A5090943298- Energy Load and Power Forecasting
- Traffic Prediction and Management Techniques
- Air Quality Monitoring and Forecasting
- Stock Market Forecasting Methods
- Time Series Analysis and Forecasting
- Solar Radiation and Photovoltaics
- Air Quality and Health Impacts
- Vehicle emissions and performance
- Machine Fault Diagnosis Techniques
- Traffic control and management
- Wind Energy Research and Development
- Railway Engineering and Dynamics
- Optical Network Technologies
- E-commerce and Technology Innovations
- Transportation Planning and Optimization
- Gear and Bearing Dynamics Analysis
- Forecasting Techniques and Applications
- Electric Power System Optimization
- Advanced Photonic Communication Systems
- Grey System Theory Applications
- Methane Hydrates and Related Phenomena
- Advanced Computing and Algorithms
- Railway Systems and Energy Efficiency
- Reproductive Health and Contraception
- Sentiment Analysis and Opinion Mining
Institute of Computing Technology
2022-2024
University of Chinese Academy of Sciences
2022-2024
Central South University
2020-2024
Chinese Academy of Sciences
2022-2024
Soochow University
2022-2024
First Affiliated Hospital of Soochow University
2022-2024
Ministry of Transport
2022
Hainan Agricultural School
2019
Kaiping Central Hospital
2009
Multivariate time series long-term prediction, which aims to predict the change of data in a long time, can provide references for decision-making. Although transformer-based models have made progress this field, they usually do not make full use three features multivariate series: global information, local and variables correlation. To effectively mine above establish high-precision prediction model, we propose double sampling transformer (DSformer), consists (DS) block temporal variable...
This paper reviews the current research status of rolling bearing fault diagnosis technology for railway vehicles. Several domains are covered, including vibration diagnosis, acoustic signal and temperature prediction methods on train test principles related research. The application scenarios, system accuracies, model structures various studies in literature also compared analyzed. Furthermore, main technical points to be improved analysis possible directions proposed, which provide new...
Multivariate time series forecasting (MTSF) is crucial for decision-making to precisely forecast the future values/trends, based on complex relationships identified from historical observations of multiple sequences. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have gradually become theme MTSF model as their powerful capability in mining spatial-temporal dependencies, but almost them heavily rely assumption data integrity. In reality, due factors such collector failures and...
The bearing temperature forecasting provide can early detection of the gearbox operating status wind turbines. To achieve high precision and reliable performance in forecasting, a novel hybrid model is proposed paper, which composed three phases. Firstly, variational mode decomposition (VMD) method employed to decompose raw data into several sub-series with different frequencies. Then, SAE-GMDH utilized as predictor subseries. stacked autoencoder (SAE) for low-latitude features data, while...
In recent years, with the rise of Internet, e-commerce has become an important field commodity sales. However, is affected by many factors, and wrong judgment supply marketing relationships will bring huge losses to operators. Therefore, it great significance establish a model that can effectively achieve high precision sales prediction for ensuring sustainable development enterprises. this paper, we propose forecasting considers features aspects correlation. first layer model, temporal...
The axle temperature is an index factor of the train operating conditions. forecasting technology very meaningful in condition monitoring and fault diagnosis to realize early warning prevent accidents. In this study, a data-driven hybrid approach consisting three steps utilized for prediction locomotive temperatures. stage I, Complementary empirical mode decomposition (CEEMD) method applied preprocessing datasets. II, Bi-directional long short-term memory (BILSTM) will be conducted...