A zonal inference model based on observed smart-card transactions for Santiago de Chile

The collection of origin–destination data for a city is an important but often costly task. This way, there is a need to develop more efficient and inexpensive methods of collecting information about citizens’ travel patterns. In this line, this paper presents a generic methodology that allows to infer the origin and destination zones for an observed trip between two public transport stops (i.e., bus stops or metro stations) using socio-economic, land use, and network information. The proposed zonal inference model follows a disaggregated Logit approach including size variables. The model enables the estimation of a zonal origin–destination matrix for a city, if trip information passively collected by a smart-card payment system is available (in form of a stop-to-stop matrix). The methodology is applied to the Santiago de Chile’s morning peak period, with the purpose of serving as input for a public transport planning computational tool. To estimate the model, information was gathered from different sources and processed into a unified framework; data included a survey conducted at public transport stops, land use information, and a stop-to-stop trip matrix. Additionally, a zonal system with 1176 zones was constructed for the city, including the definition of its access links and associated distances. Our results shows that, ceteris paribus, zones with high numbers of housing units have higher probabilities of being the origin of a morning peak trip. Likewise, health facilities, educational, residential, commercial, and offices centres have significant attraction powers during this period. In this sense, our model manages to capture the expected effects of land use on trip generation and attraction. This study has numerous policy implications, as the information obtained can be used to predict the impacts of changes in the public transport network (such as extending routes, relocating their stops, designing new routes or changing the fare structure). Further research is needed to improve the zonal inference formulation and origin–destination matrix estimation, mainly by including better cost measures, and dealing with survey and data limitations.     

Capturing the conditions that introduce systematic variation in bike-sharing travel behavior using data mining techniques

The potential of smart-card transactions within bike-sharing systems (BSS) is still to be explored. This research proposes an original offline data mining procedure that takes advantage of the quality of these data to analyze the bike usage casuistry within a sharing scheme. A difference is made between usage and travel behavior: the usage is described by the actual trip-chaining gathered with every smart-card transaction and is directly influenced by the limitations of the BSS as a public renting service, while the travel behavior relates to the spatio-temporal distribution, the travel time and trip purpose. The proposed approach is based on the hypothesis that there are systematic usage types which can be described through a set of conditions that permit to classify the rentals and reduce the heterogeneity in travel patterns. Hence, the proposed algorithm is a powerful tool to characterize the actual demand for bike-sharing systems. Furthermore, the results show that its potential goes well beyond that since service deficiencies rapidly arise and their impacts can be measured in terms of demand. Consequently, this research contributes to the state of knowledge on cycling behavior within public systems and it is also a key instrument beneficial to both decision makers and operators assisting the demand analysis, the service redesign and its optimization.     

An analysis of the factors influencing differences in survey-reported and GPS-recorded trips

Recent advances in global positioning systems (GPS) technology have resulted in a transition in household travel survey methods to test the use of GPS units to record travel details, followed by the application of an algorithm to both identify trips and impute trip purpose, typically supplemented with some level of respondent confirmation via prompted-recall surveys. As the research community evaluates this new approach to potentially replace the traditional survey-reported collection method, it is important to consider how well the GPS-recorded and algorithm-imputed details capture trip details and whether the traditional survey-reported collection method may be preferred with regards to some types of travel. This paper considers two measures of travel intensity (survey-reported and GPS-recorded) for two trip purposes (work and non-work) as dependent variables in a joint ordered response model. The empirical analysis uses a sample from the full-study of the 2009 Indianapolis regional household travel survey. Individuals in this sample provided diary details about their travel survey day as well as carried wearable GPS units for the same 24-h period. The empirical results provide important insights regarding differences in measures of travel intensities related to the two different data collection modes (diary and GPS). The results suggest that more research is needed in the development of workplace identification algorithms, that GPS should continue to be used alongside rather than in lieu of the traditional diary approach, and that assignment of individuals to the GPS or diary survey approach should consider demographics and other characteristics.     

