一种城市轨道交通短时客流智能预测方法
By combining the probabilistic parallelogram algorithm and the R-StackCat model with urban rail transit line structure, station surrounding information, and POI data, the problem of insufficient accuracy in short-term passenger flow prediction for urban rail transit was solved, achieving higher accuracy and interpretability in passenger flow prediction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING JIAOTONG UNIV
- Filing Date
- 2023-10-13
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies for short-term passenger flow forecasting in urban rail transit struggle to effectively combine individual travel behavior with macro-travel patterns, resulting in insufficient forecast accuracy, particularly in feature selection and model interpretability.
The probabilistic parallelogram algorithm is used to extract passenger travel behavior features. Combined with urban rail transit line structure, station surrounding information and POI data, an R-StackCat model is constructed. The Stacking strategy is used to integrate RF, XGBoost and CatBoost algorithms. Interpretable artificial intelligence methods are used to analyze feature importance and improve prediction accuracy.
It improves the accuracy and interpretability of short-term passenger flow forecasting for urban rail transit, enabling accurate prediction of passenger flow in different scenarios, especially during morning and evening peak hours and off-peak hours, thus enhancing the model's predictive performance and transparency.
Smart Images
Figure CN117455038B_ABST