Traffic flow parameter forecasting is the basis for the traffic control and optimization, which plays a very significant role in actual traffic scenarios. When taking the daily traffic flow parameters as the research object, the daily traffic flow patterns on holidays are often quite different from that on non-holidays. Therefore, it is important to capture the correlation between traffic flow parameters and holidays. However, in recent years, most research on daily traffic flow forecasting is only based on simple deep learning methods, and do not consider the relationship between traffic flow parameters and holidays. Meanwhile, the daily traffic flow patterns during holidays and non-holidays are not necessarily different. In this paper, we put forward a novel method for daily traffic flow parameter forecasting, taking the influence of holidays into account. Basing on the deep learning method composed of convolutional neural network and long short-term memory (CNN-LSTM), we combine the traffic flow pattern with various external factors. While considering the influence of holidays, we incorporate the “holiday special or not” feature extracted from the traffic flow parameter data itself to realize the daily forecasting. The forecasting method put forward shows good accuracy on case-testing.
A Method for Daily Traffic Flow Parameter Forecasting Combining the Impact of Holidays
Lect. Notes Electrical Eng.
International Conference on Intelligent Transportation Engineering ; 2021 ; Beijing, China October 29, 2021 - October 31, 2021
2021 6th International Conference on Intelligent Transportation Engineering (ICITE 2021) ; Chapter : 63 ; 704-715
2022-06-01
12 pages
Article/Chapter (Book)
Electronic Resource
English
A Method for Daily Traffic Flow Parameter Forecasting Combining the Impact of Holidays
British Library Conference Proceedings | 2022
|Investigating Effect of Holidays on Daily Traffic Counts
Transportation Research Record | 2007
|Investigating Effect of Holidays on Daily Traffic Counts: Time Series Approach
Online Contents | 2007
|Traffic Volume Forecasting Model of Freeway Toll Stations During Holidays – An SVM Model
DOAJ | 2022
|