Comparative analysis of deep-learning-based models for hourly bus passenger flow forecasting

Yu Zhang, Xiaodan Wang, Jingjing Xie () and Yun Bai
Additional contact information
Yu Zhang: Chongqing Jiaotong University
Xiaodan Wang: Chongqing Open University
Jingjing Xie: Chongqing Academy of Big Data
Yun Bai: Chongqing Technology and Business University

Transportation, 2024, vol. 51, issue 5, No 8, 1759-1784

Abstract: Abstract An efficient transportation system is conducive to maintaining traffic flow and safety. Passenger flow forecasting (PFF), an area of traffic forecasting, is a key part of the efficient transportation system. In recent years, deep-learning-based models have led to extensive research on the different conditions in this field. Hence, model determination is the most suitable for a specific application would be a key advantage. To address this issue, a comparative analysis of nine typical deep network approaches, including recurrent neural network (long short-term memory (LSTM) and gated recurrent unit (GRU)), bidirectional-based RNN (BiLSTM and BiGRU), convolutional neural network (CNN) (CNN1D and CNN2D), convolutional LSTM, and hybrid network (CNN1D-LSTM and CNN1D-GRU), for hourly PFF has been conducted. This comparison utilized two datasets with hourly records of bus lines from Guangzhou, China. The comparison results show that the bidirectional-based models were slightly better than other candidates in terms of the values of the root-mean-square error, determination coefficient, and Theil coefficient, and had a lower individual error distribution than the others, both numerically and proportionally. Furthermore, the bidirectional-based models were different from the other models in terms of the Friedman test (a special case is that the BiLSTM and LSTM had no significant difference for Line 10 application). Besides, the results from model structure aspect indicated that the bidirectional-based models achieved better performance with stable and reliable model structure (measurement index: posterior error distribution) and less computational complexity (measurement index: number of floating-point operations and parameters). It is concluded that the bidirectional-based deep learning models are the preferential choice for hourly PFF.

Keywords: Hourly bus passenger flow; Deep learning; Forecast; Comparative study; Model selection (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11116-023-10385-1 Abstract (text/html)
Access to full text is restricted to subscribers.

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:kap:transp:v:51:y:2024:i:5:d:10.1007_s11116-023-10385-1

Ordering information: This journal article can be ordered from
http://www.springer. ... ce/journal/11116/PS2

DOI: 10.1007/s11116-023-10385-1

Access Statistics for this article

Transportation is currently edited by Kay W. Axhausen

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