With the development of urban rail transportation, more and more passengers choose metro to travel. Predicting the short-time passenger flow at stations is the basis of metro operation scheduling. In this paper, by analyzing the characteristics of passenger flow, we use K-means clustering algorithm to classify the weekday passenger flow into three categories according to the similarity of time-varying characteristics. Then, using the first four intervals of the prediction time and the historical contemporaneous passenger flow as input, a Long-Short Term Memory neural network (LSTM) and a least squares support vector machine (LSSVM) model are used to predict each class of passenger flow respectively. The model with the best prediction results under each cluster is selected for the combination, and it is finally found that the combined model has better prediction results than the individual model.
Short-Time Prediction of Subway Inbound Passenger Flow Based on K-means Clustering Combination Model
Lect. Notes Electrical Eng.
International Conference on Intelligent Transportation Engineering ; 2021 ; Beijing, China October 29, 2021 - October 31, 2021
2021 6th International Conference on Intelligent Transportation Engineering (ICITE 2021) ; Kapitel : 62 ; 694-703
01.06.2022
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Short-Time Prediction of Subway Inbound Passenger Flow Based on K-means Clustering Combination Model
British Library Conference Proceedings | 2022
|Short-Term Subway Inbound Passenger Flow Prediction Based on AFC Data and PSO-LSTM Optimized Model
Springer Verlag | 2022
|Short-Term Interval Prediction of Inbound Passenger Flow of Subway Station under Failure Events
DOAJ | 2024
|