Modeling public transportation multi-modal route choice using smart card big data

2021 ◽  
pp. 1-16
Author(s):  
Kyoungok Kim
Keyword(s):  
Big Data ◽  
Smart Card ◽  
Public Transportation ◽  
Route Choice ◽  
Modal Route

scholarly journals Exploring Equity in Public Transportation Planning Using Smart Card Data

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3039
Author(s):  
Kiarash Ghasemlou ◽  
Murat Ergun ◽  
Nima Dadashzadeh
Keyword(s):  
Smart Card ◽  
Public Transportation ◽  
Transportation Planning ◽  
Demand Characteristic ◽  
Monthly Data ◽  
Smart Card Data ◽  
Planning Methods ◽  
Public Transportation Planning ◽  
Daily Travel ◽  
A Share

Existing public transport (PT) planning methods use a trip-based approach, rather than a user-based approach, leading to neglecting equity. In other words, the impacts of regular users—i.e., users with higher trip rates—are overrepresented during analysis and modelling because of higher trip rates. In contrast to the existing studies, this study aims to show the actual demand characteristic and users’ share are different in daily and monthly data. For this, 1-month of smart card data from the Kocaeli, Turkey, was evaluated by means of specific variables, such as boarding frequency, cardholder types, and the number of users, as well as a breakdown of the number of days traveled by each user set. Results show that the proportion of regular PT users to total users in 1 workday, is higher than the monthly proportion of regular PT users to total users. Accordingly, users who have 16–21 days boarding frequency are 16% of the total users, and yet they have been overrepresented by 39% in the 1-day analysis. Moreover, users who have 1–6 days boarding frequency, have a share of 66% in the 1-month dataset and are underrepresented with a share of 22% in the 1-day analysis. Results indicated that the daily travel data without information related to the day-to-day frequency of trips and PT use caused incorrect estimation of real PT demand. Moreover, user-based analyzing approach over a month prepares the more realistic basis for transportation planning, design, and prioritization of transport investments.

A big data approach to understanding pedestrian route choice preferences: Evidence from San Francisco

2021 ◽  
Vol 25 ◽  
pp. 41-51
Author(s):  
Andres Sevtsuk ◽  
Rounaq Basu ◽  
Xiaojiang Li ◽  
Raul Kalvo
Keyword(s):  
Big Data ◽  
San Francisco ◽  
Route Choice

Estimating Express Train Preference of Urban Railway Passengers Based on Extreme Gradient Boosting (XGBoost) using Smart Card Data

2021 ◽  
pp. 036119812110133
Author(s):  
Eun Hak Lee ◽  
Kyoungtae Kim ◽  
Seung-Young Kho ◽  
Dong-Kyu Kim ◽  
Shin-Hyung Cho
Keyword(s):  
Travel Time ◽  
Smart Card ◽  
Public Transportation ◽  
Gradient Boosting ◽  
Log Data ◽  
Smart Card Data ◽  
Extreme Gradient Boosting ◽  
Express Train ◽  
Total Travel Time ◽  
The Individual

As the share of public transport increases, the express strategy of the urban railway is regarded as one of the solutions that allow the public transportation system to operate efficiently. It is crucial to express the urban railway’s express strategy to balance a passenger load between the two types of trains, that is, local and express trains. This research aims to estimate passengers’ preference between local and express trains based on a machine learning technique. Extreme gradient boosting (XGBoost) is trained to model express train preference using smart card and train log data. The passengers are categorized into four types according to their preference for the local and express trains. The smart card data and train log data of Metro Line 9 in Seoul are combined to generate the individual trip chain alternatives for each passenger. With the dataset, the train preference is estimated by XGBoost, and Shapley additive explanations (SHAP) is used to interpret and analyze the importance of individual features. The overall F1 score of the model is estimated to be 0.982. The results of feature analysis show that the total travel time of the local train feature is found to substantially affect the probability of express train preference with a 1.871 SHAP value. As a result, the probability of the express train preference increases with longer total travel time, shorter in-vehicle time, shorter waiting time, and few transfers on the passenger’s route. The model shows notable performance in accuracy and provided an understanding of the estimation results.

scholarly journals Understanding the integration of buses and metro systems using smart card data

2019 ◽  
Vol 2 ◽  
pp. 1-6
Author(s):  
Diao Lin ◽  
Ruoxin Zhu
Keyword(s):  
Smart Card ◽  
Public Transportation ◽  
Pearson Correlation ◽  
Metro Station ◽  
Smart Card Data ◽  
Pearson Correlation Test ◽  
Metro Systems ◽  
The City ◽  
Afternoon Peak

