A5100708204- Differential Equations and Numerical Methods
- EEG and Brain-Computer Interfaces
- Glaucoma and retinal disorders
- Retinal Diseases and Treatments
- Stability and Controllability of Differential Equations
- Advanced Mathematical Modeling in Engineering
- Brain Tumor Detection and Classification
- Human Mobility and Location-Based Analysis
- Neuroscience and Neural Engineering
- Nonlinear Differential Equations Analysis
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Retinal Imaging and Analysis
- Advanced Memory and Neural Computing
- Numerical methods for differential equations
- Advanced Neural Network Applications
- AI in cancer detection
- Nonlinear Partial Differential Equations
- Service and Product Innovation
- Constraint Satisfaction and Optimization
- Retinoids in leukemia and cellular processes
- Multimedia Communication and Technology
- Visual and Cognitive Learning Processes
- Advanced Radiotherapy Techniques
- Service-Oriented Architecture and Web Services
Southwest Petroleum University
2025
Beihang University
2023-2024
Xinqiao Hospital
2024
Army Medical University
2024
Tianjin Medical University Cancer Institute and Hospital
2023
Anyang Eye Hospital
2016-2022
Linyi University
2021-2022
Sun Yat-sen University
2021
Yanshan University
2017
National Yang Ming Chiao Tung University
2016
Motor imagery (MI) based Brain-computer interfaces (BCIs) have a wide range of applications in the stroke rehabilitation field. However, due to low signal-to-noise ratio and high cross-subject variation electroencephalogram (EEG) signals generated by motor imagery, classification performance existing methods still needs be improved meet need real practice. To overcome this problem, we propose multi-scale spatial-temporal convolutional neural network called MSCNet. We introduce contrastive...
The complex fluid and solid particles inside the throttled pressure well manifold will cause a certain degree of erosion wear on inner wall, which accumulate to form defects make wall thickness thin, may eventually lead failure tee due irreversible damage, triggering serious safety accidents. In order avoid occurrence such accidents, in-service training must be non-destructive testing ensure safe operation manifold. Therefore, for throttle manifold, an simulation model was established carry...
Identifying major depressive disorder (MDD) using objective physiological signals has become a pressing challenge.
Accurate delineation of tumor targets is crucial for stereotactic body radiation therapy (SBRT) non-small cell lung cancer (NSCLC). This study aims to develop a deep learning-based segmentation approach accurately and efficiently delineate NSCLC using diagnostic PET-CT SBRT planning CT (pCT).The PET was registered pCT the transform matrix from registering pCT. We proposed 3D-UNet-based method segment on dual-modality PET-pCT images. network contained squeeze-and-excitation Residual blocks in...
In this paper, we consider an abstract equation$F(\lambda,u)=0$ with one parameter $\lambda$,where $F\in C^p(\mathbb{R} \times X, Y)$, $p\geq 2$, is a nonlinear differentiable mapping,and $X,Y$ are Banach spaces.We apply Lyapunov-Schmidt procedure and Morse Lemma to obtain 'double' saddle-node bifurcation theorem two-dimensional kernel.Applications include perturbed problem semilinear elliptic equation.
According to the latest data from Bureau of Disease Control and Prevention National Health Family Planning Commission, China currently has 199.6 million diabetic patients become world's largest country with diabetes. The prevalence rate is as high 14.3%, which much higher than world average 5.8%. primary-level ophthalmic screening service one important tasks improve medical services, corresponding imaging diagnosis technology an support for health services. Therefore, it very necessary us...
Abstract Brain tumor is a serious threat to human health. Because the size and shape of brain tumors can be uneven, irregular unstructured. Automatic segmentation from magnetic resonance imaging (MRI) challenging task. using computer-aided diagnosis has important clinical significance for prognosis treatment patients. The traditional U-Net network not take full advantage context information, which easy cause loss effective information image. Therefore, we propose multi-scale method based on...
To the memory of
With the popularity of location-based social networks (LBSNs), users would like to share their check-ins with friends for more interactions. These check-in records reflect not only when and where they are, but also what are doing. If we can capture relations location, time, activity factors in LBSNs, platforms provide personalized services users. In this paper, aim infer individual mobility based on LBSNs. For these two inference problems, analyze records, utilize Bayesian network represent...
In this paper, a spatiotemporal diffusive predator-prey system with Holling type-Ⅲ is considered. By using Lyapunov-like function, it proved that the unique local solution of must be global one if interaction intensity small enough. A comparison theorem used to show can extinction or stability in mean square under some additional conditions. Finally, an invariant measure for obtained.
We consider a nonlinear equation F ( ε , λ u ) = 0, where the parameter is perturbation parameter, differentiable mapping from R × X to Y, and Y are Banach spaces. obtain an abstract bifurcation theorem by using generalized saddle‐node theorem.
Logic puzzle games like Sudoku are getting popular for they flexible in playing time and space useful education. For puzzles, difficulty is arguably one of the most important factors problem design. A too easy boring, yet a hard frustrating. Providing problems with adequate to avoid boredom or anxiety thus an issue. In this paper we rate level human oriented, general criteria so that method can be used evaluate logic puzzles. Only few previous research based on real data rating methods...
Service industry has become a major industrial sector in Taiwan. This inseparably unique characteristics such as intangibility, perish ability and heterogeneity, which makes it difficult for service to be mass-produced with consistent quality control. In response this challenge, enterprises need rapid innovation enhance their value. blueprint is tool process design. It can specify how provided, support analysis. However, there no generally accepted practice software designing blueprints....
Based on the analysis of A-share markets in Shanghai and Shenzhen Stock Exchange from 2000 to 2023, this paper systematically evaluates applicability explanatory power Capital Asset Pricing Model (CAPM), Fama-French Three-Factor (FF3) Five-Factor (FF5) Chinese market. The study finds that although CAPM has some early stage, three-factor five-factor models can better explain cross-sectional changes stock returns as market develops. In descriptive statistics, each factor's volatility...
Improving recognition rate of motor imagery (MI)-related electroencephalography (EEG) is great importance for numerous brain computer interface (BCI) applications. However, the performance a typical BCI system greatly relies on effectiveness extracted features from raw EEG signals and ability classifier to correctly identify different MI patterns. Therefore, in this paper, new method based adaptive parameterless empirical wavelet transform (APEWT) selective integrated classification model...