Forecasting current and next trip purpose with social media data and Google Places

Trip purpose is crucial to travel behavior modeling and travel demand estimation for transportation planning and investment decisions. However, the spatial-temporal complexity of human activities makes the prediction of trip purpose a challenging problem. This research, an extension of work by Ermagun et al. (2017) and Meng et al. (2017), addresses the problem of predicting both current and next trip purposes with both Google Places and social media data. First, this paper implements a new approach to match points of interest (POIs) from the Google Places API with historical Twitter data. Therefore, the popularity of each POI can be obtained. Additionally, a Bayesian neural network (BNN) is employed to model the trip dependence on each individual’s daily trip chain and infer the trip purpose. Compared with traditional models, it is found that Google Places and Twitter information can greatly improve the overall accuracy of prediction for certain activities, including “EatOut”, “Personal”, “Recreation” and “Shopping”, but not for “Education” and “Transportation”. In addition, trip duration is found to be an important factor in inferring activity/trip purposes. Further, to address the computational challenge in the BNN, an elastic net is implemented for feature selection before the classification task. Our research can lead to three types of possible applications: activity-based travel demand modeling, survey labeling assistance, and online recommendations.     

A structural equations analysis of commuters' activity and travel patterns

An exploratory analysis of commuters' activity and travel patterns was carried out using activity-based travel survey data collected in the Washington, DC metropolitan area to investigate and estimate relationships among socio-demographics, activity participation, and travel behavior. Structural equations modeling methodology was adopted to determine the structural relationships among commuters' demographics, activity patterns, trip generation, and trip chaining information. Three types of structural equations model systems were estimated: one that models relationships between travel and activity participation, another that captures trade-offs between in-home and out-of-home activity durations, and a third that models the generation of complex work trip chains. The model estimation results show that strong relationships do exist among commuters' socio-demographic characteristics, activity engagement information, and travel behavior. The finding that significant trade-offs exist between in-home and out-of-home activity participation is noteworthy in the context of in-home vs. out-of-home substitution effects. Virtually all of the results obtained in this paper corroborate earlier findings reported in the literature regarding relationships among time use, activity participation, and travel. This revised version was published online in June 2006 with corrections to the Cover Date.     

An adaptive hawkes process formulation for estimating time-of-day zonal trip arrivals with location-based social networking check-in data

Location-Based Social Networking (LBSN) services, such as Foursquare, Facebook check-ins, and Geo-tagged Twitter tweets, have emerged as new secondary data sources for studying individual travel mobility patterns at a fine-grained level. However, the differences between human social behavioral and travel patterns can cause significant sampling bias for travel demand estimation. This paper presents a dynamic model to estimate time-of-day zonal trip arrival patterns. In the proposed model, the state propagation is formulated by the Hawkes process; the observation model implements LBSN sampling. The proposed model is applied to Foursquare check-in data collected from Austin, Texas in 2010 and calibrated with Origin-Destination (OD) data and time of day factor from Capital Area Metropolitan Planning Organization (CAMPO). The proposed model is compared with a simple aggregation model of trip purposes and time of day based on a prior daily OD estimation model using the LBSN data. The results illustrate the promising benefits of applying stochastic point process models and state-space modeling in time-of-day zonal arrival pattern estimation with the LBSN data. The proposed model can significantly reduce the number of parameters to calibrate in order to reduce the sampling bias of LBSN data for trip arrival estimation.     

Trip chaining propensity and tour mode choice of out-of-home workers: evidence from a mid-sized Canadian city

