A5037408723- Traditional Chinese Medicine Studies
- Functional Brain Connectivity Studies
- Advanced Neuroimaging Techniques and Applications
- Dementia and Cognitive Impairment Research
- Cardiac electrophysiology and arrhythmias
- Arctic and Antarctic ice dynamics
- Slime Mold and Myxomycetes Research
- Plant and Biological Electrophysiology Studies
- Brain Tumor Detection and Classification
- Biomedical Text Mining and Ontologies
- Ion channel regulation and function
- Surface Modification and Superhydrophobicity
- Bioinformatics and Genomic Networks
- Wireless Signal Modulation Classification
- Advanced Photocatalysis Techniques
- Planarian Biology and Electrostimulation
- Neurological Disease Mechanisms and Treatments
- Structural Integrity and Reliability Analysis
- Advanced Graph Neural Networks
- Electrocatalysts for Energy Conversion
- Advanced SAR Imaging Techniques
- Radar Systems and Signal Processing
- Additive Manufacturing and 3D Printing Technologies
- Medical Imaging Techniques and Applications
- Icing and De-icing Technologies
Dalian Maritime University
2024-2025
Shanghai University
2022-2024
Xidian University
2022-2024
Hebei University of Science and Technology
2020-2022
University of Science and Technology Beijing
2022
Kyushu University
2021
Huazhong University of Science and Technology
2002-2010
Union Hospital
2010
Abstract Exploring individual brain atrophy patterns is of great value in precision medicine for Alzheimer's disease (AD) and mild cognitive impairment (MCI). However, the current detection models are deficient. Here, we proposed a framework called generative adversarial network constrained multiple loss autoencoder (GANCMLAE) precisely depicting patterns. The GANCMLAE model was trained using normal controls (NCs) from Disease Neuroimaging Initiative cohort, Xuanwu cohort employed to...
Evidence-based treatment is the basis of traditional Chinese medicine (TCM), and accurate differentiation syndromes important for in this context. The automatic unstructured medical records requires two steps: word segmentation text classification. Due to ambiguity language peculiarities syndrome differentiation, these tasks pose a daunting challenge. We use classification model TCM, multi-task learning (MTL) deep accomplish challenging differentiation. Two classic neural...
The long QT syndrome (LQTS) is a cardiac disorder characterized by prolongation of the interval on electrocardiograms (ECGs), syncope and sudden death caused specific ventricular tachyarrhythmia known as torsade de pointes. LQTS mutations in ion channel genes including sodium gene SCN5A, potassium subunit KCNQ1, KCNH2, KCNE1, KCNE2. Little information available about Chinese population. In this study, we 42 families for two most common genes, KCNQ1 KCNH2. We report here identification four...
Inner surface of Nepenthes slippery zone shows anisotropic superhydrophobic wettability. Here, we investigate what factors cause the anisotropy via sliding angle measurement, morphology/structure observation and model analysis. Static contact ultrapure-water droplet exhibits value 154.80°-156.83°, towards pitcher bottom up is 2.82 ± 0.45° 5.22 0.28°, respectively. The under investigation covered by plenty lunate cells with both ends bending downward, a dense layer wax coverings without...
Abstract Background Functional connectivity (FC) biomarkers play a crucial role in the early diagnosis and mechanistic study of Alzheimer’s disease (AD). However, identification effective FC remains challenging. In this study, we introduce novel approach, spatiotemporal graph convolutional network (ST-GCN) combined with gradient-based class activation mapping (Grad-CAM) model (STGC-GCAM), to effectively identify for AD. Methods This multi-center cross-racial retrospective involved 2,272...
The conventional methods for interpreting tau PET imaging in Alzheimer's disease (AD), including visual assessment and semi-quantitative analysis of fixed hallmark regions, are insensitive to detect individual small lesions because the spatiotemporal neuropathology's heterogeneity. In this study, we proposed a latent feature-enhanced generative adversarial network model automatic extraction brain deposition regions. propose can learn distribution characteristics images cognitively normal...
