•A multiscale radial basis function (MSRBF) network is proposed.MSRBF network can predict irregular subway passenger flow under special events.•MSRBF network can pinpoint vulnerable subway stations ...for crowd control measures.•MSRBF network significantly outperforms traditional prediction methods.
Reliable and accurate short-term subway passenger flow prediction is important for passengers, transit operators, and public agencies. Traditional studies focus on regular demand forecasting and have inherent disadvantages in predicting passenger flows under special events scenarios. These special events may have a disruptive impact on public transportation systems, and should thus be given more attention for proactive management and timely information dissemination. This study proposes a novel multiscale radial basis function (MSRBF) network for forecasting the irregular fluctuation of subway passenger flows. This model is simplified using a matching pursuit orthogonal least squares algorithm through the selection of significant model terms to produce a parsimonious MSRBF model. Combined with transit smart card data, this approach not only exhibits superior predictive performance over prevailing computational intelligence methods for non-regular demand forecasting at least 30min prior, but also leverages network knowledge to enhance prediction capability and pinpoint vulnerable subway stations for crowd control measures. Three empirical studies with special events in Beijing demonstrate that the proposed algorithm can effectively predict the emergence of passenger flow bursts.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
•Methods are proposed for prediction of individual trip making and trip attributes.•A Bayesian n-gram model is developed for trip attribute prediction.•The methods are tested using transit smart card ...data of 10,000 users in London.•Prediction accuracies vary by attribute with time harder to predict than location.•Significant variations are found across users in terms of prediction performance.
For intelligent urban transportation systems, the ability to predict individual mobility is crucial for personalized traveler information, targeted demand management, and dynamic system operations. Whereas existing methods focus on predicting the next location of users, little is known regarding the prediction of the next trip. The paper develops a methodology for predicting daily individual mobility represented as a chain of trips (including the null set, no travel), each defined as a combination of the trip start time t, origin o, and destination d. To predict individual mobility, we first predict whether the user will travel (trip making prediction), and then, if so, predict the attributes of the next trip (t,o,d) (trip attribute prediction). Each of the two problems can be further decomposed into two subproblems based on the triggering event. For trip attribute prediction, we propose a new model, based on the Bayesian n-gram model used in language modeling, to estimate the probability distribution of the next trip conditional on the previous one. The proposed methodology is tested using the pseudonymized transit smart card records from more than 10,000 users in London, U.K. over two years. Based on regularized logistic regression, our trip making prediction models achieve median accuracy levels of over 80%. The prediction accuracy for trip attributes varies by the attribute considered—around 40% for t, 70–80% for o and 60–70% for d. Relatively, the first trip of the day is more difficult to predict. Significant variations are found across individuals in terms of the model performance, implying diverse travel behavior patterns.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
•Investigates bus passengers’ habitual route choice behaviours using smart card data.•Introduces the concept of stickiness to describe a tendency of sticking to one route.•Proposes Stickiness Index ...to quantify bus passengers’ route stickiness.•Performs both longitudinal and cross-sectional analyses at a metropolitan-wide scale.
This paper explores how we can use smart card data for bus passengers to reveal individual and aggregate travel behaviour. More specifically, we measure the extent to which both individual and bus routes exhibit habitual behaviour. To achieve this, we introduce a metric called Stickiness Index to quantify the range of preferences of users that always select to travel on the same route (high stickiness) to those with a more varied patterns of route selection (low stickiness). Adopting a visual analytic and modelling approach using a suite of regression models we find evidence to suggest that stickiness varies across the metropolitan area and over a 24-h period wherein higher stickiness is associated with high frequency users where there is substantial variability of route travel times across all alternatives. We argue that our findings are important in their capacity to contribute to a new evidence base with the potential to inform the (re)-design and scheduling of a public transit systems through unveiling the complexities of transit behaviour.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
•A robust trip chaining algorithm is proposed to improve inference of trips in AFC data.•The method infers the trajectory of the AFC tag by finding the most likely trajectory.•An extension of the ...algorithm is developed for inferring trips with pay-exit tags.•The proposed method shows more inference compared with a baseline algorithm.