Suburban development patterns, flexible work hours, and increasing participation in out-of-home activities are making the travel patterns of individuals more complex, and complex trip chaining could be a major barrier to the shift from drive-alone to public transport. This study introduces a cohort-based approach to analyse trip tour behaviors, in order to better understand and model their relationships to socio-demographics, trip attributes, and land use patterns. Specifically, it employs worker population cohorts with homogenous activity patterns to explore differences and similarities in tour frequency, trip chaining, and tour mode choices, all of which are required for travel demand modeling. The paper shows how modeling of these important tour variables may be improved, for integration into an activity-based modeling framework. Using data from the Space–Time Activity Research (STAR) survey for Halifax, Canada, five clusters of workers were identified from their activity travel patterns. These were labeled as extended workers, 8 to 4 workers, shorter work-day workers, 7 to 3 workers, and 9 to 5 workers. The number of home-based tours per day for all clusters were modeled using a Poisson regression model. Trip chaining was then modeled using an Ordered Probit model, and tour mode choice was modeled using a Multinomial logit (MNL) model. Statistical analysis showed that socio-demographic characteristics and tour attributes are significant predictors of travel behavior, consistent with existing literature. Urban form characteristics also have a significant influence on non-workers’ travel behavior and tour complexity. The findings of this study will assist in the future evaluation of transportation projects, and in land-use policymaking.

     

Integrated imputation of activity-travel diaries incorporating the measurement of uncertainty

Procedures to transform GPS tracks into activity-travel diaries have been increasingly addressed due to their potential benefit to replace traditional methods used in travel surveys. Existing approaches for data annotation however are not sufficiently accurate, which normally involves a prompted recall survey for data validation. Imputation algorithms for transportation mode detection seem to be largely dependent on speed-related features, which may blur the quality of classification results, especially with transportation modes having similar speeds. Therefore, in this paper we propose an enhanced integrated imputation approach by incorporating the critical indicators related to trip patterns, reflecting the effects of uncertain travel environments, including bus stops and speed percentiles. A two-step procedure which embeds a segmentation model and a transportation mode inference model is designed and examined based on purified prompted recall data collected in a large-scale travel survey. Results show the superior performance of the proposed approach, where the overall accuracy at trip level reaches 93.2% and 88.1% for training and surveyed data, respectively.     

Estimating origin-destination matrices from roadside survey data

The purpose of this study is to develop a valid and efficient method for estimating origin-destination tables from roadside survey data. Roadside surveys, whether conducted by interviews or postcard mailback methods, typically have in common the sampling of trip origin and destination information at survey stations. These survey stations are generally located where roads cross “screenlines,” which are imaginary barriers drawn to intercept the trip types of interest.Such surveys also include counts of traffic volumes, by which the partial origin-destination (O-D) tables obtained at the different stations can be expanded and combined to obtain the complete O-D table which represents travel throughout the entire study area. The procedure used to expand the sample O-D information from the survey stations must recognize and deal appropriately with a number of problems:

• 1.(i) The “double counting” problem: Long-distance trips may pass through more than one survey station location; thus certain trips have the possibility of being sampled and expanded more than once, leading to a potentially serious overrepresentation of long-distance trips in the complete expanded trip table.
• 2.(ii) The “leaky screenline” problem: Some route choices, particularly those using very lightly traveled roads, may miss the survey stations entirely, leading to an underestimation of certain O-D patterns, or to distorted estimates if such sites are arbitrarily coupled with actual nearby station locations.
• 3.(iii) The efficient use of the data: There is a need to adjust expansion factors to compensate for double counting and leaky screenlines. How can this be accomplished such that all of the data obtained at the stations are used without loss of information?
• 4.(iv) The consequences of uncertainty and unknown travel behavior: Since the O-D data and other sampled variables are subject to random error, and since in general the probability of encountering a long-distance trip at some survey stations is affected by traveler route-choice behavior, which is not understood, the sample expansion procedure must rely on the use of erroneous input data and questionable assumptions. The preferred procedure must minimize, rather than amplify, the effects of such input errors.

Here, five alternate methods for expanding roadside survey data in an unbiased manner are proposed and evaluated. In all cases, it is assumed that traveler route choice generally follows the pattern described by Dial's multipath assignment method. All methods are applied to a simple hypothetical network in order to examine their efficiency and error amplification properties. The evaluation of the five methods reveals that their performance properties vary considerably and that no single method is best in all circumstances. A microcomputer program has been provided as a tool to facilitate comparison among methods and to select the most appropriate expansion method for a particular application.     

