Urban taxi demand prediction plays an important role in reducing the taxi empty driving rate and alleviating road traffic congestion. However, due to the complex structure of urban road network, taxi flow is difficult to be accurately predicted. In order to capture the spatial features of taxi data and accurately predict the future demand changes of taxi, a new hybrid model — LSGCN model is proposed in this paper. This model combines graph convolutional neural network (GCN) and long short-term memory network (LSTM) to achieve simultaneous acquisition of spatial-temporal correlation. Finally, the taxi demand prediction experiment is conducted based on the real order data set of Haikou taxi-hailing platform to verify the prediction performance of the model proposed in this paper.
Urban Taxi Demand Forecast Based on Graph Convolutional Network
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 : 54 ; 515-524
19.02.2022
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Urban Taxi Demand Forecast Based on Graph Convolutional Network
TIBKAT | 2022
|Urban Taxi Demand Forecast Based on Graph Convolutional Network
British Library Conference Proceedings | 2022
|Predictions of Taxi Demand Based on Neural Network Algorithms
Springer Verlag | 2021
|