Search

Accurately understanding the travel demand of urban rail transit (URT) systems is crucial for effective operational management. Despite the recognition that the diversity in human activity patterns results in different travel demands, few studies have thoroughly investigated the heterogeneity among passengers and its impact on URT ridership. This study utilizes smart card data collected from the Beijing Subway to categorize passengers into four groups: tourist passengers, flexible commuters, regular commuters, and life‐oriented passengers, based on their spatiotemporal travel patterns. Furthermore, a Multiscale Geographically Weighted Regression (MGWR) model is employed to examine the relationship between station‐level ridership of URT and its determinants, including the built environment and station properties, for each passenger group. The results indicate that the influence of these determinants on station‐level ridership varies across passenger groups and spatial scales. For instance, regular commuters exhibit lower sensitivity to accessibility on workdays, whereas those unfamiliar with the URT network are more concerned about the bus accessibility in pedestrian‐ or bicycle‐unfriendly areas. Notably, for tourist and life‐oriented passengers, the stations significantly affected by population density are concentrated in areas with a higher proportion of elderly individuals. Conversely, for flexible and regular commuters, these stations are predominantly situated in areas associated with internet technology and scientific research. These findings are valuable for policymakers in designing strategies tailored to different passenger groups to balance trip demand and capacity, thereby improving URT services and promoting a sustainable urban environment. [ABSTRACT FROM AUTHOR]

Objective When mining travel characteristics from urban rail transit travel trajectory data, passenger travel activity patterns are found closely related to the stations near their residence and workplace. This is reflected in their travel trajectories by fixed boarding/alighting routes and concentrated entry/exit stations. Meanwhile, passenger travel trajectories associated with residence and workplace exhibit certain fluctuations, and the travel data strongly related to workplace-residence often differ significantly from other travel data. To accurately extract passenger travel trajectory characteristics, it is essential to clarify the residence-workplace relationship within urban rail transit passenger travel data. Method A mechanism for mining travel characteristics and classifying passengers based on residence-workplace relationship is proposed. The preliminary workplace-residence judgments are formed by identifying the hotspots of passenger trajectory activities related to residence, workplace and social activity locations. Then, the spatio-temporal patterns strongly associated with workplace-residence are explored. A K-means clustering algorithm extracted on the basis of passenger travel trajectory characteristic values is used to cluster passengers according to their residence-workplace judgment, resulting in a passenger classification method that precisely matches the passenger travel characteristics. Result & Conclusion Simulation validation results indicate that passengers with clearly defined residence-workplace relationship exhibit four distinct travel patterns of two-point, two-point-two-line, three-point, and multi-point. These travel pattern classification results make up a crucial technical foundation for constructing detailed passenger profiles and developing intelligent security check strategies.

Copyright of Urban Mass Transit is the property of Urban Mass Transit Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To alleviate peak-hour congestion in urban rail transit, this study proposes a new off-peak fare discount strategy to incentivize passengers to shift their departure time from peak to off-peak hours. Firstly, a questionnaire survey of Shanghai metro passengers is conducted to analyze their willingness to change departure time under different fare strategies. Secondly, based on the survey results, a time-differentiated fare discount model is constructed, considering both the company's revenue and passengers' travel benefits, and with the optimization objective of achieving balanced peak-hour and off-peak-hour train loads throughout the day. Subsequently, a genetic algorithm with nested fmincon functions is designed and combined with the actual data of Shanghai rail transit line 9 for arithmetic analysis. Finally, the effectiveness of the model is validated using the survey data. The research results show that the off-peak fare discount strategy can incentivize 6.88% of passengers traveling in the morning peak and 6.66% of passengers traveling in the evening peak to shift to off-peak travel. This research provides theoretical support and decision-making guidance for implementing time-differentiated pricing in urban rail transit systems. [ABSTRACT FROM AUTHOR]

Abstract To alleviate peak-hour congestion in urban rail transit, this study proposes a new off-peak fare discount strategy to incentivize passengers to shift their departure time from peak to off-peak hours. Firstly, a questionnaire survey of Shanghai metro passengers is conducted to analyze their willingness to change departure time under different fare strategies. Secondly, based on the survey results, a time-differentiated fare discount model is constructed, considering both the company’s revenue and passengers’ travel benefits, and with the optimization objective of achieving balanced peak-hour and off-peak-hour train loads throughout the day. Subsequently, a genetic algorithm with nested fmincon functions is designed and combined with the actual data of Shanghai rail transit line 9 for arithmetic analysis. Finally, the effectiveness of the model is validated using the survey data. The research results show that the off-peak fare discount strategy can incentivize 6.88% of passengers traveling in the morning peak and 6.66% of passengers traveling in the evening peak to shift to off-peak travel. This research provides theoretical support and decision-making guidance for implementing time-differentiated pricing in urban rail transit systems.

Accurate short-term passenger flow prediction plays an important role in transit planning and operation. Existing research is mostly based on a joint modelling approach in which transit demand is predicted in an aggregated manner taking the overall passenger flow as input. A critical problem for the joint modelling approach is that the complexity of passenger flow composition and the distinct behavioural response to influential factors are missing out. To address this challenge, this paper proposes a separate modelling approach for passenger flow prediction based on behavioural patterns. To this end, we develop a novel hybrid decision tree (HDT) model coupled with a decision tree model and time series model. The upper layer is a decision tree model, in which the dataset is divided according to passenger types and influential factors, while the lower layer is the time series model achieved by the recurrent neural network. Particularly, this research first undertakes passenger classification using smartcard data through cluster analysis, from which the correlation between the classified passenger flow and influential factors is obtained. The proposed method is tested in a real-life bus route in Guangzhou, China. We also investigate the impact of passenger classification schemes and the minimum amount of data contained by leaf nodes on the performance of the HDT model. Based on this, we recommend the best classification scheme and the optimal value of the minimum amount of data contained by leaf nodes. Comparisons show that our method outperforms other traditional methods in terms of both prediction accuracy and stability. In addition, our method could also provide the prediction of passenger flow composition, which provides more references for customized bus service design. • A novel hybrid decision trees combining the advantages of machine learning model and time series method. • Our method can handle big data by capturing correlations between the external and internal factors. • As opposed to joint modelling, our method is able to predict passenger flow composition. • The prediction outcome is quite outstanding with MAPE of as low as 5%. [ABSTRACT FROM AUTHOR]