Real-time trip purpose prediction using online location-based search and discovery services

The use of smartphone technology is increasingly considered a state-of-the-art practice in travel data collection. Researchers have investigated various methods to automatically predict trip characteristics based upon locational and other smartphone sensing data. Of the trip characteristics being studied, trip purpose prediction has received relatively less attention. This research develops trip purpose prediction models based upon online location-based search and discovery services (specifically, Google Places API) and a limited set of trip data that are usually available upon the completion of the trip. The models have the potential to be integrated with smartphone technology to produce real-time trip purpose prediction. We use a recent, large-scale travel behavior survey that is augmented by downloaded Google Places information on each trip destination to develop and validate the models. Two statistical and machine learning prediction approaches are used, including nested logit and random forest methods. Both sets of models show that Google Places information is a useful predictor of trip purpose in situations where activity- and person-related information is uncollectable, missing, or unreliable. Even when activity- and person-related information is available, incorporating Google Places information provides incremental improvements in trip purpose prediction.     

Importance of scenic byways in route choice: a survey of driving tourists in the United States

In order to develop more effective tourist information systems for use along scenic byways, it is important to know the characteristics of those people who include the presence of scenic byways in their selections of routes. Gaining a better understanding of these characteristics was the purpose of this study. The data presented here are from a United States (US) survey of the driving tourist's information needs and preferences weighted to be representative of US tourist travelers. The study showed that when planning a route to a destination on an overnight automobile trip, the driving tourist is most concerned with factors related to the actual driving of the route, such as the directness, safety, amount of congestion, and distance. Of secondary importance are factors that make the route entertaining or pleasant to drive, including whether the route is a scenic byway. Analysis of the importance of scenic byways by several demographic factors showed little difference in importance ratings except for age and household income. Examination of importance ratings by trip characteristics showed that the presence of scenic byways in selecting a route was more important for the traveler whose trip purpose is a vacation, who is in the midst of a long distance and duration trip, who will be either camping or staying in a hotel, and who has planned the trip well in advance. These results suggest that scenic byways are an excellent area for the implementation and testing of in-vehicle information systems for the driving tourist.     

Detecting trip purposes from smartphone-based travel surveys with artificial neural networks and particle swarm optimization

Travel surveys based on global positioning system (GPS) data have exponentially increased over the past decades. Trip characteristics, including trip ends, travel modes, and trip purposes need to be detected from GPS data. Compared with other trip characteristics, studies on trip purpose detection are limited. These studies struggle with three types of limitations, namely, data validation, classification approach-related issues, and result comparison under multiple scenarios. Therefore, we attempt to obtain full understanding and improve these three aspects when detecting trip purposes in the current study. First, a smartphone-based travel survey is employed to collect GPS data, and a surveyor-intervened prompted recall survey is used to validate trip characteristics automatically detected from the GPS data. Second, artificial neural networks combined with particle swarm optimization are used to detect trip purposes from the GPS data. Third, four scenarios are constructed by employing two methods for land-use type coding, i.e., polygon-based information and point of interest, and two methods for selecting training dataset, i.e., equal proportion selection and equal number selection. The accuracy of trip purpose detection is then compared under these scenarios. The highest accuracies of 97.22% for the training dataset and 96.53% for the test dataset are achieved under the scenario of polygon-based information and equal proportion selection by comparing the detected and validated trip purposes. Promising results indicate that a smartphone-based travel survey can complement conventional travel surveys.     

