Document Type : Original Article
Authors
1
PhD Candidate in civil engineering, majoring in transportation planning, Faculty of Civil Engineering, Arts and Architecture, Tehran Science and Research
2
Department of Industrial Engineeeing, Islamic Azad University, Tehran, Iran
3
Graduated from Master's degree in Civil Engineering, Transportation Planning, South Tehran University
10.22034/road.2024.415667.2197
Abstract
Public transportation is of particular importance as a heavy system of passenger movement, hence the damage to this system is of great importance either financially or technically. In this research, using the data prepared from the bus company, passenger prediction is discussed. Forecasting is a critical component of transportation systems that can be used to adjust travel behaviors, reduce passenger traffic, and increase the service quality of transportation systems. In this research, the prediction of the number of passengers has been investigated using the neural network method. The prediction method based on the neural network model can be summarized as follows: After examining the data and performing a series of possible tests, the type of hyperbolic tangent function and the number of 6 neurons were determined. Between 7:30 and 8:30 at this time, because people and students go to their workplaces or studies, it has the largest number of passengers. The second peak in the graph, which is shorter, is between 5:30 and 6:30. The neural model with an error of 5% has a good prediction ability and for different stations, the prediction accuracy was 92%. The results show that the neural network is successful in predicting the number of passengers.
Keywords