In order to overcome the dynamic interference problem of internal related factors in the prediction process of road traffic flow, a deep learning road traffic flow prediction model based on multi-dimensional influence factors is proposed. On the basis of analyzing the characteristics of traffic flow time and space, this model analyzes the traffic flow characteristics of urban traffic system under the relevant factors such as working day, holidays and weather, quantifies the relevant influence factors, and constructs multi-dimensional state vectors combined with road traffic flow. Simulations show that MAE of the MDLSTM prediction model based on multi-dimensional data is reduced by 5.528 and 3.018, and RMSE is reduced by 6.827 and 2.154, respectively, compared with the traditional BP neural network and LSTM models.
Short-Term Road Traffic Flow Prediction Based on Multi-Dimensional Data
2021-03-01
2576994 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
The Urban Road Short-Term Traffic Flow Prediction Research
Trans Tech Publications | 2013
|Multi-Section Short-Term Traffic Flow Prediction Based on Multi-Dimensional Time Series
British Library Conference Proceedings | 2009
|Short-term traffic flow prediction of road network based on deep learning
IET | 2020
|Short‐term traffic flow prediction of road network based on deep learning
Wiley | 2020
|