Yuan Zhong

ORCID: 0009-0009-5422-7407
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • High-Temperature Coating Behaviors
  • Machine Learning in Healthcare
  • Topic Modeling
  • Metal Alloys Wear and Properties
  • Adversarial Robustness in Machine Learning
  • Materials Engineering and Processing
  • Aluminum Alloys Composites Properties
  • Advanced ceramic materials synthesis
  • Digital Radiography and Breast Imaging
  • Anomaly Detection Techniques and Applications
  • Integrated Circuits and Semiconductor Failure Analysis
  • Natural Language Processing Techniques
  • Advanced materials and composites
  • Drilling and Well Engineering
  • Mineral Processing and Grinding
  • Privacy-Preserving Technologies in Data
  • Fault Detection and Control Systems
  • Artificial Intelligence in Healthcare and Education
  • Peer-to-Peer Network Technologies
  • Artificial Intelligence in Healthcare
  • Vehicle License Plate Recognition
  • Music and Audio Processing
  • Wikis in Education and Collaboration
  • Terahertz technology and applications
  • Security and Verification in Computing

National Synchrotron Radiation Laboratory
2024-2025

University of Science and Technology of China
2024-2025

Chinese University of Hong Kong
2023-2025

China University of Geosciences
2024

Pennsylvania State University
2023-2024

Chinese Academy of Sciences
2024

Hebei Medical University
2024

Hunan University
2023-2024

Sun Yat-sen University
2024

Nanjing University of Information Science and Technology
2023

Abstract The production of formic acid via electrochemical CO 2 reduction may serve as a key link for the carbon cycle in economy, yet its practical feasibility is largely limited by quantity and concentration product. Here we demonstrate continuous at M an industrial‐level current densities (i.e., 200 mA cm −2 ) 300 h on membrane electrode assembly using scalable lattice‐distorted bismuth catalysts. optimized catalysts also enable Faradaic efficiency formate 94.2 % highest partial density...

10.1002/anie.202317628 article EN Angewandte Chemie International Edition 2024-02-02

A novel ternary eutectic salt, NaNO3-KNO3-Na2SO4 (TMS), was designed and prepared for thermal energy storage (TES) to address the issues of narrow temperature range low specific heat solar salt molten salt. The thermo-physical properties TMS-2, such as melting point, decomposition temperature, fusion enthalpy, density, viscosity, capacity volumetric (ETES), were determined. Furthermore, a comparison between commercial TMS-2 carried out. had point 6.5 °C lower 38.93 higher than those use TMS...

10.3390/molecules29102328 article EN cc-by Molecules 2024-05-15

Maximizing the utilization of in situ extraterrestrial resources, including solar-powered water electrolysis using lunar soil as a catalyst, is promising strategy for achieving sustainable fuel and oxygen supply exploration. However, these soil-based silicate minerals suffer from unsatisfactory intrinsic activity splitting due to poor electrical conductivity lack catalytic sites. Here we report use simple Joule-heating method sinter into disordered matrix at ∼2000 °C. The as-prepared...

10.1021/acsmaterialslett.4c02448 article EN ACS Materials Letters 2025-01-10

Thyroid-associated orbitopathy (TAO) is a prevalent inflammatory autoimmune disorder, leading to orbital disfigurement and visual disability. Automatic comprehensive segmentation tailored for quantitative multi-modal MRI assessment of TAO holds enormous promise but still lacking. In this paper, we propose novel method, named cross-modal attentive self-training (CMAST), the multi-organ in using partially labeled unaligned data. Our method first introduces dedicatedly designed pseudo label...

10.1109/jbhi.2025.3545138 article EN IEEE Journal of Biomedical and Health Informatics 2025-01-01

The development of electronic health records (EHR) systems has enabled the collection a vast amount digitized patient data. However, utilizing EHR data for predictive modeling presents several challenges due to its unique characteristics. With advancements in machine learning techniques, deep demonstrated superiority various applications, including healthcare. This survey systematically reviews recent advances learning-based models using Specifically, we introduce background and provide...

10.24963/ijcai.2024/914 article EN 2024-07-26

Terahertz (THz) plasmonic resonance, particularly on artificially designed metasurfaces, has garnered considerable attention for enhancing the identification of biomolecules. However, narrow-band response these resonances hinders comprehensive analysis sample characteristic fingerprints, leading to false-positive results. Here, we developed a multifunctional THz biosensor based broad-spectrum multi-Fano resonance capable noninvasive and ultrasensitive detection trace biological molecular...

