Short Term Traffic Flow Prediction Based on LSTM

摘要

Traffic flow prediction is important in modern traffic control and induction. Short-term traffic flow prediction plays an important role in urban traffic navigation planning and traffic optimization control. Due to the advantage in processing of time series data, LSTM is very suitable for predicting short-term traffic flow. This paper builds a deep learning model based on LSTM to predict the traffic flow volume. In experiment, we build models with different hyper parameters, compared and analyzed the performance of different models.