Community Traffic State Prediction Based on CPM and LSTM

  • Yuange Ma


Accurate prediction of road traffic status can effectively alleviate the increasingly serious urban traffic congestion and promote the development of intelligent transportation system (ITS). Different from other studies that predicted only one road area, this paper predicted a group of road areas with traffic similarity (a community), which made it easier and more accurate to find the key features. Based on CPM algorithm, LSTM model and FCM algorithm, this paper predicts the overall speed and flow of the community and divides it into some traffic states, effectively captures the long and short time characteristics of time series, solves the limitations of traditional road prediction research and improves the prediction accuracy. In order to verify the accuracy and effectiveness of the model, we selected taxi data in New York City for model training and testing. The results show that the model can predict the speed and flow of community 1and divide it into some traffic states well, with good prediction accuracy, and has great application value in the road traffic state prediction.

How to Cite
Yuange Ma. (1). Community Traffic State Prediction Based on CPM and LSTM. Forest Chemicals Review, 1623-1647. Retrieved from