To assist intelligent traffic management, traffic flow prediction, which plays a crucial role in intelligent transportation system, involves forecasting future traffic flow based on road characteristics and historical traffic data. Due to the inherent complexity of traffic systems, achieving high accuracy in long-term traffic flow prediction poses significant challenges. Therefore, we propose a novel neural network model, which is able to capture both temporal and spatial dependencies in the traffic flow data using the combination of GCN layer and LSTM layer. Experiments have demonstrated that our model is effective and accurate when used to predict the short-term traffic flow.
A Spatial-Temporal Neural Network for Short-Term Traffic Flow Prediction
20.12.2024
530402 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Short-Term Traffic Prediction considering Spatial-Temporal Characteristics of Freeway Flow
DOAJ | 2021
|