In recent years, with the continuous improvement of people's quality of life, the purchase of motor vehicles has become more and more. Accompanied by serious traffic congestion, people's travel caused great inconvenience. Short-term traffic flow prediction can help the traffic department to timely understand the future congestion situation of a certain section, so as to respond in advance. At the same time, it also has certain significance for people's travel, so that people can avoid the congested section in time. In view of the problem that traditional forecasting methods only consider the temporal characteristics of traffic flow, ignoring its spatial characteristics, a short-time traffic flow forecasting model combining convolutional neural network (CNN) and long short-term memory network (LSTM) was proposed. The spatial correlation of traffic flow is mined through CNN, the temporal characteristics of traffic flow are mined through LSTM model, and the extracted temporal and spatial characteristics are integrated to achieve short-term traffic prediction. The experimental results show that the error of CNN-LSTM traffic flow prediction model is obviously smaller than other models.
Expressway Short-Term Traffic Flow Prediction Based on CNN-LSTM
Lect. Notes Electrical Eng.
International Conference on Genetic and Evolutionary Computing ; 2023 ; Kaohsiung, Taiwan October 06, 2023 - October 08, 2023
2024-01-25
8 pages
Article/Chapter (Book)
Electronic Resource
English
Short-term traffic flow prediction method based on improved LSTM
European Patent Office | 2021
|Short-term traffic flow prediction method based on Conv1D-LSTM model
European Patent Office | 2023
|Short-term traffic flow prediction method based on CASSA-LSTM algorithm
European Patent Office | 2022
|