A5068620302- Advanced Memory and Neural Computing
- Neural dynamics and brain function
- Advanced Data Compression Techniques
- Neural Networks and Reservoir Computing
- Spectroscopy and Quantum Chemical Studies
- Complex Network Analysis Techniques
- Chemical and Physical Properties in Aqueous Solutions
- Thermodynamic properties of mixtures
- Human Mobility and Location-Based Analysis
- Electron and X-Ray Spectroscopy Techniques
- Advanced Electron Microscopy Techniques and Applications
- Advanced Vision and Imaging
- Metal-Organic Frameworks: Synthesis and Applications
- Bauxite Residue and Utilization
- Advanced Neural Network Applications
- Molten salt chemistry and electrochemical processes
- Advanced Image and Video Retrieval Techniques
- Machine Learning in Bioinformatics
- Advanced ceramic materials synthesis
- Image Processing Techniques and Applications
- Molecular Sensors and Ion Detection
- Protein Structure and Dynamics
- Neural Networks and Applications
- Gambling Behavior and Treatments
- Water Quality Monitoring and Analysis
Northwest Normal University
2016-2025
Qingdao Mental Health Center
2024-2025
Queen's University Belfast
2024
Lanzhou University
2017-2024
Jining Medical University
2024
Alcoa (United States)
2011-2024
First Hospital of Lanzhou University
2019-2024
Hainan University
2024
Suzhou Research Institute
2023-2024
Almac (United Kingdom)
2024
Rapidly predicting enzyme properties for catalyzing specific substrates is essential identifying potential enzymes industrial transformations. The demand sustainable production of valuable industry chemicals utilizing biological resources raised a pressing need to speed up biocatalyst screening using machine learning techniques. In this research, we developed an all-purpose deep-learning-based multiple-toolkit (ALDELE) workflow catalysts. ALDELE incorporates both structural and sequence...
We present an ab initio molecular dynamics study of the alkali metal ions Li+, Na+, K+ and Cs+, alkaline earth Mg2+ Ca2+ in both pure water electrolyte solutions containing counterions Cl- SO42-. Simulations were conducted using different density functional theory methods (PBE, BLYP revPBE), with without inclusion dispersion interactions (-D3). Analysis ion-water structure interaction strength, exchange between first second hydration shell, hydrogen bond network low-frequency reorientation...
Generative dataset expansion methods can effectively alleviate the scarcity of data in dermoscopic image segmentation but commonly employ a two-stage synthesis strategy that contains additional learnable components and complex design, which results high computational resource costs. Diffusion models utilizing self-conditioning have shown strong potential for efficiently reusing priors pipeline without relying on excessively complicated conditioning designs. Inspired by this, we propose...
Human mobility patterns deeply affect the dynamics of many social systems. In this paper, we empirically analyze real-world human movements based GPS records, and observe rich scaling properties in temporal-spatial as well an abnormal transition speed-displacement patterns. We notice that displacements at population level show significant positive correlation, indicating a cascade-like nature movements. Furthermore, our analysis individual finds displacement distributions users with strong...
Abstract We present an atomistic simulation scheme for the determination of hydration number ( h ) aqueous electrolyte solutions based on calculation water dipole reorientation dynamics. In this methodology, time evolution solution generated from ab initio molecular dynamics simulations is used to compute different subpopulations. The value determined by considering whether subpopulations retarded with respect bulk‐like behavior. application computational protocol magnesium chloride (MgCl 2...
Darknet markets are online services behind Tor where cybercriminals trade illegal goods and stolen datasets. In recent years, security analysts law enforcement start to investigate the darknet study cybercriminal networks predict future incidents. However, vendors in these often create multiple accounts (\em i.e., Sybils), making it challenging infer relationships between identify coordinated crimes. this paper, we present a novel approach link of same through photo analytics. The core idea...
A reliable assessment model can help financial institutions to increase profits and reduce losses. In credit data, classes of the data are extremely imbalanced owing small sample size bad customers. this paper, we propose a risk algorithm using deep neural networks with clustering merging, achieve balanced dataset judge whether customer be granted loans. algorithm, majority class samples divided into several subgroups by k-means each subgroup is merged minority produce subgroups, these...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Gastric cancer (GC) often develops resistance to cisplatin treatment, but while latent transforming growth factor β-binding protein (LTBP2) is recognized as a potential regulator in GC, its specific role not fully understood. This study investigated LTBP2's impact on GC. LTBP2 expression was assessed various GC cell lines, and correlation with sensitivity determined through viability assays. Lentivirus-mediated silencing HGC-27 cells demonstrated enhanced sensitivity, reduced proliferation,...
Nowadays online searches are undeniably the most common form of information gathering, as witnessed by billions clicks generated each day on search engines. In this work we describe foraging processes that take place semi-infinite line. Using a variety quantities like probability distributions and complementary cumulative distribution functions step length waiting time well mean square displacements entropies, analyze three different click-through logs contain detailed millions queries...