Travel Behavior Models Research Articles

How will automated vehicles shape users’ daily activities? Insights from focus groups with commuters in the Netherlands

Automated Vehicles (AVs) are expected to allow their users to engage in a broad range of non-driving activities while travelling, such as working, sleeping, playing games. The impact of this possibility on the satisfaction with travel and on travel demand has been extensively discussed in the literature. However, it has been hardly recognised that the availability of on-board activities influences the (time-geographic) constraints of daily activities and may alter the selection, location, and sequencing of other activities in the day. This hampers correct representation of travel behaviour in activity-based models aiming to predict the effects of AVs on mobility and environment (e.g., greenhouse gas emissions). To help fill this gap, we gathered and analysed qualitative data from focus groups, in which 27 commuters discussed their expectations concerning on-board activities and daily schedules in the AV-era. Among the core insights are the following three. First, it is useful to separate in modelling the satisfaction with travel and the potential for on-board activities during travel: they have different determinants and different consequences for activity schedules and individual travel demand. Second, on-board activities may be classified in 4 quadrants according to their novelty and priority level: this classification is helpful in understanding the potential re-arrangements of daily activities. Third, performing new activities during travel may lead to complex re-arrangements of daily activity patterns; the re-arrangements may ease or also increase time pressure. These, and other reported insights may facilitate more realistic representation of activity-travel behaviour in future travel behaviour models.

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.

Enriching Activity-Based Models using Smartphone-Based Travel Surveys

Smartphone-based travel surveys have attracted much attention recently, for their potential to improve data quality and response rate. One of the first such survey systems, Future Mobility Sensing (FMS), leverages sensors on smartphones, and machine learning techniques to collect detailed personal travel data. The main purpose of this research is to compare data collected by FMS and traditional methods, and study the implications of using FMS data for travel behavior modeling. Since its initial field test in Singapore, FMS has been used in several large-scale household travel surveys, including one in Tel Aviv, Israel. We present comparative analyses that make use of the rich datasets from Singapore and Tel Aviv, focusing on three main aspects: (1) richness in activity behaviors observed, (2) completeness of travel and activity data, and (3) data accuracy. Results show that FMS has clear advantages over traditional travel surveys: it has higher resolution and better accuracy of times, locations, and paths; FMS represents out-of-work and leisure activities well; and reveals large variability in day-to-day activity pattern, which is inadequately captured in a one-day snapshot in typical traditional surveys. FMS also captures travel and activities that tend to be under-reported in traditional surveys such as multiple stops in a tour and work-based sub-tours. These richer and more complete and accurate data can improve future activity-based modeling.

Integrating mesoscopic dynamic traffic assignment with agent-based travel behavior models for cumulative land development impact analysis

A number of approaches have been developed to evaluate the impact of land development on transportation infrastructure. While traditional approaches are either limited to static modeling of traffic performance or lack a strong travel behavior foundation, today’s advanced computational technology makes it feasible to model an individual traveler’s response to land development. This study integrates dynamic traffic assignment (DTA) with a positive agent-based microsimulation travel behavior model for cumulative land development impact studies. The integrated model not only enhances the behavioral implementation of DTA, but also captures traffic dynamics. It provides an advanced yet practical approach to understanding the impact of a single or series of land development projects on an individual driver’s behavior, as well as the aggregated impacts on the demand pattern and time-dependent traffic conditions. A simulation-based optimization (SBO) approach is proposed for the calibration of the modeling system. The SBO calibration approach enhances the transferability of this integrated model to other study areas. Using a case study that focuses on the cumulative land development impact along a congested corridor in Maryland, various regional and local travel behavior changes are discussed to show the capability of this tool for behavior side estimations and the corresponding traffic impacts.

