A5100348599- Traffic Prediction and Management Techniques
- Recycling and utilization of industrial and municipal waste in materials production
- Dyeing and Modifying Textile Fibers
- Traffic control and management
- Glass properties and applications
- Building Energy and Comfort Optimization
- Photopolymerization techniques and applications
- Pigment Synthesis and Properties
- Traffic and Road Safety
- Advanced ceramic materials synthesis
- Transportation Planning and Optimization
- Concrete and Cement Materials Research
- Nuclear materials and radiation effects
- Skin Protection and Aging
- Time Series Analysis and Forecasting
- Image Enhancement Techniques
- Materials Engineering and Processing
- Nanoparticles: synthesis and applications
- Anomaly Detection Techniques and Applications
- Landfill Environmental Impact Studies
- Advanced Image Fusion Techniques
- Urban Design and Spatial Analysis
- Dye analysis and toxicity
- Human Mobility and Location-Based Analysis
- Nanocomposite Films for Food Packaging
Yunnan University
2019-2025
Shanghai University of Engineering Science
2021-2023
Xihua University
2023
Zhengzhou University of Light Industry
2023
Zhejiang Sci-Tech University
2022-2023
University of Jinan
2023
Northeast Forestry University
2022
Qingdao University of Science and Technology
2022
Inner Mongolia University of Science and Technology
2019-2021
State Key Laboratory of Building Safety and Built Environment
2021
Deep learning-based medical image segmentation methods are generally divided into convolutional neural networks (CNNs) and Transformer-based models. Traditional CNNs limited by their receptive field, making it challenging to capture long-range dependencies. While Transformers excel at modeling global information, high computational complexity restricts practical application in clinical scenarios. To address these limitations, this study introduces VMAXL-UNet, a novel network that integrates...
Aggressive driving behavior (ADB) is one of the main causes traffic accidents. The accurate recognition ADB premise to timely and effectively conduct warning or intervention driver. There are some disadvantages, such as high miss rate low accuracy, in previous data-driven methods ADB, which caused by problems improper processing dataset with imbalanced class distribution single classifier utilized. Aiming deal these an ensemble learning-based method proposed this paper. First, majority...
Porous ceramics are lightweight materials with diverse pore structures, finding wide applications in areas such as thermal insulation, sound absorption, filtration, catalysis, and energy storage. However, excessive shrinkage during the sintering process of porous leads to cracking deterioration, posing significant challenges for achieving complex shape. Despite its importance, field low has not received sufficient attention. This review systematically discusses principles progress...
As a promising new dyeing process without using water, the non-aqueous medium of polyester has attracted people's attention and some progress been made in related research. However, oligomers fiber can affect during use silicone waterless system. Based on this point, oligomer problem system was investigated. The different types were extracted by solvent extraction. A treatment method with little influence used to reduce content polyester. improvement effect after studied, also analyzed. For...
The imputation of time series traffic flow data is great significance to the intelligent transportation, urban planning, and road emergency handling. This paper proposes a filling missing with Generative Adversarial Network (ST-FVGAN), which not only considers spatio-temporal correlation utilizes idea generating Network, but also external factors introduces more comprehensive loss function. Specifically, model firstly constructs Generator network composed convolutional layer, residual block,...
The fabrics of health care function have drawn increasing attention. Herein, AgNO 3 was in-situ reduced into nano silver (AgNPs) by aloe extract (AVE) as reducing agent to gain AgNPs@hinokitiol-grafted chitosan (AgNPs@HTCS). antibacterial and antioxidant cotton fabric were fabricated LBL method using AgNPs@HTCS positive layer hyaluronic acid negative layer. results showed that the optimum preparation conditions follows: 10 mmol/L, HTCS 40 v/v %, AVE 15 mL, 80 °C, 6 h. MIC values against S....
The use of deep learning methods to predict traffic flow in transportation systems has become a hot research project. existing predictive model method faces problems such as long calculation time and difficult data pre‐processing, especially for the prediction effect high area. In this study, authors propose novel framework ST‐ESNet, spatio‐temporal expand‐and‐squeeze networks, that designs several effective strategies considering complexity, non‐linearity uncertainty flow, better captures...
Abstract There has been great interest in the radiant floor cooling system over past decades due to its potential for energy conservation and load shifting, improvement of indoor thermal comfort. However, as a thermally activated building system, performance is highly related enclosure mass through heat exchange with outdoor environment, therefore, operation challenged by control strategies. Because shift characteristic during day variable weather conditions, realistic will increase park if...
Abstract In this study, calcium carbonate, sepiolite, and commonly used diatomite (DE) carriers were mixed to prepare carbonate or sepiolite DE/nano-titanium dioxide (TiO 2 ). The analyses of X-ray diffraction scanning electron microscope confirmed that the particle size nano-TiO was about 20–24 nm in DE/nano-TiO , particles relatively uniform. When (calcium + DE)/nano-TiO used, Ti content composite remained unchanged, while increased a certain extent. Among them, use material significantly....