A5103076897- Air Quality and Health Impacts
- Chinese history and philosophy
- Air Quality Monitoring and Forecasting
- Seismic Imaging and Inversion Techniques
- Vehicle emissions and performance
- Hydraulic Fracturing and Reservoir Analysis
- Hydrocarbon exploration and reservoir analysis
- Advanced Computational Techniques and Applications
- Complex Network Analysis Techniques
- Rough Sets and Fuzzy Logic
- Meteorological Phenomena and Simulations
- Tropical and Extratropical Cyclones Research
- Topic Modeling
- Drilling and Well Engineering
- Ocean Waves and Remote Sensing
- Cryptography and Data Security
- Data Mining Algorithms and Applications
- Context-Aware Activity Recognition Systems
- Geological and Geochemical Analysis
- AI-based Problem Solving and Planning
- Human Pose and Action Recognition
- Text and Document Classification Technologies
- Cryospheric studies and observations
- Cloud Data Security Solutions
- Political Economy and Marxism
Shanghai Normal University
2003-2024
Research Institute of Petroleum Exploration and Development
2013-2022
Shanghai University
2007-2008
Peking University
2008
Hanalei Watershed Hui
2005
Strong tropical cyclones have made a drastic effect on human life and natural environment. As large amounts of meteorological data monitoring continue to accumulate, traditional methods for predicting cyclone tracks face numerous challenges regarding their prediction efficiency accuracy. Deep learning recently been proven be able learn both spatial temporal features from amount dataset extremely efficient accurate forecasting in complex structures. In this paper, we propose novel data-driven...
Abstract Seismic characterisation of deep carbonate reservoirs is considerable interest for reservoir distribution prediction, quality evaluation and structure delineation. However, it challenging to use the traditional methodology predict a deep-buried because highly nonlinear mapping relationship between heterogeneous features seismic responses. We propose machine-learning-based method (random forest) with physical constraints enhance prediction performance from multi-seismic attributes....
Several stratigraphic breaks and unconformities exist in the Mesoproterozoic successions northern margin of North China Block. Geologic characters spatial distributions five these unconformities, which have resulted from different geological processes, been studied. The unconformity beneath Dahongyu Formation is interpreted as a breakup unconformity, representing time transition continental rift to passive margin. Gaoyuzhuang Yangzhuang formations are considered be consequence regional...
Precise prediction of air pollutants can effectively reducre the occurrence heavy pollution incidents. With current surge massive data, deep learning appears to be a promising technique achieve dynamic pollutant concentration from both spatial and temporal dimensions. This paper presents Dev-LSTM, model building on deconvolution LSTM. The novelty Dev-LSTM lies in its capability fully extract feature correlation preventing excessive loss information caused by traditional convolution. At same...
Under global climate change, the frequency of typhoons and their strong wind, heavy rain, storm surge increase, seriously threatening life property human society. However, traditional tropical cyclone track prediction methods have difficulties in processing large amounts complex data terms efficiency accuracy. Recently, deep learning shown a potential capability to process efficiently accurately. In this paper, we propose novel data-driven approach based on auto-encoder (AE) gated recurrent...
To precisely forecast the operation status of transmission line during an ice storm and achieve early warning, a method based on adaptive relevance vector machine (ARVM) is proposed for fault probability prediction icing. According to basic theory RVM, this paper establishes forecasting model, which consists selection preprocessing data, initial parameter optimization, icing with optimization line. The quantum particle swarm algorithm, together K-fold Cross-validation applied optimize model...
Abstract Recently, with the accumulation of remote sensing data, traditional tropical cyclone (TC) track prediction methods (e.g., dynamic and statistical methods) have limitations in efficiency accuracy when dealing a large amount data. However, deep learning begin to show their advantages capture complex spatiotemporal features high-dimensional The task TC based on images can be formulated as sequence-to-sequence problem. Therefore, novel encoding-to-forecasting model convolutional long...
Human Activity Recognition (HAR) is nowadays widely used in intelligent perception and medical detection, the use of traditional neural networks deep learning methods has made great progress this field recent years. However, most existing assume that data independent identical distribution (I.I.D.) ignore variability different individual volunteers. In addition, models are characterized by many parameters high resources consumption, making it difficult to run real time on embedded devices....
Knowledge tracing is a significant research area in educational data mining, aiming to predict future performance based on students’ historical learning data. In the field of programming, several challenges are faced knowledge tracing, including inaccurate exercise representation and limited student information. These issues can lead biased models predictions states. To effectively address these issues, we propose novel programming model named GPPKT (Knowledge Graph Personalized Answer...
The nature of autonomy and openness E-commerce in online social (ECOS) networks poses a challenge to the security transactions as it is difficult ensure reliability trustworthiness parties on both ends. Transactions ECOS may, therefore, be conducted an unreliable environment vulnerable frauds. Trust management schemes, naturally, have come feasible solutions. With view making improvement existing trust mechanisms, we, this paper, propose factor-enrichment-based hybrid framework for...
Air pollution has become a critical issue in human’s life. Predicting the changing trends of air pollutants would be great help for public health and natural environments. Current methods focus on prediction accuracy retain forecasting time span within 12 hours. Shorter decreases practicability these perditions, even with higher accuracy. This study proposes an attention autoencoder (A&A) hybrid learning approach to obtain longer period while holding same high Since pollutant...
Covers advancements in spacecraft and tactical strategic missile systems, including subsystem design application, mission analysis, materials structures, developments space sciences, processing manufacturing, operations, applications of technologies to other fields.