A5077994352- Advanced Neural Network Applications
- Advanced Sensor and Control Systems
- Smart Grid and Power Systems
- Distributed Control Multi-Agent Systems
- Vehicle License Plate Recognition
- Power Systems and Renewable Energy
- Advanced Algorithms and Applications
- Thermography and Photoacoustic Techniques
- Neural Networks Stability and Synchronization
- Industrial Vision Systems and Defect Detection
- Wireless Sensor Networks and IoT
- EEG and Brain-Computer Interfaces
- Video Surveillance and Tracking Methods
- Control Systems and Identification
- Advanced Computational Techniques and Applications
- ECG Monitoring and Analysis
- Environmental Quality and Pollution
- Advanced Measurement and Detection Methods
- Autonomous Vehicle Technology and Safety
- Power Systems and Technologies
- Evaluation Methods in Various Fields
- Advanced Control Systems Optimization
- MicroRNA in disease regulation
- Thermal properties of materials
- Fault Detection and Control Systems
Second Hospital of Anhui Medical University
2022-2024
Zhejiang University of Science and Technology
2007-2024
Anhui Medical University
2016-2024
First Affiliated Hospital of Anhui Medical University
2022
Zhejiang University
2021
Nanjing University of Aeronautics and Astronautics
2021
Institute of Automation
2006
Acute lung injury (ALI) is characterized by pulmonary diffusion abnormalities that may progress to multiple-organ failure in severe cases. There are limited effective treatments for ALI, which makes the search new therapeutic avenues critically important. Macrophages play a pivotal role pathogenesis of ALI. The degree macrophage polarization closely related severity and prognosis S100A9 promotes M1 macrophages. present study assessed effects S100A9-gene deficiency on acute injury. Our cohort...
Abstract Chronic trauma in diabetes is a leading cause of disability and mortality. Exosomes show promise tissue regeneration. This study investigates the role exosomes derived from adipose stem cells (ADSC-Exos) angiogenesis. MiRNA-seq analysis revealed significant changes 47 genes human umbilical vein endothelial (HUVECs) treated with ADSC-Exos, miR-146a-5p highly expressed. MiR-146a-5p mimics enhanced pro-angiogenic effects while inhibitors had opposite effect. JAZF1 was identified as...
The repair of critical-sized bone defects (CSBD) remains a significant challenge in clinical practice. Personalized 3D porous scaffolding is generally considered an ideal approach for directed regeneration CSBD, which usually has irregular and complex geometry. In this study, we designed customized scaffold rabbit radius based on body-centered cubic unit. Borate bioactive glass/polycaprolactone (BBG/PCL) composite scaffolds with different BBG contents (0%, 5%, 10%, 20%, 40%) were fabricated...
This study proposes a GC-YOLOv5s crack-detection network of UAVs to work out several issues, such as the low efficiency, detection accuracy caused by shadows, occlusions and contrast, influences due road noise in classic methods complicated traffic routes. A Focal-GIOU loss function with focal has been introduced this proposed algorithm, which is applied address issue imbalance difficult easy samples crack images. Meanwhile, original localization CIOU replaced GIOU that more suitable for...
In the realm of power systems, short-term electric load forecasting is pivotal for ensuring supply–demand balance, optimizing generation planning, reducing operational costs, and maintaining grid stability. Short-term curves are characteristically coarse, revealing high-frequency data upon decomposition that exhibit pronounced non-linearity significant noise, complicating efforts to enhance precision. To address these challenges, this study introduces an innovative model. This model employs...
Abstract To address several common problems of finger vein recognition, a lightweight recognition algorithm by means small sample has been proposed in this study. First all, Gabor filter is applied to deal with the images for purpose that these processed can simulate kind situation at low temperature, such generalization ability model be improved as well. By cutting down amount convolutional layers and fully connected VGG-19, network given. Meanwhile, activation function some replaced...
Nonparametric Bayesian modeling receive a great deal of attention in last decades. Dirichlet Process Mixture Model (DPMM) based soft sensing model is developed where the number parameters can be determined automatically on given data. The core task nonparametric posterior inference. A novel variational inference algorithm proposed to determine distribution. In this approach, gradient computation optimization derived by Monte Carlo sampling which not restricted specific expression. To address...
Arrhythmia classification is introduced for automatic diagnosis and treatment of cardiac diseases. Scalar autoregressive (AR) modeling was performed on two-lead electrocardiogram (ECG) signals to extract features. AR coefficients were estimated from each channel concatenated together form the ECG Five types obtained MIT-BIH database including normal sinus rhythm, atria premature contraction, ventricular tachycardia fibrillation. A stage-by-stage quadratic discriminant function (QDF) based...
YOLO (You Only Look Once), as a target detection algorithm with good speed and precision, is widely used in the industry. In process of driving, vehicle image captured by driving camera detected it extracts license plate front part vehicle. Compared network structure YOLOv3-tiny algorithm, acquisition method anchor box improved combining Birch algorithm. order to improve real-time performance, original two-scale added multi-scale prediction three-scale ensure its accuracy. Finally,...
Complete and high-quality labeled dataset is indispensable for image classification. Considering the often arduous task of data labeling, clustering algorithms are commonly utilized in preliminary stages classification to perform categorization. Traditional algorithms, such as K-means Gaussian Mixture Model, struggle effectively cluster images. In this paper, we propose a novel method utilizing teacher-student model autoencoder. Specifically, teacher fully connected autoencoder student...
This paper is concerned with the sampled-data consensus of networked Euler-Lagrange systems. The system has enormous advantages in analyzing and designing dynamical Yet, some problems arise equation-based control laws when they contain feedback. law differentiates discontinuous signals to generate its input. In this process, infinities input are inevitable. main goal work eliminate these infinities. To reach goal, a class differentiable scaling functions designed replace conventional...
Abstract Lane detection is a key technical challenge in autonomous driving and advanced assistance systems. The current lane system has insufficient robustness low accuracy problem complex harsh environmental conditions, lacks research on visual cues without information. In order to accurately effectively detect multiple lanes challenging scenarios meet the real-time requirements of actual driving, method based cross attention mechanism proposed this paper. Firstly, by embedding feature...
The thermal properties of bipolar plates, being key elements polymer electrolyte membrane fuel cells, significantly affect their heat conduction and management. This study employed an innovative approach known as a flow loop integral method to experimentally assess the in-plane conductivity graphite addressing constraints traditional methods that have strict demands for stimulation, boundary or initial conditions, sample size. employs infrared imaging gather information from surface...