Developing a Short term traffic prediction (STTP) model to determine the traffic patterns is one of the most challenging aspect in the present day. As there is a rapid increase in the amount of vehicles and details of traffic leading to congestions. Congestion on roads can be controlled with the arrival of accurate forecast of the traffic flow, therefore, a study to predict short-term traffic on roads achieves momentum in the present days. Fb-Prophet models which are developed by Facebook, were used as a technique to forecast the trends in time series data. In this paper, STTP models were developed to predict traffic volume using Fb-PROPHET and Neural-PROPHET. Classified traffic volume count for seven days- 24 hours on National Highway 744 in Tamil Nadu was collected using pneumatic method. The developed models goodness-of-fit was checked in terms of Mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) tests. The proposed work benefits traffic management agencies for proper planning and assigning of routes to avoid congestion.
Short - Term Traffic Prediction Using Fb-PROPHET and Neural-PROPHET
11.02.2022
435003 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Traffic volume prediction method of Prophet-DeepAR model
Europäisches Patentamt | 2023
|Prophet-DCRNN traffic flow prediction method fusing multi-modal information
Europäisches Patentamt | 2021
|Real-Time Traffic Congestion Forecasting Using Prophet and Spark Streaming
Springer Verlag | 2022
|