Peak hour public transit passenger flow prediction based on moving average method and Markov model

Zian Wang

doi:10.1117/12.2619886

22 December 2021 Peak hour public transit passenger flow prediction based on moving average method and Markov model

Zian Wang

Proceedings Volume 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021); 1205817 (2021) https://doi.org/10.1117/12.2619886
Event: 5th International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 2021, Chongqing, China

Abstract

In recent years, the urban public transit system has been faced with problems such as low operating efficiency and low passenger load percentage, and thus the reliability and attractiveness of transit lines have gradually decreased. The primary task to solve the above problems is to obtain accurate future data of passenger flow. However, due to the diversity of residents' travel choices, the fluctuation of flow during peak hours is more obvious and thus prediction is more difficult. Based on existing passenger flow forecasting models, this paper starts from two perspectives of passenger flow volatility and prediction status. Based on moving average method, Markov model is used to modify the prediction results. An example is given by using historical data of Bus Line 16 in Beijing, which proves the performance of the mixed model is better than traditional models at peak hours. The results can provide basic data support for bus operation companies to formulate high-quality timetabling and scheduling.

Citation Download Citation

Zian Wang "Peak hour public transit passenger flow prediction based on moving average method and Markov model", Proc. SPIE 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 1205817 (22 December 2021); https://doi.org/10.1117/12.2619886

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available