A5088612057- Computational Drug Discovery Methods
- Scientific Computing and Data Management
- Complex Network Analysis Techniques
- Analytical Chemistry and Chromatography
- Distributed and Parallel Computing Systems
- Opinion Dynamics and Social Influence
- Protein Structure and Dynamics
- Machine Learning in Materials Science
- Spectroscopy and Chemometric Analyses
- Advanced Graph Neural Networks
- Cloud Computing and Resource Management
- Cardiovascular Function and Risk Factors
- Cardiac Imaging and Diagnostics
- Bioinformatics and Genomic Networks
- Advanced Chemical Sensor Technologies
- Recommender Systems and Techniques
- Text and Document Classification Technologies
- Machine Learning in Bioinformatics
- Advanced Authentication Protocols Security
- Advanced Clustering Algorithms Research
- Digital Marketing and Social Media
- Peer-to-Peer Network Technologies
- Chemical Thermodynamics and Molecular Structure
- Advancements in Battery Materials
- User Authentication and Security Systems
Lanzhou University
2016-2025
East China Normal University
2025
Dalian University
2024
Dalian University of Technology
2024
Chinese Academy of Medical Sciences & Peking Union Medical College
2017-2024
Beijing Institute of Petrochemical Technology
2024
Nanjing University of Science and Technology
2023-2024
Beijing Hospital
2010-2024
Chinese Academy of Forestry
2021-2024
University of Minnesota
2013-2024
Hard Carbon have become the most promising anode candidates for sodium-ion batteries, but poor rate performance and cycle life remain key issues. In this work, N-doped hard carbon with abundant defects expanded interlayer spacing is constructed by using carboxymethyl cellulose sodium as precursor assistance of graphitic nitride. The formation nanosheet structure realized CN• or CC• radicals generated through conversion nitrile intermediates in pyrolysis process. This greatly enhances...
Support vector machines (SVMs) were used to develop QSAR models that correlate molecular structures their toxicity and bioactivities. The performance predictive ability of SVM are investigated compared with other methods such as multiple linear regression radial basis function neural network methods. In the present study, two different data sets evaluated. first one involves an application development a model for prediction toxicities 153 phenols, second investigation deals between...
A least-squares support vector machine (LSSVM) was used for the first time as a novel machine-learning technique prediction of solubility C60 in large number diverse solvents using calculated molecular descriptors from structure alone and on basis software CODESSA inputs. The heuristic method to select correlated build linear model. Both nonlinear models can give very satisfactory results: square correlation coefficient R(2) 0.892 0.903, root-mean-square error 0.126 0.116, respectively,...
Tumor-immune crosstalk within the tumor microenvironment (TME) occurs at all stages of tumorigenesis. Tumor-associated M2 macrophages play a central role in development, but molecular underpinnings have not been fully elucidated. We demonstrated that produce interleukin 1β (IL-1β), which activates phosphorylation glycolytic enzyme glycerol-3-phosphate dehydrogenase (GPD2) threonine 10 (GPD2 pT10) through phosphatidylinositol-3-kinase-mediated activation protein kinase-delta (PKCδ) glioma...
Abstract Seeking high‐performance photoresists is an important item for semiconductor industry due to the continuous miniaturization and intelligentization of integrated circuits. Polymer resin containing carbonate group has many desirable properties, such as high transmittance, acid sensitivity chemical formulation, thus serving promising photoresist material. In this work, a series aqueous developable CO 2 ‐sourced polycarbonates (CO ‐PCs) were produced via alternating copolymerization...
Long-range ordered phases in most high-entropy and medium-entropy alloys (HEAs/MEAs) exhibit poor ductility, stemming from their brittle nature of complex crystal structure with specific bonding state. Here, we propose a design strategy to severalfold strengthen single-phase face-centered cubic (fcc) Ni 2 CoFeV MEA by introducing trigonal κ L1 intermetallic via hierarchical ordering. The tri-phase has an ultrahigh tensile strength exceeding 1.6 GPa outstanding ductility 30% at room...
1060/7N01/1060 laminated composites with reliable bonding interfaces were successfully fabricated via single-pass hot rolling at 475 °C. The effects of layer thickness ratios on microstructure and mechanical property synthesized laminates studied using scanning electron microscope, transmission microscope backscattered diffraction technique accompanied hardness tensile testing. Moreover, DCR (direct cold rolling) ACR (solution annealing peak ageing plus samples also explored. results show...
The support vector machine (SVM), as a novel type of learning machine, for the first time, was used to develop QSPR model that relates structures 35 amino acids their isoelectric point. Molecular descriptors calculated from structure alone were represent molecular structures. seven selected using GA-PLS, which is sophisticated hybrid approach combines GA powerful optimization method with PLS robust statistical variable selection, inputs RBFNNs and SVM predict point an acid. optimal developed...
The Support Vector Machine (SVM) classification algorithm, recently developed from the machine learning community, was used to diagnose breast cancer. At same time, SVM compared several techniques currently in this field. task involves predicting state of diseases, using data obtained UCI repository. outperformed k-means cluster and two artificial neural networks on whole. It can be concluded that nine samples could mislabeled comparison techniques.
Collaborative filtering (CF) predicts user preferences in item selection based on the known ratings of items. As one most common approach to recommender systems, CF has been proved be effective for solving information overload problem. can divided into two main branches: memory-based and model-based. Most present researches improve accuracy Memory-based algorithms only by improving similarity measures. But few focused prediction score models which we believe are more important than The...