Real-time and accurate traffic flow prediction is one of the key technologies of Intelligent Transportation System (ITS). Traditional traffic flow prediction models cannot extract the spatio-temporal characteristics of road traffic flow well. To solve the problem, this paper proposes a short-term traffic flow prediction model based on Dynamic Time Warping (DTW) algorithm and Bi-directional Gated Recurrent Unit (BiGRU) network. The DWT algorithm is used to extract the spatial features of the traffic flow, and the extracted spatio-temporal feature matrix is input to BiGRU network for temporal features extraction. Experimental verification shows that the predicted root mean square error (RMSE) of the DTW-BiGRU model is 20.46% and 21.03% smaller than the Long Short-Term Memory (LSTM) network and Gated Recurrent Unit (GRU) network, respectively. The results show that the DTW-BiGRU model is an effective short-term traffic flow prediction model.
Short-Term Traffic Flow Prediction using DTW-BiGRU Model
16.10.2020
825278 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
SARO‐MB3‐BiGRU: A novel model for short‐term traffic flow forecasting in the context of big data
DOAJ | 2024
|SARO‐MB3‐BiGRU: A novel model for short‐term traffic flow forecasting in the context of big data
Wiley | 2024
|Short-Term Traffic Flow Prediction: Using LSTM
IEEE | 2020
|Event-Based Short-Term Traffic Flow Prediction Model
British Library Conference Proceedings | 1995
|Event-Based Short-Term Traffic Flow Prediction Model
Online Contents | 1995
|