Abstract Ship-ice interaction is an important engineering issue in the polar region. Choosing appropriate sea ice simulation method of ship-ice collision will have a greater impact on force ship hull. Sea complex solid. If you want to truly Simulating actual properties presents significant challenges. In order more accurately simulate navigation, this study uses nonlinear explicit finite element for calculation, and establishes calculation model based piecewise linear plastic constitutive...
Abstract In a high-speed sampling system, the clock jitter of analog-to-digital converters (ADCs) will greatly affect its accuracy, leading to reduction signal-to-noise ratio (SNR) system output. Therefore, it is necessary compensate results reduce error caused by measuring distribution sequence jitter. this paper, influence on ADC process analyzed, and an measurement scheme based simple coherent algorithm investigated. This can accurately measure jitter, has characteristics low...
Slippery zone of Nepenthes alata presents anisotropic friction behaviors depending on its evolved structures. Studies have demonstrated the contribution lunate cells, but role wax coverings has not been specially investigated.In this paper, we showed findings obtained from AFM scanning and SEM observation characterizing frictional properties coverings.Friction data generated by cantilever along downward upward directions were different.The difference was insignificant (2.56%) when applying...
Exploring individual brain atrophy patterns is of great value for precision medicine Alzheimer’s disease (AD) and mild cognitive impairment (MCI). However, current detection models are lacking. In this study, we proposed a framework called generative adversarial networks constrained multiple loss autoencoder (GANCMLAE). The results showed that the GANCMLAE model could achieve good image reconstruction performance on Structural Similarity Index Measure (SSIM) (0.929 ± 0.003), Peak...
王立新 1 张硕研 闫世兴 2 董世运 (1.河北科技大学机械工程学院 石家庄 050018； 2. 陆军装甲兵学院再制造技术国家重点实验室 北京 100072) 摘要：猪笼草滑移区因具有微纳复合结构而呈现超疏水润湿特性，为超疏水表面研制提供了潜在的仿生原型，但其超疏水润 湿机理仍未得到充分揭示，这源于现有技术手段不能准确获取液滴对滑移区微纳复合结构的浸润程度。构建滑移区微纳复合 结构(月骨体、 蜡质晶体)的三维模型， 划分网格并对液滴网格单元的顶点进行受力分析； 然后基于最小能量原理并采用 Surface Evolver
Pulse compression signal is widely used in the field of radar ranging to solve contradiction between range resolution and operating range. Vector analyzer an important tool for measuring modulation quality. The commonly single-pulse envelope extraction method neural network has high algorithm complexity not suitable application instrument software platform. In this paper, a single pulse based on model proposed. Firstly, top power, base overall amplitude are determined by using histogram;...
In this paper, we present a convergence proof for an iterative procedure of local mode filtering. We formulate the filtering as quadratic optimization problem based on Legendre transform convex function, from which two closed-form expressions at each iteration step are derived variables to be optimized. Those analytical solutions ensure that value objective function increases monotonically with progress procedure. also show experimental results using grayscale image, support our theoretical...
Background: Functional connectivity (FC) biomarkers play a crucial role in the early diagnosis and mechanistic study of Alzheimer's disease (AD). However, identification effective FC remains challenging. In this study, we introduce novel approach, spatio-temporal graph convolutional network (ST-GCN) combined with gradient-based class activation mapping (Grad-CAM) model (STGC-GCAM), to effectively identify for AD.Methods: This multi-center cross-racial retrospective involved 2,272...
Abstract Different tau positron emission tomography (PET) radiotracer holds promises for monitoring the accumulation of pathology in vivo. However, low availability relative to massive demand tau-PET has ultimately hinders potential benefits majority patients. Here, we developed a unified deep learning model synthesizing images from more available structural magnetic resonance imaging (sMRI). A total 1387 subjects two different cohorts were included this study, involving with 18...