Development of an origin-destination demand matrix is crucial for transit planning. The development process is facilitated by automated transit smart card data, making it possible to mine boarding and alighting patterns on an individual basis. This research proposes a novel trip chaining method which uses Automatic Fare Collection (AFC) and General Transit Feed Specification (GTFS) data to infer the most likely trajectory of individual transit passengers. The method relaxes the assumptions on various parameters used in the existing trip chaining algorithms such as transfer walking distance threshold, buffer distance for selecting the boarding location, time window for selecting the vehicle trip, etc. The method also resolves issues related to errors in GPS location recorded by AFC systems or selection of incorrect sub-route from GTFS data. The proposed trip chaining method generates a set of candidate trajectories for each AFC tag to reach the next tag, calculates the probability of each trajectory, and selects the most likely trajectory to infer the boarding and alighting stops. The method is applied to transit data from the Twin Cities, MN, which has an open transit system where passengers tap smart cards only once when boarding (or when alighting on pay-exit buses). Based on the consecutive tags of the passenger, the proposed algorithm is also modified for pay-exit cases. The method is compared to previous methods developed by the researchers and shows improvement in the number of inferred cases. Finally, results are visualized to understand the route ridership and geographical pattern of trips.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
•Introduce longitudinal representation of transit user’s multi-week activity sequence.•Investigate passenger heterogeneity in such sequences based on smart card data.•Identify 11 clusters with ...distinct sequence structure in London’s transit users.•Reveal significant connections between demographics and activity sequence patterns.
The public transport networks of dense cities such as London serve passengers with widely different travel patterns. In line with the diverse lives of urban dwellers, activities and journeys are combined within days and across days in diverse sequences. From personalized customer information, to improved travel demand models, understanding this type of heterogeneity among transit users is relevant to a number of applications core to public transport agencies’ function. In this study, passenger heterogeneity is investigated based on a longitudinal representation of each user’s multi-week activity sequence derived from smart card data. We propose a methodology leveraging this representation to identify clusters of users with similar activity sequence structure. The methodology is applied to a large sample (n=33,026) from London’s public transport network, in which each passenger is represented by a continuous 4-week activity sequence. The application reveals 11 clusters, each characterized by a distinct sequence structure. Socio-demographic information available for a small sample of users (n=1973) is combined to smart card transactions to analyze associations between the identified patterns and demographic attributes including passenger age, occupation, household composition and income, and vehicle ownership. The analysis reveals that significant connections exist between the demographic attributes of users and activity patterns identified exclusively from fare transactions.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
•Proposes a general approach for the design of promotion-based transit TDM strategies.•Formulates the optimal promotion design as a 0-1 integer optimization problem.•Recognizes explicitly the role of ...effective and ineffective users in the formulation.•Evaluates the performance profile of various structures in space, time and discount.
Travel demand management (TDM) is used for managing congestion in urban areas. While TDM is well studied for car traffic, its application in transit is still emerging. Well-structured transit TDM approaches can help agencies better manage the available system capacity when the opportunity and investment to expand are limited. However, transit systems are complex and the design of a TDM scheme, deciding when, where, and how much discount or surcharge is implemented, is not trivial. The paper proposes a general framework for the optimal design of promotion based TDM strategies in urban rail systems. The framework consists of two major components: network performance and optimization. The network performance model updates the origin-destination (OD) demand based on the response to the promotion strategy, assigns it to the network, and estimates performance metrics. The optimization model allocates resources to maximize promotion performance in a cost effective way by better targeting users whose behavioral response to the promotion improves system performance. The optimal design of promotion strategies is facilitated by the availability of smart card (automated fare collection, AFC) data. The proposed approach is demonstrated with data from a busy urban rail system. The results illustrate the value of the method, compare the effectiveness of different strategies, and highlight the limits of the effectiveness of such strategies.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
•Transport impacts of weather using smartcard data and meteorological observations are explored.•Weather impact on hourly public transit ridership is examined.•Weather impact on the ridership at ...individual metro station is investigated.•Regular transit users’ response to weather conditions is explored.•Statistical models are developed to quantify these impacts.
