A5035964645- High Temperature Alloys and Creep
- Intermetallics and Advanced Alloy Properties
- High Entropy Alloys Studies
- Retinal Imaging and Analysis
- Graph theory and applications
- Satellite Communication Systems
- Limits and Structures in Graph Theory
- Statistical and numerical algorithms
- Fusion materials and technologies
- Digital Imaging for Blood Diseases
- Innovative Teaching and Learning Methods
- Recommender Systems and Techniques
- Modeling and Simulation Systems
- Aerospace and Aviation Technology
- Vibration and Dynamic Analysis
- Vibration Control and Rheological Fluids
- Neural Networks and Applications
- AI in cancer detection
- Occupational Health and Safety Research
- Vehicular Ad Hoc Networks (VANETs)
- Advanced Materials and Mechanics
- Human-Automation Interaction and Safety
- Molecular Junctions and Nanostructures
- Autonomous Vehicle Technology and Safety
- Geomechanics and Mining Engineering
First Bethune Hospital of Jilin University
2025
Shihezi University
2024
Xiamen University
2007-2023
Collaborative Innovation Center of Chemistry for Energy Materials
2022
Jinling Institute of Technology
2021-2022
Pearl River Hydraulic Research Institute
2018
Global Risk Institute in Financial Services
2016
Tongji University
2016
Rapid and precise 3D organ segmentation is crucial for the automatic extraction of phenotypic traits, forming a fundamental prerequisite intelligent plant breeding. The advancement deep learning technology has replaced labor-intensive manual measurements traditional computer vision methods, which are sensitive to parameters, in trait extraction. However, current larger network structures not only require extensive point cloud data but also consume substantial computational resources,...
Abstract With the rapid development of online learning platforms, learners have more access to various kinds courses. However, they may find it difficult make choices due massive number The main contribution our research is design a course recommendation framework which extracts multimodal features based on deep models. In this framework, different information course, such as title, and audio comments, are used proper in platforms. Moreover, we utilize both explicit implicit feedback infer...
Objective: This study aims to implement and investigate the application of a special intelligent diagnostic system based on deep learning in diagnosis pterygium using anterior segment photographs. Methods: A total 1,220 photographs normal eyes patients were collected for training (using 750 images) testing 470 develop an model. The images classified into three categories by experts system: (i) group, (ii) observation group pterygium, (iii) operation pterygium. results compared with those...
Abstract Background Screening of malignant hematological diseases is great importance for their diagnosis and subsequent treatment. This study constructed an optimal screening model based on routine blood cell parameters. Methods The venous samples 1751 patients collected from 10 tertiary hospitals in China were divided into a training set (1223 cases) validation (528 cases). In addition to the clinical diagnostic information set, 26 parameters including morphological selected using manual...
This study is aimed at developing an intelligent algorithm based on deep learning and discussing its application for the classification diagnosis of retinal vein occlusions (RVO) using fundus images. A total 501 images healthy eyes patients with RVO were used model training testing to investigate system. The first classified into four categories by disease specialists: (i) (group 0), (ii) branch (BRVO) 1), (iii) central (CRVO) 2), (iv) macular (MBRVO) 3), before being diagnosed ResNet18...
Reducing the vibration of marine power machinery can improve warships' capabilities concealment and reconnaissance. Being one most effective means to reduce mechanical vibrations, active control technology overcome poor effect in low frequency traditional passive isolation. As vibrations arising from operation are actually frequency-varying disturbances, H ∞ method is adopted suppress disturbances. The solve stability problems caused by uncertainty model reshape response function closed loop...
For a conventional narrowband radar system, its insufficient bandwidth usually leads to the lack of detectable information target, and it is difficult for classify target types, such as rotor helicopter, propeller aircraft, jet aircraft. To address classification problem three different types aircraft joint multifeature method based on micro-Doppler effect in echo caused by micromotion proposed this paper. Through characteristics analysis simulation echoes obtained from scattering point...
The civil aviation community is actively exploring and developing the solutions of single pilot operations SPO for large commercial aircraft. Human factors engineering research has been launched, mainly focuses on three solutions: flight deck airborne equipment upgrade, support from ground stations, combined solution "flight stations". This paper reviews analyzez progress human SPO. preliminary outcome tends to solution. However, current not comprehensive cannot provide a complete For future...
For a decade, lot of researches have focused on the development and deployment automated mobility services means for road networks (urban, suburb, rural, highway). In autonomous driving embedded systems, several stages are needed. The first one concerns perception layers. second is dedicated to risk assessment, decision strategy layers optimal path planning. last addresses control/command parts. Based Autonomous Decision-Support Framework (ADSF) EU project Trustonomy, this paper proposes...
As the carrier of water resources, environment and ecology, river course is very important to human ecological in coastal areas. The rapid economic development areas needs take into account improvement regional order achieve a higher level development. characteristics are closely related tidal fluctuation. It an direction for control improve restore self-purification capacity by guiding draining power. In this paper, YACHONG River Basin, which borders Macau Zhuhai, selected as study area....
Automatic differentiation (AD) is a practical field of computational mathematics that growing interest across many industries, including finance. The use reverse mode AD particularly interesting, since it allows for the computation gradients in same time required to evaluate objective function itself. However, requires excessive memory. This memory requirement can make reverse-mode infeasible some cases (depending on complexity and available RAM) slower than expected others, due secondary...
Entropy engineering is commonly identified as an effective approach for phase stabilization of high-entropy alloys (HEAs). However, this high entropy philosophy in γ/γ′ HEAs seems incompatible with their intermetallic nature. Taking (FeCoNi)86Ti7Al7 object, we theoretically viewed the individual/synergetic contributions and enthalpy to stability HEAs. Our results show that accelerates γ but it shows limited positive effects even negative on γ’ intermetallics, especially vibrational entropy....
Abstract The emerging of molecular spintronics offers a unique chance for the design devices with different spin-state, and control spin-state becomes essential spin switches. However, intrinsic switching from low-spin to high-spin state is temperature-dependent process small energy barrier that low temperature required maintain state, thus room-temperature operation single-molecule have not yet been achieved. Here, we investigated charge transport through diamagnetic square planar...
Entropy engineering is usually identified as an effective approach for phase stabilization of high-entropy alloys (HEAs). However, this high entropy philosophy in γ/γ′ HEAs seems incompatible with their intermetallic nature. Taking γ/γ' (FeCoNi)86Ti7Al7 object, we theoretically viewed the individual/synergetic contributions and enthalpy to stability HEAs. Our results show that accelerates γ but it shows limited positive effects even negative on γ' intermetallics, especially vibrational...
The control of molecular folding plays an essential role in the operation machines, and electric field offers a unique strategy to drive conformation charge transport through single molecules but remains unexplored. Here, we use single-molecule using scanning tunneling microscope break junction (STM-BJ) technique. fields induced could lead ~1400% conductance change junctions, folding/unfolding process can be in-situ switched at scale milliseconds. DFT calculations suggest conformational...