Intrapersonal variability and model goodness-of-fit

This paper investigates the effect of day-to-day variability in individuals' travel behavior on the goodness-of-fit of travel demand models estimated with conventional cross-sectional data sets. In particular, this paper examines the effect of day-to-day variability on the goodness-of-fit of least squares regression models of person trip generation. The analytic results show that the conventional R-square goodness-of-fit measure for least squares regression models estimated with cross-sectional data is dependent upon two factors. The first factor is the proportion of the between-person variability that is accounted for by the explanatory variables in the model. The second factor is the proportion of the total variability in the dependent variable that is due to between-person variability. One week activity diary data are used to estimate the relative magnitude of the intrapersonal and interpersonal variability components for a variety of measures of trip-making. This analysis shows that intrapersonal variability may comprise a substantial proportion of the total variability, although the relative magnitude of the intrapersonal variability component varies with trip purpose and across population segments. Generally, however, intrapersonal variability is found to have a considerable effect on the apparent goodness-of-fit of person level trip generation models estimated with cross-sectional data. The paper also illustrates that recognizing the effect of intrapersonal variability on model goodness-of-fit may be useful in interpreting and evaluating model estimation and model transferability results.     

Path-constrained traffic assignment: A trip chain analysis under range anxiety

This paper proposes and analyzes a distance-constrained traffic assignment problem with trip chains embedded in equilibrium network flows. The purpose of studying this problem is to develop an appropriate modeling tool for characterizing traffic flow patterns in emerging transportation networks that serve a massive adoption of plug-in electric vehicles. This need arises from the facts that electric vehicles suffer from the “range anxiety” issue caused by the unavailability or insufficiency of public electricity-charging infrastructures and the far-below-expectation battery capacity. It is suggested that if range anxiety makes any impact on travel behaviors, it more likely occurs on the trip chain level rather than the trip level, where a trip chain here is defined as a series of trips between two possible charging opportunities (Tamor et al., 2013). The focus of this paper is thus given to the development of the modeling and solution methods for the proposed traffic assignment problem. In this modeling paradigm, given that trip chains are the basic modeling unit for individual decision making, any traveler’s combined travel route and activity location choices under the distance limit results in a distance-constrained, node-sequenced shortest path problem. A cascading labeling algorithm is developed for this shortest path problem and embedded into a linear approximation framework for equilibrium network solutions. The numerical result derived from an illustrative example clearly shows the mechanism and magnitude of the distance limit and trip chain settings in reshaping network flows from the simple case characterized merely by user equilibrium.     

Identifying trip ends from raw GPS data with a hybrid spatio-temporal clustering algorithm and random forest model: a case study in Shanghai

ABSTRACT

Smartphones have been advocated as the preferred devices for travel behavior studies over conventional surveys. But the primary challenges are candidate stops extraction from GPS data and trip ends distinction from noise. This paper develops a Resident Travel Survey System (RTSS) for GPS data collection and travel diary verification, and then uses a two-step method to identify trip ends. In the first step, a density-based spatio-temporal clustering algorithm is proposed to extract candidate stops from trajectories. In the second step, a random forest model is applied to distinguish trip ends from mode transfer points. Results show that the clustering algorithm achieves a precision of 96.2%, a recall of 99.6%, mean absolute error of time within 3?min, and average offset distance within 30 meters. The comprehensive accuracy of trip ends identification is 99.2%. The two-step method performs well in trip ends identification and promotes the efficiency of travel survey systems.     

An exploration of the relationships between socioeconomics,land use and daily trip chain pattern among low-income residents

Daily trip chain complexity and type choices of low-income residents are examined based on activity travel diary survey data in Nanjing, China. Statistical tests reveal that non-work trip chain complexity is distinctly distinct between low-income residents and non-low-income residents. Low-income residents are inclined to make simple non-work chains. Two types of econometric models, a stereotype logit model and mixed logit model, are then developed to investigate the possible explanatory variables affecting their trip pattern. The number of stops within a chain and chain types are considered as dependent variables, while independent variables include household and personal characteristics as well as land use variables. Results show that once convenient and flexible conditions are supplied, low-income residents are more likely to make multiple activities in a trip chain. Areas with high population and employment densities are associated with complex work trip chains and more non-work activity involvement.     

