A5101903282- Histone Deacetylase Inhibitors Research
- Computational Geometry and Mesh Generation
- Cancer-related molecular mechanisms research
- Random lasers and scattering media
- Neuroblastoma Research and Treatments
- Computer Graphics and Visualization Techniques
- MicroRNA in disease regulation
- Video Surveillance and Tracking Methods
- Medical Image Segmentation Techniques
- RNA modifications and cancer
- Peptidase Inhibition and Analysis
- Data Management and Algorithms
- Image Retrieval and Classification Techniques
- Optical Coherence Tomography Applications
- Advanced Vision and Imaging
- AI in cancer detection
- Model Reduction and Neural Networks
- Neural Networks and Applications
- Advanced Image and Video Retrieval Techniques
- Infrared Target Detection Methodologies
- Regional Economic and Spatial Analysis
- Advanced Optical Imaging Technologies
- Generative Adversarial Networks and Image Synthesis
- Signaling Pathways in Disease
- Advanced Image Processing Techniques
Jilin University
2012-2025
Jinzhou Medical University
2025
First Affiliated Hospital of GuangXi Medical University
2022-2024
Guangxi Medical University
2022-2024
Shandong Provincial Hospital
2022-2024
Shandong University
2006-2024
Shandong Normal University
2017-2024
Tianjin Chengjian University
2024
Northwestern Polytechnical University
2024
National University of Defense Technology
2023-2024
Irregular human behaviors and univariate datasets remain as two main obstacles of data-driven energy consumption predictions for individual households. In this study, a hybrid deep learning model is proposed combining an ensemble long short term memory (LSTM) neural network with the stationary wavelet transform (SWT) technique. The SWT alleviates volatility increases data dimensions, which potentially help improve LSTM forecasting accuracy. Moreover, further enhances performance method....
Medical image segmentation plays an important role in disease diagnosis and surgical guidance. There are two problems the current field of medical segmentation. First, due to inherent locality convolution operations, it is difficult for convolutional neural network models capture global context information. Second, data set usually small model at risk overfitting. To solve above problems, we innovatively introduced Transformer information bottlenecks based on UNet (IB-TransUNet). can...
Abstract Background Accurate medical image segmentation is crucial for disease diagnosis and surgical planning. Transformer networks offer a promising alternative as they can learn global features through self‐attention mechanisms. To further enhance performance, many researchers have incorporated more layers into their models. However, this approach often results in the model parameters increasing significantly, causing potential rise complexity. Moreover, datasets of usually fewer samples,...
Abstract This paper presents an efficient scheme for single-pixel imaging (SPI) utilizing a phase-controlled fiber laser array and untrained deep neural network. The lasers are arranged in compact hexagonal structure coherently combined to generate illuminating light fields. Through the utilization of high-speed electro-optic modulators each individual module, randomly modulated enables rapid speckle projection onto object interest. Furthermore, network is incorporated into image...
There are limited real-world data evidence assessing the clinical characteristics of hospitalized osteoporotic fractures in China. To investigate major Northeast We identified fracture patients aged 50 and over from First Affiliated Hospital Jinzhou Medical University between January 1, 2018, December 31, 2022. Major including hip, vertebral, forearm wrist, humerus were diagnosed based on x-ray reports extracted electronic medical records (EMR). The cause fracture, comorbidities, surgical...
Diabetic foot ulcers (DFU) are among the serious complications which closely linked to diabetes mellitus. However, there is still a lack of accurate and effective standard prevention treatment programs for DFU. In this manuscript, we have investigated function lncRNA cancer susceptibility candidate 2 (CASC2)/miR-155/hypoxia-inducible factor 1-alpha (HIF-1α) in wound healing We analyzed CASC2`s expression marginal tissues patients mice with Additionally, interaction relationship mechanism...
Transformer network is widely emphasized and studied relying on its excellent performance. The self-attention mechanism finds a good solution for feature coding among multiple channels of electroencephalography (EEG) signals. However, using the to construct models EEG data suffers from problem large amount required complexity algorithm.
The onset of osteonecrosis the femoral head (ONFH) is intimately associated with extensive administration glucocorticoids (GCs). Long-term stimulation GCs can induce oxidative stress in both osteoclasts (OCs) and osteoblasts (OBs), resulting disturbance bone remodelling. An alkaloid named crebanine (CN) demonstrates pharmacological properties including anti-inflammation reactive oxygen species (ROS) modulation. Our objective to assess therapeutic potential CN treating ONFH elucidate...
We propose the first graphics processing unit (GPU) solution to compute 2D constrained Delaunay triangulation (CDT) of a planar straight line graph (PSLG) consisting points and edges. There are many existing CPU algorithms solve CDT problem in computational geometry, yet there has been no prior approach this efficiently using parallel computing power GPU. For special case where PSLG consists just points, which is simply normal (DT) problem, hybrid GPU together with partially speed up...
We propose a Fermat spiral laser array as illumination source in ghost imaging. Due to the aperiodic structure, generates illuminating light field without spatial periodicity on normalized second-order intensity correlation function. A single-pixel detector is used receive signal from object for image reconstruction. The effects of parameters quality imaging are analyzed comprehensively. Through experimental demonstration, successfully achieves with high by combining compressive sensing...
We propose the first GPU solution to compute 2D constrained Delaunay triangulation (CDT) of a planar straight line graph (PSLG) consisting points and edges. There are many CPU algorithms developed solve CDT problem in computational geometry, yet there has been no known prior approach using parallel computing power this efficiently. For special case with PSLG just points, which is normal problem, hybrid already presented that uses together partially speed up computation. Our work, on other...
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of data density. The framework defines prior noise as a standard Gaussian distribution, whereas corresponding distribution may be more complicated than which potentially introduces inefficiency in denoising into sample because discrepancy between and prior. In this paper, we propose PriorGrad improve efficiency conditional model for speech synthesis (for example,...