A5101611042- Fuzzy and Soft Set Theory
- Advanced Algebra and Logic
- Hydrocarbon exploration and reservoir analysis
- Advanced Topics in Algebra
- Higher Education and Teaching Methods
- Reservoir Engineering and Simulation Methods
- Hydraulic Fracturing and Reservoir Analysis
- Probabilistic and Robust Engineering Design
- Rings, Modules, and Algebras
- Education and Work Dynamics
- Groundwater flow and contamination studies
- Educational Technology and Pedagogy
- Ideological and Political Education
- Biomedical Text Mining and Ontologies
- Mineral Processing and Grinding
- Water Quality Monitoring and Analysis
- Drilling and Well Engineering
- Model Reduction and Neural Networks
- Seismic Imaging and Inversion Techniques
- Biological Stains and Phytochemicals
- Science Education and Perceptions
- NMR spectroscopy and applications
- Topic Modeling
- Innovative Educational Techniques
- Cancer-related molecular mechanisms research
Peking University
2017-2025
Sinopec (China)
2022-2024
First Hospital of Jilin University
2024
Jilin University
2011-2024
Tsinghua University
2024
Affiliated Hospital of Jining Medical University
2023
South China Institute Of Environmental Sciences
2023
South China Normal University
2022
State Key Laboratory of Chemical Engineering
2019
Tianjin University
2019
To supplement missing logging information without increasing economic cost, a machine learning method to generate synthetic well logs from the existing log data was presented, and experimental verification application effect analysis were carried out. Since traditional Fully Connected Neural Network (FCNN) is incapable of preserving spatial dependency, Long Short-Term Memory (LSTM) network, which kind Recurrent (RNN), utilized establish for reconstruction. By this method, can be generated...
The massive amount and multi-sourced, multi-structured data in the upstream petroleum industry impose great challenge on integration smart application. Knowledge graph, as an emerging technology, can potentially provide a way to tackle challenges associated with oil gas big data. This paper proposes engineering-based method that improve upon traditional natural language processing construct domain knowledge graph based exploration development ontology. is constructed by assembling Sinopec's...
In this study, an efficient stochastic gradient-free method, the ensemble neural networks (ENN), is developed. ENN, optimization process relies on covariance matrices rather than derivatives. The are calculated by randomized maximum likelihood algorithm (EnRML), which inverse modeling method. ENN able to simultaneously provide estimations and perform uncertainty quantification since it built under Bayesian framework. also robust small training data size because of realizations essentially...
A comprehensive and precise analysis of shale gas production performance is crucial for evaluating resource potential, designing a field development plan, making investment decisions. However, quantitative can be challenging because dominated by the complex interaction among series geological engineering factors. In fact, each factor viewed as player who makes cooperative contributions to payoff within constraints physical laws models. Inspired idea, we propose hybrid data-driven framework...
High-spin states of the odd-odd 136Pr nucleus have been investigated using 100Mo(40Ar, 1𝑝3𝑛) reaction with JUROGAM II 𝛾-ray spectrometer. Many new transitions and levels were identified in addition to confirmation most previously known levels. The high statistics present data set allowed multipolarity assignments for many be established, which assigned tentatively. Possible configuration bands above 𝐼𝜋=6+ isomer are analyzed within tilted axis cranking covariant density functional theory...
Indocyanine green (ICG) is a diagnostic dye commonly used in medical imaging and liver function monitoring. Given its widespread use, there need for detailed evaluations of adverse drug reactions real-world settings. As the comprehensive overview safety profile very limited, this study aimed to analyze events (AEs) associated with ICG using data from Food Drug Administration Adverse Event Reporting System (FAERS). Data between 2004Q1 2023Q4 were extracted FAERS database. Signal detection was...
In this paper, we propose an efficient coupled approach for uncertainty quantification of permeability randomly reconstructed three-dimensional (3D) pore images, where the porosity and two-point correlations a realistic sandstone sample are honored. The Joshi-Quiblier-Adler Karhunen-Lo\`eve expansion utilized quick reconstruction 3D images with reduced random dimensionality. eigenvalue problem covariance matrix intermediate Gaussian fields is solved equivalently by kernel method. Then,...
Abstract Subsurface flow and transport problems usually involve some degree of uncertainty. Polynomial chaos expansion can be used as surrogate physical models for uncertainty quantification. However, a global model hardly found responses with strong nonlinearity or irregularity. In this study, we propose novel approach by use the classification method in machine learning, that is, supported vector machine, to cope such nonlinearity/irregularity. Piecewise are constructed relatively smooth...
It has been proposed that cancer stem cells (CSCs) are responsible for almost all malignant phenotypes of tumors. Long non-coding RNA WT1 antisense (WT1-AS) found to be implicated in lung cell stemness. However, the roles and molecular mechanisms WT1-AS development gastric (GCSCs) remain unknown. Our present study showed negatively regulated expression GCSCs. knockdown or Wilms' tumor 1 (WT1) overexpression improved GCSC proliferative migratory capacities, inhibited apoptosis, potentiated...
Unexpected hard rubbing of the fan tip and case occurred during reduced-scale high-bypass performance test which took place at a bypass compressor Test-Facility an institute. A great deal effort had been expended with regard to this event. Firstly, failure investigation was done by means Fault Tree Analysis based on on-site records, pieces dis-assembly check check. Results indicate that fault waspossibly caused combination effect over-rated motor starting acceleration insufficient value...
In this paper, we propose a mixed radio frequency (RF)/free space optical (FSO) unmanned aerial vehicle (UAV) communication system, based on modulating retro-reflector (MRR) and reconfigurable intelligent surface (RIS), which adopts the hybrid L-ary pulse position modulation-binary phase shift keying-subcarrier intensity modulation (L-PPM-BPSK-SIM). More specifically, RF channel follows Rayleigh distribution, while FSO obeys Gamma–Gamma distribution that considers atmospheric turbulence...
The premise of the full use unstructured electronic medical records is to maintain fully protection a patient's information privacy. Presently, in prior processing record date, identification and removing relevant which can be used identify patient research hotspot nowadays. There are very few methods de-identification Chinese their cross-center performance poor. Therefore we develop method mixture rule-based machine learning methods. was tested on 700 from six hospitals. Five-fold cross...
ABSTRACT: To bridge the gap between data and its application, Sinopec Exploration Production Research Institute Schlumberger Digital Integration Group combined capabilities of Sinopec's Business Cooperation Platform (EPBP) Open Underground Data Universe (OSDU) for governance in a private cloud infrastructure. test viability from to rock mechanics parameters were derived direct standardization both single well seismic data. An exclusive application programming interface (API) was formulated,...