10.1109/tps.2024.3368191 article EN IEEE Transactions on Plasma Science 2024-02-29

To explore the Co/Cr ratio impact on high-velocity oxygen fuel (HVOF)-sprayed WC-Co-Cr coatings microstructure and performances, three kinds of coatings, namely WC-4Co-10Cr, WC-7Co-7Cr, WC-10Co-4Cr, were prepared by using a (HVOF) spraying process. The coatings’ phase composition, microstructure, basic mechanical properties, abrasive wear, corrosion resistance investigated. results show that all comprise main WC, minor W2C, amorphous W-Co-Cr phase, besides WC-4Co-10Cr coating containing...

10.3390/ma16217003 article EN Materials 2023-11-01

This study proposes a short-term load prediction method of bidirectional long memory network based on feature mining the power consumption big data in combination with attention mechanism (AT) Bayesian optimization to address problems that considerable amount factors exist and relationship is obscured historical data. The comprehensively considers global features space local time. First, Cen-CK-means clustering used cluster electricity users, statistical, combination, time category...

10.1063/5.0176239 article EN cc-by AIP Advances 2023-12-01

Summary High-voltage electric pulse rock-breaking (HVEPB) has proved to be a novel and inexpensive method of breaking rock regardless composition, but the design electrode drill bit lacks theoretical basis. In this paper, we first establish plasma channel model for breakdown numerical HVEPB, which can simulate electrical effect different bits on HVEPB. Second, analyze effects arrangement structures high-voltage angles channels internal cracks processes through simulation. Finally, describe...

10.2118/219735-pa article EN SPE Journal 2024-03-19

Pretraining has proven to be a powerful technique in natural language processing (NLP), exhibiting remarkable success various NLP downstream tasks. However, the medical domain, existing pretrained models on electronic health records (EHR) fail capture hierarchical nature of EHR data, limiting their generalization capability across diverse tasks using single model. To tackle this challenge, paper introduces novel, general, and unified pretraining framework called MedHMP, specifically designed...

10.18653/v1/2023.emnlp-main.171 article EN cc-by Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing 2023-01-01

The development of electronic health records (EHR) systems has enabled the collection a vast amount digitized patient data. However, utilizing EHR data for predictive modeling presents several challenges due to its unique characteristics. With advancements in machine learning techniques, deep demonstrated superiority various applications, including healthcare. This survey systematically reviews recent advances learning-based models using Specifically, we begin by introducing background and...

10.48550/arxiv.2402.01077 preprint EN arXiv (Cornell University) 2024-02-01

The widespread adoption of Electronic Health Record (EHR) systems in healthcare institutes has generated vast amounts medical data, offering significant opportunities for improving services through deep learning techniques. However, the complex and diverse modalities feature structures real-world EHR data pose great challenges model design. To address multi-modality challenge current approaches primarily rely on hand-crafted architectures based intuition empirical experiences, leading to...

10.48550/arxiv.2401.11252 preprint EN cc-by arXiv (Cornell University) 2024-01-01

This work systematically investigated the microstructure and interfacial characteristics of cold sprayed (CS) 2024Al coating on 2024Al-T3 substrate. Within internal structure layer, recrystallization processes induced by intense stress were seen, resulting in formation nanograins with sizes ranging from 30-100 nm, as well ultrafine grains 100-300 nm. Different bonding modes splat/splat, including mechanical bonding, interlocking, metallurgical have been found at interface between...

10.2139/ssrn.4745098 preprint EN 2024-01-01

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

10.2139/ssrn.4717570 preprint EN 2024-01-01

The widespread adoption of Electronic Health Record (EHR) systems in healthcare institutes has generated vast amounts medical data, offering significant opportunities for improving services through deep learning techniques. However, the complex and diverse modalities feature structures real-world EHR data pose great challenges model design. To address multi-modality challenge current approaches primarily rely on hand-crafted architectures based intuition empirical experiences, leading to...

10.1137/1.9781611978032.41 article EN Society for Industrial and Applied Mathematics eBooks 2024-01-01
Coming Soon ...