Multi-step Time Series Forecasting of Bus Passenger Flow with Deep Learning Methods

Feng Jiao (), Lei Huang () and Zetian Gao ()
Additional contact information
Feng Jiao: Beijing Jiaotong University
Lei Huang: Beijing Jiaotong University
Zetian Gao: Warwick University

A chapter in LISS 2020, 2021, pp 539-553 from Springer

Abstract: Abstract Currently, bus is the major transportation option of the public, with nearly 9 million passengers travelling by bus every day in Beijing, with a result that the bus transportation system in Beijing has experienced huge challenges due to the large volumes of passenger flows. To solve the issues, it is necessary to predict the short-term passenger flow in an accurate way, which allows the schedule system of Beijing Public Transport Corporation to be more efficient, and then to provide better passenger services. In this study, the first step is to clean the bus and weather data and fuse them into a multi-dimensional data set. Then, the bus route 651 was chosen as the research objective, 5 min as time step in prediction. The research built one-step and multi-step prediction models by using LSTM and GRU. In the final step, we would evaluate the prediction performance between distinct prediction models with different hyperparameters. The result reveals that LSTM performs better in multi-step prediction model for route 651.

Keywords: Bus passenger flow; Multi-step time series forecasting; LSTM; GRU (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-33-4359-7_38

Ordering information: This item can be ordered from
http://www.springer.com/9789813343597

DOI: 10.1007/978-981-33-4359-7_38

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().