A5100745804- Textile materials and evaluations
- Hydrocarbon exploration and reservoir analysis
- Advanced Sensor and Control Systems
- Industrial Technology and Control Systems
- Advanced Algorithms and Applications
- Advanced Decision-Making Techniques
- Advanced Measurement and Detection Methods
- Evaluation Methods in Various Fields
- Bone Tissue Engineering Materials
- Evaluation and Optimization Models
- Geological Studies and Exploration
- Graphene and Nanomaterials Applications
- Geological and Geophysical Studies
- Methane Hydrates and Related Phenomena
- Remote-Sensing Image Classification
- Fire Detection and Safety Systems
- Tribology and Lubrication Engineering
- Energy Load and Power Forecasting
- Seismic Imaging and Inversion Techniques
- Hydrological Forecasting Using AI
- Structural Load-Bearing Analysis
- Bioinformatics and Genomic Networks
- Coal Properties and Utilization
- Advanced Computational Techniques and Applications
- Computational Drug Discovery Methods
Nankai University
2023-2024
Peking University
2012-2024
Shanghai Jiao Tong University
2024
Data Assurance and Communication Security
2023
China University of Geosciences (Beijing)
2014-2023
Qingdao University
2021-2022
Affiliated Hospital of Qingdao University
2021-2022
Chongqing Medical University
2021
Changchun University of Science and Technology
2021
Suzhou Institute of Biomedical Engineering and Technology
2021
The regeneration of diabetic bone defects remains challenging as the innate healing process is impaired by glucose fluctuation, reactive oxygen species (ROS), and overexpression proteinases (such matrix metalloproteinases, MMPs). A "diagnostic" therapeutic dual-logic-based hydrogel for therefore developed through design a double-network consisting phenylboronic-acid-crosslinked poly(vinyl alcohol) gelatin colloids. It exhibits logic to interpret pathological cues (glucose ROS, MMPs)...
In this letter, a new deep learning framework for spectral–spatial classification of hyperspectral images is presented. The proposed serves as an engine merging the spatial and spectral features via suitable architecture: stacked autoencoders (SAEs) convolutional neural networks (DCNNs) followed by logistic regression (LR) classifier. framework, SAEs aimed to get useful high-level one-dimensional which dimension reduction features, while DCNNs can learn rich from training data automatically...
Abstract Drug–target interaction (DTI) prediction is an essential step in drug repositioning. A few graph neural network (GNN)-based methods have been proposed for DTI using heterogeneous biological data. However, existing GNN-based only aggregate information from directly connected nodes restricted a drug-related or target-related and are incapable of capturing high-order dependencies the graph. In this paper, we propose metapath-aggregated (MHGNN) to capture complex structures rich...
Traditional methods for predicting thermal error ignore the correlation between physical world data and virtual data, leading to low prediction accuracy of errors affecting normal processing CNC machine tool (CNCMT) spindle. To solve above problem, we propose a approach based on digital twins long short-term memory (DT-LSTM). DT-LSTM combines high simulation capabilities DT strong LSTM. Firstly, develop system characteristics analysis When is implemented, can obtain theoretical value error....
Consolidated bioprocessing (CBP), integrating cellulase production, cellulose saccharification, and fermentation into one step has been widely considered as the ultimate low-cost configuration for producing second-generation fuel ethanol. However, requirement of a microbial strain able to hydrolyze cellulosic biomass convert resulting sugars high-titer ethanol limits CBP application. In this work, cellulolytic yeasts were developed by engineering Saccharomyces cerevisiae with heterologous...
Purpose The low‐dose computed tomography (CT) imaging can reduce the damage caused by x‐ray radiation to human body. However, CT images have a different degree of artifacts than conventional images, and their resolution is lower that which affect disease diagnosis clinicians. Therefore, methods for noise‐level reduction improvement in inevitably become research hotspot field imaging. Methods In this paper, residual attention modules (RAMs) are incorporated into encoder–decoder convolutional...
In recent times, deep neural networks have drawn much attention in ground-based cloud recognition. Yet such kind of approaches simply center upon learning global features from visual information, which causes incomplete representations for clouds. this paper, we propose a novel method named multi-evidence and multi-modal fusion network (MMFN) recognition, could learn extended information by fusing heterogeneous unified framework. Namely, MMFN exploits multiple pieces evidence, i.e., local...