Marketing of Public Services

Public services are provided by government and have been traditionally supply-oriented. Changing citizen expectations put pressure on government agencies and public sector organizations to be accountable for efficiency and effectiveness. Further, the quest to enhance international competitiveness by ranking high in the echelons of world’s best governments, led to the adoption of proven marketing philosophy and methodologies in the domain of public service as well. The present study aims at examining the impact of Service quality, Reputation and Consumer Engagement on Customer Perceived Value, Satisfaction and Loyalty for an important public service viz., Dubai Metro which operated in an intensely competitive market. The study aimed at developing and empirically testing a structural model of travel behavior based on variables such as satisfaction, value, quality, reputation and engagement that have been found to drive loyalty in various industry settings. An understanding of the drivers of satisfaction contributes to the government’s aim of delivering services that rival the best in the private sector; contributes to the neglected public service context in the service management literature and captures insights that help the shift to service-dominant thinking within the public sector.

Measuring and enhancing the transferability of hidden Markov models for dynamic travel behavioral analysis

As an emerging dynamic modeling method that incorporates time-dependent heterogeneity, hidden Markov models (HMM) are receiving increased research attention with regards to travel behavior modeling and travel demand forecasting. This paper focuses on the model transferability of HMM. Based on a series of transferability and goodness-of-fit measures, it finds that HMMs have a superior performance in predicting future transportation mode choice, compared to conventional choice models. Aimed at further enhancing its transferability, this paper proposes a Bayesian conditional recalibration approach that maps the model prediction directly to the context data. Compared to traditional model transferring methods, the proposed approach does not assume fixed parameterization and recalibrates the utilities and the prediction directly. A comparison between the proposed approach and the traditional transfer-scaling favors our approach, with higher goodness-of-fit. This paper fills the gap in understanding the transferability of HMM and proposes a practical method that enables potential applications of HMM.

Active commuting among junior high school students in a Chinese medium-sized city: Application of the theory of planned behavior

In China, junior high school students are considered as adolescents, and their parents have guardianship of them. If junior high school students want to travel by motorized vehicles, they need to get assistance from their parents. The present study uses the theory of planned behavior to construct a model of dependent travel behavior that depicts the active commuting of junior high school students to school. A total of 449 junior high school students’ parents in Jinjiang city of Fujian Province in China were surveyed by using a questionnaire. Non-parametric test, reliability and validity test, factor analysis, and a logistic model were performed to test the model. The results show that the model is a good fit for the junior high school students’ active travel to school in the morning, and the Nagelkerke R2 of the model is 0.68. Behavioral intention and perceived behavioral control of parents affect students’ active commuting behavior, and behavioral intention is larger on behavior. Besides the inner attitude, the external environment such as non-motorized traffic facilities and the road traffic conditions along the way to school have significant effect on the behavior. In contrast to our expectations, parents leaving home for work in the morning, children’s gender, grade, and household income have no significant influence on the behavior. Measures should be taken by the local government to promote students’ active commuting to school, such as improving road traffic environment and providing safe routes.

Travel pattern modelling and future travel behaviour prediction based on GMM and GPR

How to use historical data of public smart card to predict user behaviour attracts a lot of attention. This paper aims at modelling travel patterns and predicting future travel behaviour of metro system smart card holders. We apply Gaussian mixture model (GMM) on time series to model user behaviour. We propose a new method based on the perplexity for finite GMM and use expectation-maximisation (EM) algorithm to estimate parameters of GMM. In order to predict the future travel behaviour, we introduce the Gaussian process regression (GPR) to define distributions over GMM, which can not only tell the probability of travelling at a certain moment but also tell the reliability of the prediction. Experimental results show that our whole system in the centre of GMM and GPR can effectively mine the hidden knowledge of historical data of smart card, and thus model the travel patterns and predict future travel behaviour.

