A5101367989- Human Pose and Action Recognition
- Model Reduction and Neural Networks
- Cardiac Imaging and Diagnostics
- Cardiac Valve Diseases and Treatments
- Generative Adversarial Networks and Image Synthesis
- Identification and Quantification in Food
- Gaussian Processes and Bayesian Inference
- Design Education and Practice
- Data Management and Algorithms
- Digital Media and Visual Art
- Time Series Analysis and Forecasting
- Water Quality Monitoring Technologies
- Meteorological Phenomena and Simulations
- Neural Networks and Applications
- Oceanographic and Atmospheric Processes
- Spectroscopy and Chemometric Analyses
- Traffic Prediction and Management Techniques
- Anomaly Detection Techniques and Applications
- Color perception and design
- Climate variability and models
- Ergonomics and Musculoskeletal Disorders
- Cardiovascular Function and Risk Factors
University of Science and Technology of China
2024-2025
Tencent (China)
2024
Southeast University
2024
Jiangnan University
2024
Anhui Xinhua University
2019
Abstract The unusually warm sea surface temperature events known as marine heatwaves (MHWs) have a profound impact on ecosystems. Accurate prediction of extreme MHWs has significant scientific and financial worth. However, existing methods still certain limitations, especially in the most MHWs. In this study, to address these issues, based physical nature MHWs, we created novel deep learning neural network that is capable accurate 10 day MHW forecasting. Our framework significantly improves...
Aquatic biodiversity monitoring relies on species recognition from images. While deep learning (DL) streamlines the process, performance of these method is closely linked to large-scale labeled datasets, necessitating manual processing with expert knowledge and consume substantial time, labor, financial resources. Semi-supervised (SSL) offers a promising avenue improve DL models by utilizing extensive unlabeled samples. However, complex collection environments long-tailed class imbalance...
Modeling the evolution of physical dynamics is a foundational problem in science and engineering, it regarded as modeling an operator mapping between infinite-dimensional functional spaces. Operator learning methods, underlying high-dimensional latent space, have shown significant potential dynamics. However, there remains insufficient research on how to approximate using finite-dimensional parameter space. Inappropriate dimensionality representation leads convergence difficulties,...
Safety Helmet comfort factor analysis is the foundation of safety helmet design.This paper analyzes characteristics comfort, adopts questionnaire investigation requirements each component system analyzed, at same time build factors that affect level model, and various influence importance. The relevant research results can be used as basis for design helmet.