A5072556657- Advanced Graph Neural Networks
- Online Learning and Analytics
- Software Engineering Research
- Recommender Systems and Techniques
- Human Mobility and Location-Based Analysis
- Organic Food and Agriculture
- Traffic Prediction and Management Techniques
- MicroRNA in disease regulation
- Circular RNAs in diseases
- Stock Market Forecasting Methods
- Electronic and Structural Properties of Oxides
- Data Quality and Management
- Coffee research and impacts
- Gas Sensing Nanomaterials and Sensors
- Neural Networks and Applications
- Urban Heat Island Mitigation
- Context-Aware Activity Recognition Systems
- Air Quality Monitoring and Forecasting
- Body Composition Measurement Techniques
- Microbial Fuel Cells and Bioremediation
- Anaerobic Digestion and Biogas Production
- Biochemical and biochemical processes
- Gait Recognition and Analysis
- Safety and Risk Management
- Arsenic contamination and mitigation
Sichuan University
2025
Jiangxi Agricultural University
2025
Chinese Academy of Medical Sciences & Peking Union Medical College
2023-2024
Northeastern University
2023-2024
Guiyang University
2022-2023
Xiamen University
2023
Southeast University
2023
Academia Sinica
2022
Central South University
2021
Gannan Normal University
2021
In recent years, bismuth-based semiconductors have become a research hotspot in the new semiconductor field due to their unique optical and electronic properties.
Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility modeling complex graph structure data. Among all learning methods, hypergraph is a technique for exploring the implicit higher-order correlations when training embedding space of graph. In this paper, we propose framework named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Learning from Heterogeneity (LFH)</i> that capable...
Normal Tissue Complication Probability (NTCP) models predict temporal lobe injury risk post-intensity-modulated radiotherapy in nasopharyngeal carcinoma patients. Optimal parameter estimation methods for NTCP need refinement. To identify optimal method following intensity-modulated In this study, all patients underwent curative radiation therapy at two research centers. Data of lobes from three cohorts [Data-A, n = 278(training set); Data-B, 119(external validation Data-C, 215(internal...
Gliomas are a type of malignant central nervous system tumor with poor prognosis. Molecular biomarkers gliomas can predict glioma patient’s clinical outcome, but their limitations also emerging. C-X-C motif chemokine ligand family plays critical role in shaping immune landscape and modulating progression, its is elusive. In this work, samples TCGA were treated as the training cohort, for validation two CGGA datasets, four datasets from GEO database, our own enrolled. Consensus clustering...
Abstract An electrochromic device with the as‐obtained nanoporous NiO /ZnO nanoarray as a working electrode was constructed and assembled. The NiO/ZnO film three‐dimensional structure prepared on indium tin oxide (ITO) glass substrate through two‐step route that combined chemical bath deposition method hydrothermal method. reveals noticeable improvement in electrochromism compared of alone, including higher optical modulation (81 %), coloration efficiency (78.5 cm 2 C −1 ), faster response...
Sleep stage classification is crucial for detecting patients' health conditions. Existing models, which mainly use Convolutional Neural Networks (CNN) modelling Euclidean data and Graph Convolution (GNN) non-Euclidean data, are unable to consider the heterogeneity interactivity of multimodal as well spatial-temporal correlation simultaneously, hinders a further improvement performance. In this paper, we propose dynamic learning framework STHL, introduces hypergraph encode sleep...
Twenty agroforestry systems consisting of different management practices (conventional and organic) shade types were set up for coffee plantations in 2,000 at the Tropical Agricultural Research Higher Education Center (CATIE), Turrialba, Costa Rica. The physical (density, bulk density, moisture content, roasting loss) chemical attributes (mineral, total lipid, fatty acids, caffeine, carbohydrate contents) harvested green beans investigated. full sun Erythrina tree significantly improved ( p...
Spatial-temporal data contains rich information and has been widely studied in recent years due to the rapid development of relevant applications many fields. For instance, medical institutions often use electrodes attached different parts a patient analyse electorencephal with spatial temporal features for health assessment disease diagnosis. Existing research mainly used deep learning techniques such as convolutional neural network (CNN) or recurrent (RNN) extract hidden spatial-temporal...
We present a spatial-temporal federated learning framework for graph neural networks, namely STFL. The explores the underlying correlation of input data and transform it to both node features adjacency matrix. setting in ensures privacy while achieving good model generalization. Experiments results on sleep stage dataset, ISRUC_S3, illustrate effectiveness STFL prediction tasks.
This article proposes a family of spatial three translational and one rotational parallel mechanisms (PMs) for pick-and-place operation. Their features are independent rotation the mechanism with four identical limbs, which provided by revolute joints on moving platform. The capability PMs has range at least 180°. focuses synthesis kinematics analysis 4- P(2-SS)R mechanism. First, based Lie group theory, parallelograms used in designing PMs. limbs listed two types synthesized. Then, typical...
A long experiment has been established since 2000 at CATIE (Tropical Agricultural Research and Higher Education Center), Turrialba, Costa Rica. Twenty agro-forestry systems with different shade types managements (organic non-organic) consisting of an incomplete randomized block-design tree as main effect subplots represented by management were set up. The effects on the aroma color generation roasted coffee beans investigated. total protein content was significantly higher ( P &lt; 0.05)...