors affecting microenvironment, bioelectric field and oxygen are crucial. At present, some new technologies based microenvironmental including promote have been used in clinical practice. With further research development roles their mechanisms, a series products that regulate or create most suitable for will be produced,...