A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Traffic congestion has always been a problem that is difficult to solve in modern cities. Traffic trajectory prediction is one of the effective means to solve traffic congestion. The problem studied in this chapter is to establish a vehicle trajectory prediction model based on vehicle historical trajectory data. The research idea is to use machine learning algorithms and neural network algorithms to predict future trajectories after pre-processing the vehicle trajectory data. A decomposition algorithm is then used to improve the performance of the prediction model. The methods used include the ELM, BPNN, and EWT. The trajectory data of three different cars during the day is selected for prediction experiments. The experimental results show that the ELM model and the BPNN model have good prediction accuracy and practical useful value in the dataset selected in this chapter. The EWT method can effectively improve the prediction accuracy of individual models.
Traffic congestion has always been a problem that is difficult to solve in modern cities. Traffic trajectory prediction is one of the effective means to solve traffic congestion. The problem studied in this chapter is to establish a vehicle trajectory prediction model based on vehicle historical trajectory data. The research idea is to use machine learning algorithms and neural network algorithms to predict future trajectories after pre-processing the vehicle trajectory data. A decomposition algorithm is then used to improve the performance of the prediction model. The methods used include the ELM, BPNN, and EWT. The trajectory data of three different cars during the day is selected for prediction experiments. The experimental results show that the ELM model and the BPNN model have good prediction accuracy and practical useful value in the dataset selected in this chapter. The EWT method can effectively improve the prediction accuracy of individual models.
Characteristics and Analysis of Urban Traffic Flow in Smart Traffic Systems
Liu, Hui (author)
Smart Cities: Big Data Prediction Methods and Applications ; Chapter: 5 ; 125-158
2020-03-26
34 pages
Article/Chapter (Book)
Electronic Resource
English
Research on Traffic Flow Characteristics of Urban Expressway
| British Library Conference Proceedings | 2014