Accurate forecasting of metro outbound passenger flow is of great significance to station operations and connected transportation systems. This paper constructs a multi-variable sequence LSTM outbound passenger flow forecasting model after analyzing the time series characteristics and the spatial-temporal correlation characteristics. And the dimensionality of spatial angles data is reduced based on t-SNE to improve the efficiency of the forecasting model. Finally, we take the Dongsishitiao station as an example to carry out an outbound passenger flow forecasting experiment, and compare the passenger flow forecasting accuracy under different characteristic inputs to show the effectiveness of the spatial-temporal correlation characteristics input. The forecasting error index MAPE of the experimental model reached 9.6%, indicating the availability of the model forecasting results, and the comparison of forecasting results with commonly used models proved the superiority of the forecasting model.
Metro Outbound Passenger Flow Forecasting Considering Spatial-Temporal Correlation Characteristics
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2021 October 21, 2021 - October 23, 2021
Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021 ; Kapitel : 55 ; 525-534
19.02.2022
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Metro Outbound Passenger Flow Forecasting Considering Spatial-Temporal Correlation Characteristics
British Library Conference Proceedings | 2022
|