<p><strong>Abstract.</strong> Buses are considered as an important type of feeder model for urban metro systems. It is important to understand the integration of buses and metro systems for promoting public transportation. Using smart card data generated by automatic fare collection systems, we aim at exploring the characteristics of bus-and-metro integration. Taking Shanghai as a case study, we first introduced a rule-based method to extract metro trips and bus-and-metro trips from the raw smart card records. Based on the identified trips, we conducted three analyses to explore the characteristics of bus-and-metro integration. The first analysis showed that 46% users have at least two times of using buses to access metro stations during five weekdays. By combining the ridership of metro and bus-and-metro, the second analysis examined how the share of buses as the feeder mode change across space and time. Results showed that the share of buses as the feeder mode in morning peak hours is much larger than in afternoon peak hours, and metro stations away from the city center tend to have a larger share. Pearson correlation test was employed in the third analysis to explore the factors associated with the ratios of bus-and-metro trips. The metro station density and access metro duration are positively associated with the ratios. The number of bus lines around 100&amp;thinsp;m to 400&amp;thinsp;m of metro stations all showed a negative association, and the coefficient for 200&amp;thinsp;m is the largest. In addition, the temporal differences of the coefficients also suggest the importance of a factor might change with respect to different times. These results enhanced our understanding of the integration of buses and metro systems.</p>

scholarly journals Optimization of Evacuation and Walking-Home Routes from Osaka City After a Nankai Megathrust Earthquake Using Road Network Big Data

2021 ◽  
pp. 369-389
Author(s):  
Atsushi Takizawa ◽  
Yutaka Kawagishi
Keyword(s):  
Big Data ◽  
Public Transportation ◽  
Urban Areas ◽  
Road Network ◽  
Large Earthquake ◽  
The Road ◽  
Return Home ◽  
Flooded Area ◽  
Network Big Data ◽  
Surrounding Areas

AbstractWhen a disaster such as a large earthquake occurs, the resulting breakdown in public transportation leaves urban areas with many people who are struggling to return home. With people from various surrounding areas gathered in the city, unusually heavy congestion may occur on the roads when the commuters start to return home all at once on foot. In this chapter, it is assumed that a large earthquake caused by the Nankai Trough occurs at 2 p.m. on a weekday in Osaka City, where there are many commuters. We then assume a scenario in which evacuation from a resulting tsunami is carried out in the flooded area and people return home on foot in the other areas. At this time, evacuation and returning-home routes with the shortest possible travel times are obtained by solving the evacuation planning problem. However, the road network big data for Osaka City make such optimization difficult. Therefore, we propose methods for simplifying the large network while keeping those properties necessary for solving the optimization problem and then recovering the network. The obtained routes are then verified by large-scale pedestrian simulation, and the effect of the optimization is verified.

Creating Intelligent, Coordinated Transit

2005 ◽  
Vol 1927 (1) ◽  
pp. 138-148
Author(s):  
Judith M. Espinosa ◽  
Eric F. Holm ◽  
Mary E. White
Keyword(s):  
New Mexico ◽  
Rural Communities ◽  
Smart Card ◽  
Public Transportation ◽  
Rural Areas ◽  
The United States ◽  
Automatic Generation ◽  
Client Referral ◽  
Transportation Research ◽  
Contactless Smart Card

New Mexico is among the first states in the United States to develop, implement, and deploy contactless, smart card technology in a rural area. The Alliance for Transportation Research Institute, working with the New Mexico Department of Transportation's Public Transportation Programs Bureau, developed the Intelligent, Coordinated Transit (ICTransit) smart card technology and the Client, Referral, Ridership, and Financial Tracking (CRRAFT) software. The U.S. Department of Transportation's FTA–FHWA Joint Program Office provided federal funding for the project. The ICTransit smart card functions as a universal use electronic fare card, enabling passengers to transfer between transit providers to access jobs, education, and health care beyond their local rural communities. ICTransit's Global Positioning System receiver and Pocket PC capture the time and location that passengers board and exit the vehicle and the passenger miles traveled on the vehicle. The CRRAFT software system for express scheduling, automatic generation of monthly financial reports, and onboard tracking of ridership provides increased efficiency in rural areas. The ICTransit system with CRRAFT can overcome barriers to coordinated interagency transportation and provide increased access and mobility to all, but especially to those underserved by public transportation. ICTransit with CRRAFT can empower states to build coordinated transportation networks that provide safe and seamless movement of people and enhance the quality of life.

Sign in / Sign up

Export Citation Format

Share Document