Published multiple journal articles covering topics such as time series forecasting, disease prediction, and energy forecasting. Some of the papers include:
- Explainable time-varying directional representations for photovoltaic power generation forecasting
- Sparse dynamic graph learning for district heat load forecasting
- Carbon futures price forecasting based on feature selection
- A new feature selection method based on importance measures for crude oil return forecasting
- Temporal collaborative attention for wind power forecasting
- Enhanced transfer learning with data augmentation
- Crosstalk between computational medicine and neuroscience in healthcare
- Oriented Transformer for Infectious Disease Case Prediction
- Explainable district heat load forecasting with active deep learning
- A multivariate time series graph neural network for district heat load forecasting
- A low-complexity evolutionary algorithm for wind farm layout optimization
- Laplacian Lp norm least squares twin support vector machine
- HFMD Cases Prediction using Transfer One-step-ahead Learning
- Dual-grained directional representation for infectious disease case prediction
- A Multi-view Multi-omics Model for Cancer Drug Response Prediction
- A multi-view time series model for share turnover prediction
- COVID-19 cases prediction in multiple areas via shapelet learning
- Parallel XPath query based on cost optimization
- Protein Secondary Structure Prediction With a Reductive Deep Learning Method
- Dual-grained representation for hand, foot, and mouth disease
Research Experience
Held a position at the College of Computer Engineering, Jimei University from July 2016 to present; project founder and lead programmer of the popular open-source time series forecasting library pyFAST.
Education
No specific educational background information provided.
Background
Research interests include: AI in health/healthcare (developing predictive models for infectious diseases and personalized medicine), time series forecasting (creating advanced models for multivariate, graph-based, and sparse time series forecasting), and recommendation systems (enhancing user experience through personalized recommendations). Affiliated with the College of Computer Engineering, Jimei University.
Miscellany
Contributions to pyFAST are welcome! Please submit issues or pull requests on GitHub.