The existing studies concerning the influence of weather on public transport have mainly focused on the impacts of average weather conditions on the aggregate ridership of public transit. Not much research has examined these impacts at disaggregate levels. This study aims to fill this gap by accounting for intra-day variations in weather as well as public transport ridership and investigating the effect of weather on the travel behavior of individual public transit users. We have collected smart card data for public transit and meteorological records from Shenzhen, China for the entire month of September 2014. The data allow us to establish association between the system-wide public transit ridership and weather condition on not only daily, but also hourly basis and for each metro station. In addition, with the detailed trip records of individual card holders, the travel pattern by public transit are constructed for card holders and this pattern is linked to the weather conditions he/she has experienced. Multivariate modeling approach is applied to analyze the influence of weather on public transit ridership and the travel behavior of regular transit users. Results show that some weather elements have more influence than others on public transportation. Metro stations located in urban areas are more vulnerable to outdoor weather in regard to ridership. Regular transit users are found to be rather resilient to changes in weather conditions. Findings contribute to a more in-depth understanding of the relationship between everyday weather and public transit travels and also provide valuable information for short-term scheduling in transit management.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Though metro systems are established in many Chinese cities including Nanjing, they have yet covered every corner of a city. Bikeshare as a feeder mode to metro helps solve the last mile problem. ...Thus, it is necessary to monitor and analyze metro-bikeshare transfer characteristics. The primary objective of this study is to derive a reproducible methodology that isolates bicycle-metro transfer trips using smart card data. Two recognition rules proposed are a maximum transfer time of 10 min and a maximum transfer distance of 300 m. To explore the general characteristics of metro-bikeshare transfer trips, transfer stations served at less than 30 transfer trips during three consecutive weeks were eliminated to ensure that a non-typical transfer pattern would not distort the results. The results show that more than 89% passengers recognized have less than 6 transfers in 3 weeks, indicating that most users integrate bikeshare with metro impromptu. Two transfer peaks on workdays are during 7:00–9:00 and 17:00–19:00, especially in suburban areas, while at weekends, transfers show quite even during 8:00–19:00. As to “Return-Enter” and “Exit-Lease” transfer modes, the “time difference” phenomenon does exist, which means that the transfer peak of “Return-Enter”mode always happens one hour earlier than that of “Exit-Lease”. Furthermore, the demographic differences in metro-bikeshare usage pattern are revealed. Finally, policy implications are involved to improve the performance of metro-bikeshare integration for all kinds of people without creating inequality.
•Recognizing valid metro-bikeshare transfer trips from metro and bikeshare smart card data.•Metro-bikeshare transfer patterns are explored from multiple perspectives.•Policy implications are involved to improve the performance of metro-bikeshare integration without creating inequality.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
•The paper develops a spatiotemporal topic model for human activity discovery.•Each topic is a distribution over space and time that corresponds to an activity.•The model accounts for a mixture of ...discrete and continuous travel attributes.•The model fits the data significantly better than heuristic approaches.•The number of topics controls the granularity of discovered activity patterns.
Although automatically collected human travel records can accurately capture the time and location of human movements, they do not directly explain the hidden semantic structures behind the data, e.g., activity types. This work proposes a probabilistic topic model, adapted from Latent Dirichlet Allocation (LDA), to discover representative and interpretable activity categorization from individual-level spatiotemporal data in an unsupervised manner. Specifically, the activity-travel episodes of an individual user are treated as words in a document, and each topic is a distribution over space and time that corresponds to certain type of activity. The model accounts for a mixture of discrete and continuous attributes—the location, start time of day, start day of week, and duration of each activity episode. The proposed methodology is demonstrated using pseudonymized transit smart card data from London, U.K. The results show that the model can successfully distinguish the three most basic types of activities—home, work, and other. As the specified number of activity categories increases, more specific subpatterns for home and work emerge, and both the goodness of fit and predictive performance for travel behavior improve. This work makes it possible to enrich human mobility data with representative and interpretable activity patterns without relying on predefined activity categories or heuristic rules.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK