Hyper passenger volume leads to crowdedness, trampling and falling to rail in subway station, optimum passenger organization will lessen emergency. The short-term passenger flow prediction is the basis of optimum passenger organization. To improve the prediction accuracy of passenger flow arriving at subway station, a PSO_LSTM network is built in the paper. First, the Automatic Fare Collection (AFC) transaction data of Shanghai Metro are processed and analyzed. Second, based on the particle swarm optimization (PSO), passenger prediction model is constructed. Third, to verify the model, the historical passenger flow data of Shanghai Railway Station of Shanghai Metro Line 1 are used to predict passenger arriving at the station in a certain time. The results show that mean absolute percentage error (MAPE) of passenger arriving prediction in test set with the PSO_LSTM network reduced by 3.15% and 3.59% respectively compared with that of original LSTM network and GRU network.
Short-term Passenger Flow Prediction of Subway Station Based on PSO_LSTM
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 ; Chapter : 39 ; 355-363
2022-02-19
9 pages
Article/Chapter (Book)
Electronic Resource
English
Short-term Passenger Flow Prediction of Subway Station Based on PSO_LSTM
British Library Conference Proceedings | 2022
|Short-term subway station entering passenger flow volume prediction method
European Patent Office | 2023
|Passenger subway at Padua Central station
Engineering Index Backfile | 1932
|