2020 · 19 citations · 9 references
ComputingCivil EngineeringComputer ScienceForecastingMachine LearningTransportation EngineeringDeep LearningNeural NetworksTime Series ForecastingTime Series PredictionTraffic EngineeringTraffic Flow AnalysisDeep Learning For ForecastingDeep Learning For Time Series ForecastingDeep Learning-based ForecastingGated Recurrent Unit NetworksShort-term Traffic PredictionTraffic Flow ForecastingTraffic Flow PredictionTraffic Prediction
To solve the problem of low prediction accuracy and poor robustness due to the short-term prediction only adopts the time series of current link traffic flow and fails to consider the spatial relationship in traffic flow data, this paper proposes a hybrid deep learning method considering the spatialtemporal correlation of traffic flow called AutoEncoder Gated Recurrent Unit (AE-GRU). The model fully considers the impact of upstream and downstream links traffic flow of the current link, can effectively use the topological spatial relationship of the road network, reduce the computational complexity, and can avoid the problem of unstable prediction results caused by the introduction of low-correlation road data. The results show that this method has higher prediction accuracy than the traditional prediction model and it is an effective traffic flow prediction model.
9
LSTM network: a deep learning approach for short‐term traffic forecast
Zheng Zhao, Weihai Chen, Xingming Wu et al. · IET Intelligent Transport Systems · 2017 · 1.8K citations
Computing, Data Science, Forecasting +16
Using LSTM and GRU neural network methods for traffic flow prediction
Rui Fu, Zuo‐Feng Zhang, Li Li · 2016 · 1.4K citations