Research on Sample Selection of Urban Rail Transit Passenger Flow Forecasting Based on SCBP Algorithm

This study analyses and compares several forecast methods of urban rail transit passenger flow, and indicates the necessity of forecasting short-term passenger flow. Support vector regression is a promising method for the forecast of passenger flow because it uses a risk function consisting of the empirical error and a regularized term which is based on the structural risk minimization principle. In this paper, the prediction model of urban rail transit passenger flow is constructed. Through the comparison with BP neural networks forecast methods, the experimental results show that applying this method in URT passenger flow forecasting is feasible and it provides a promising alternative to passenger flow prediction.

Download Full-text

Operation Organization at Urban Rail Transit Station under Large Passenger Flow

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.253-255.1995 ◽

2012 ◽

Vol 253-255 ◽

pp. 1995-2000

Author(s):

Qiao Mei Tang ◽

Li Ping Shen ◽

Xian Yong Tang

Keyword(s):

Transport Process ◽

Urban Rail Transit ◽

Rail Transit ◽

Common Condition ◽

Urban Transit ◽

Passenger Flow ◽

Operation Process ◽

Urban Rail ◽

Transit Station ◽

Transit Operation

large passenger flow is a common condition of urban transit operation, and the station bears the pressure of large passenger flow directly. This paper analyzes the reason for the appearance of large passenger flow and the characteristics of it, discusses the principles and methods that the station can apply under large passenger flow combined with the passenger’s transport process and the operation process.

Download Full-text

Forecast of Urban Rail Transit Passenger Flow in Holidays Based on Support Vector Machine Model

2020 5th International Conference on Electromechanical Control Technology and Transportation (ICECTT) ◽

10.1109/icectt50890.2020.00133 ◽

2020 ◽

Author(s):

Gaoxiang Zhou ◽

Jinjin Tang

Keyword(s):

Support Vector Machine ◽

Support Vector Machine Model ◽

Urban Rail Transit ◽

Support Vector ◽

Rail Transit ◽

Machine Model ◽

Passenger Flow ◽

Urban Rail

Download Full-text

Forecast Method of Short - term Passenger Flow on Urban Rail Transit

Proceedings of the 2017 VI International Conference on Network, Communication and Computing - ICNCC 2017 ◽

10.1145/3171592.3171633 ◽

2017 ◽

Cited By ~ 2

Author(s):

Ling Guo ◽

Yue Yuan

Keyword(s):

Urban Rail Transit ◽

Rail Transit ◽

Forecast Method ◽

Short Term ◽

Passenger Flow ◽

Urban Rail

Download Full-text

Research on Passenger Flow Forecast of Urban Rail Transit Based on SARIMA-RBF Combination Model

10.1109/icitbs53129.2021.00015 ◽

2021 ◽

Author(s):

Jiawei Liu ◽

Xinfeng Yang

Keyword(s):

Urban Rail Transit ◽

Rail Transit ◽

Combination Model ◽

Passenger Flow ◽

Urban Rail ◽

Flow Forecast

Download Full-text

Collaborative passenger flow control of urban rail transit network considering balanced distribution of passengers

Modern Physics Letters B ◽

10.1142/s0217984921504613 ◽

2021 ◽

pp. 2150461

Author(s):

Xiang Li ◽

Yan Bai ◽

Kaixiong Su

Keyword(s):

Flow Control ◽

Programming Model ◽

Flow Characteristics ◽

Service Level ◽

Urban Traffic ◽

Urban Rail Transit ◽

Control Measures ◽

Rail Transit ◽

Passenger Flow ◽

Urban Rail

The increase of urban traffic demands has directly affected some large cities that are now dealing with more serious urban rail transit congestion. In order to ensure the travel efficiency of passengers and improve the service level of urban rail transit, we proposed a multi-line collaborative passenger flow control model for urban rail transit networks. The model constructed here is based on passenger flow characteristics and congestion propagation rules. Considering the passenger demand constraints, as well as section transport and station capacity constraints, a linear programming model is established with the aim of minimizing total delayed time of passengers and minimizing control intensities at each station. The network constructed by Line 2, Line 6 and Line 8 of the Beijing metro is the study case used in this research to analyze control stations, control durations and control intensities. The results show that the number of delayed passengers is significantly reduced and the average flow control ratio is relatively balanced at each station, which indicates that the model can effectively relieve congestion and provide quantitative references for urban rail transit operators to come up with new and more effective passenger flow control measures.

Download Full-text