A combined method for short-term traffic flow prediction based on recurrent neural network

Lu, Saiqun and Zhang, Qiyan and Chen, Guangsen and Seng, Dewen (2020) A combined method for short-term traffic flow prediction based on recurrent neural network. A combined method for short-term traffic flow prediction based on recurrent neural network, 61 (1). pp. 87-94. ISSN 1110-0168

Text A-combined-method-for-short-term-traffic-flow-predict_2021_Alexandria-Engine.pdf Restricted to Repository staff only Download (1MB)

Abstract

The accurate prediction of real-time traffic flow is indispensable to intelligent transport systems. However, the short-term prediction remains a thorny issue, due to the complexity and stochasticity of the traffic flow. To solve the problem, a combined prediction method for shortterm traffic flow based on the autoregressive integral moving average (ARIMA) model and long short-term memory (LSTM) neural network was proposed. The method could make short-term pre�dictions of future traffic flow based on historical traffic data. Firstly, the linear regression feature of the traffic data was captured using the rolling regression ARIMA model; then, backpropagation was used to train the LSTM network to capture the non-linear features of the traffic data; and finally, based on the dynamic weighting of sliding window combined the predicted effects of these two techniques. Using MAE, MSE RMSE and MAPE as evaluation indicators, the prediction per�formance of the combined method proposed was evaluated on three real highway data sets, and compared with the three comparative baselines of ARIMA and LSTM two single methods and equal weight combination. The experimental results show that the dynamic weighted combination model proposed has better prediction effect, which proves the versatility of this method

Actions (login required)

View Item