A combined model of random forest and multilayer perceptron to forecast expressway traffic flow

The real-time and accurate forecasting of expressway traffic is an important prerequisite for the development of reasonable traffic management control scheme, the reasonable choice of travel route and the effective prevention of traffic congestion. The current traffic data are mostly collected using a variety of monitoring equipment, but the data can only reflect a certain traffic flow and the cost is too high. This paper proposes a combined algorithm based on machine learning by using the expressway toll data to predict the traffic flow. The experimental results show that the combined algorithm proposed in this paper improves the accuracy of traffic flow forecast.