Modelling Complex Activity‐Travel Scheduling Decisions: Procedure for the Simultaneous Estimation of Activity Generation and Duration Functions

Abstract

Activity generation is a key factor in individual's choices of trip frequency and trip purpose. This paper describes the results of an experiment conducted to estimate functions of several temporal factors on individuals' propensity to schedule a given activity on a given day. The theory on which the experimental design is based states that the probability of scheduling an activity is a complex and continuous function of how long ago the activity was lastly performed, the duration constraints for the activity and the amount of available time in the activity schedule of the day considered. Aurora, an existing model of activity scheduling, assumes S‐shaped utility functions for the history as well as the duration functions, whereas most time‐use studies assume monotonically decreasing marginal utilities. The stated‐choice experiment involves a range of flexible activities and a large sample of individuals to measure the utility effects of a set of carefully chosen levels for the factors and tests these specific assumptions. The results suggest that the amount of discretionary time on a day has no significant impact on the scheduling decisions provided that enough time is available for the activity. The effects of other factors are as expected and show diminishing marginal utilities. We find mixed evidence for an initial phase of increasing marginal returns as assumed in an S‐shaped function.     

Deriving and validating trip purposes and travel modes for multi-day GPS-based travel surveys: A large-scale application in the Netherlands

In the past few decades, travel patterns have become more complex and policy makers demand more detailed information. As a result, conventional data collection methods seem no longer adequate to satisfy all data needs. Travel researchers around the world are currently experimenting with different Global Positioning System (GPS)-based data collection methods. An overview of the literature shows the potential of these methods, especially when algorithms that include spatial data are used to derive trip characteristics from the GPS logs. This article presents an innovative method that combines GPS logs, Geographic Information System (GIS) technology and an interactive web-based validation application. In particular, this approach concentrates on the issue of deriving and validating trip purposes and travel modes, as well as allowing for reliable multi-day data collection. In 2007, this method was used in practice in a large-scale study conducted in the Netherlands. In total, 1104 respondents successfully participated in the one-week survey. The project demonstrated that GPS-based methods now provide reliable multi-day data. In comparison with data from the Dutch Travel Survey, travel mode and trip purpose shares were almost equal while more trips per tour were recorded, which indicates the ability of collecting trips that are missed by paper diary methods.     

Modelling the relationship between travel behaviours and social disadvantage

The purpose of this paper is to model the travel behaviour of socially disadvantaged population segments in the United Kingdom (UK) using the data from the UK National Travel Survey 2002–2010. This was achieved by introducing additional socioeconomic variables into a standard national-level trip end model (TEM) and using purpose-based analysis of the travel behaviours of certain key socially disadvantaged groups. Specifically the paper aims to explore how far the economic and social disadvantages of these individuals can be used to explain the inequalities in their travel behaviours.The models demonstrated important differences in travel behaviours according to household income, presence of children in the household, possession of a driver’s licence and belonging to a vulnerable population group, such as being disabled, non-white or having single parent household status. In the case of household income, there was a non-linear relationship with trip frequency and a linear one with distance travelled. The recent economic austerity measures that have been introduced in the UK and many other European countries have led to major cutbacks in public subsidies for socially necessary transport services, making results such as these increasingly important for transport policy decision-making. The results indicate that the inclusion of additional socioeconomic variables is useful for identifying significant differences in the trip patterns and distances travelled by low-income.     

A multiobjective planning model for intercity train seat allocation

This paper presents a multiobjective planning model for generating optimal train seat allocation plans on an intercity rail line serving passengers with many‐to‐many origin‐destination pairs. Two planning objectives of the model are to maximise the operator's total passenger revenue and to minimise the passenger's total discomfort level. For a given set of travel demand, train capacity, and train stop‐schedules, the model is solved by fuzzy mathematical programming to generate a best‐compromise train seat allocation plan. The plan determines how many reserved and non‐reserved seats are to be allocated at each origin station for all subsequent destination stations on each train run operated within a specified operating period. An empirical study on the to‐be‐built Taiwan's high‐speed rail system is conducted to demonstrate the effectiveness of the model. The model can be used for any setting of travel demand and stop‐schedules with various train seating capacities.