Nano-hydroxyapatite (nHA) has been widely applied as a tissue-engineering biomaterial and interacted with osteoblasts/stem cells to repair bone defects. In addition, T that coexist in the modulate regulation of osteoimmunology by cytokine formation. However, effects nHA on following regulatory interplay osteogenic differentiation have rarely examined. this work, physicochemical properties needle-like are characterized field emission scanning electron microscopy, zeta potential, Fourier...
Maintenance costs can be greatly reduced by improving the prediction accuracy of wind turbine faults. In this paper, a new method combining K-means clustering and Neural Net classification methods are adopted to predict fault condition turbine. First, data preprocessing has been done with from SCADA (Supervisory Control And Data Acquisition) system. According internal association data, adopting unsupervised learning K-means, similar features transformed one cluster, after which BP is made...
<abstract><p>The reachable set estimation for two-dimensional (2-D) switched nonlinear positive systems (SNPSs) with bounded disturbances given by the Roesser model is investigated in this paper, which both time-varying delays and lagged impulsive effects are taken into account. By applying average dwell time (ADT) technique, we provide a sufficient condition presence of ball such that any solution system converges exponentially within it. An accurate estimate convergence rate...
Abstract: In order to understand the origin and flow of formation water evaluate hydrocarbon accumulation preservation conditions, properties chemistry dynamics Zhenwu area in southern Gaoyou Sag, North Jiangsu Basin, China, have been investigated. The results show that Xuzhuang oilfield is infiltrated discontinuously by meteoric under gravity, which consequently leads desalination water. Formation Caozhuang oilfields less influenced infiltration, interpreted be connate Hydrocarbon...
Mine safety is of primary concern in the underground coal mining system. At present, there a lack an efficient platform to manage numerical simulation procedure and inherent spatiotemporal data for mine disasters. This necessitates coupling model with geographic information system (GIS) practical application. Here, novel tightly coupled GIS presented improve model-data integration. Such tight achieved by developing lattice Boltzmann method (LBM) based turbulent underlying shared FluentEntity...
Composite pistons are often used in highly rated marine diesel engines. Fretting usually occurs on the mating surfaces of piston crown and skirt due to alternating loads. A finite element contact model is introduced calculate temperature stress distribution composite a engine. The Archard Smith–Watson–Topper parameter (a prediction fretting fatigue, also called SWT for short), which as wear fatigue criteria, calculated according strain variation relative slip surface. has been validated by...
Accurate prediction of protein–ligand binding affinities can significantly advance the development drug discovery. Several graph neural network (GNN)-based methods learn representations complexes via modeling intermolecule interactions and spatial structures (e.g., distances angles) complexes. However, these fail to emphasize importance bonds hierarchical complexes, which are significant for affinity prediction. In this article, we propose structure-aware attention diffusion (SGADN)...
The Cambrian carbonate & evaporite paragenesis system in the Sichuan Basin is made up of Longwangmiao, Gaotai and Xixiangchi Fms. So far, great breakthrough has been only Longwangmiao Fm instead latter two, Anyue Gasfield was discovered center this basin. In paper, therefore, analyzed terms its structural–sedimentary setting, sequence stratigraphic framework, sedimentary facies distribution evaporites by using various geologic, logging seismic data. Then, geological model established range...
Abstract: The Tahe Oilfield is a complex petroleum reservoir of Ordovician carbonate formation and made up spatially overlapping fracture‐cavity units. oilfield controlled by cave system resulting from structure‐karst cyclic sedimentation. Due to significant heterogeneity the reservoir, distribution oil water complicated. Horizontally, fresh zone due meteoric can be found in north part Akekule uplift. A marginal freshening caused released mudstone compaction at bottom southern slope. Located...
<title>Abstract</title> Precipitation prediction has important applications in a variety of industries, including agriculture, water conservation, and transportation. In previous study, analyses rainfall were rarely carried out separately from the spatial temporal scales. The data every observation point Zhejiang Province 2015 compared on scale using Inverse Distance Weighted Interpolation (IDW), Kringing Interpolation, Moving Cube (MC), Natural Neighbour Decomposition (MSM), Nearest (NeaN),...