Travel pattern modelling and future travel behaviour prediction based on GMM and GPR

Travel pattern modelling and future travel behaviour prediction based on GMM and GPR

Individual Travel Behavior Modeling of Public Transport Passenger Based on Graph Construction

This paper presents a novel method for mining the individual travel behavior regularity of different public transport passengers through constructing travel behavior graph based model. The individual travel behavior graph is developed to represent spatial positions, time distributions, and travel routes and further forecasts the public transport passenger’s behavior choice. The proposed travel behavior graph is composed of macronodes, arcs, and transfer probability. Each macronode corresponds to a travel association map and represents a travel behavior. A travel association map also contains its own nodes. The nodes of a travel association map are created when the processed travel chain data shows significant change. Thus, each node of three layers represents a significant change of spatial travel positions, travel time, and routes, respectively. Since a travel association map represents a travel behavior, the graph can be considered a sequence of travel behaviors. Through integrating travel association map and calculating the probabilities of the arcs, it is possible to construct a unique travel behavior graph for each passenger. The data used in this study are multimode data matched by certain rules based on the data of public transport smart card transactions and network features. The case study results show that graph based method to model the individual travel behavior of public transport passengers is effective and feasible. Travel behavior graphs support customized public transport travel characteristics analysis and demand prediction.

Personalized Air Travel Prediction

Human mobility analysis is one of the most important research problems in the field of urban computing. Existing research mainly focuses on the intra-city ground travel behavior modeling, while the inter-city air travel behavior modeling has been largely ignored. Actually, the inter-city travel analysis can be of equivalent importance and complementary to the intra-city travel analysis. Understanding massive passenger-air-travel behavior delivers intelligence for airlines’ precision marketing and related socioeconomic activities, such as airport planning, emergency management, local transportation planning, and tourism-related businesses. Moreover, it provides opportunities to study the characteristics of cities and the mutual relationships between them. However, modeling and predicting air traveler behavior is challenging due to the complex factors of the market situation and individual characteristics of customers (e.g., airlines’ market share, customer membership, and travelers’ intrinsic interests on destinations). To this end, in this article, we present a systematic study on the personalized air travel prediction problem, namely where a customer will fly to and which airline carrier to fly with, by leveraging real-world anonymized Passenger Name Record (PNR) data. Specifically, we first propose a relational travel topic model, which combines the merits of latent factor model with a neighborhood-based method, to uncover the personal travel preferences of aviation customers and the latent travel topics of air routes and airline carriers simultaneously. Then we present a multi-factor travel prediction framework, which fuses complex factors of the market situation and individual characteristics of customers, to predict airline customers’ personalized travel demands. Experimental results on two real-world PNR datasets demonstrate the effectiveness of our approach on both travel topic discovery and customer travel prediction.

A surrogate-assisted genetic algorithm for the selection and design of highway safety and travel time improvement projects

Measures to improve highway safety can affect travel times, just like measures to reduce travel times can affect highway safety. For this reason, the models used in the process of allocating funds across different highway improvement projects should simultaneously consider the safety and travel time effects of the project alternatives. In this paper, an optimization model is presented for the joint selection and design of highway safety and travel time improvement projects. The model is formulated as a bi-objective, mixed-integer optimization problem with constraints on project costs and on the types of improvement combinations admissible at project sites. By incorporating travel behavior models within the optimization process, the model accounts for the potential network-level effects of highway improvement schemes. Given that the model systems needed in this process are time-consuming, a genetic algorithm is proposed that utilizes surrogate models to accelerate the discovery of good solutions to the presented optimization model. In this algorithm, the surrogate models are used to generate computationally inexpensive approximations to computationally expensive functions that quantify a decision-maker’s safety and travel time objectives. Like the problem formulation, the proposed heuristic can be employed in conjunction with computer-based travel demand models commonly used by transportation planning agencies. An illustrative application of the model and its solution heuristic is presented using a hypothetical planning scenario in Southwest Puerto Rico. Besides illustrating the application of the model, the example was used to test the surrogates’ predictive accuracy and the impact of different parameter values on the algorithm’s performance.

Decision field theory: Improvements to current methodology and comparisons with standard choice modelling techniques

There is a growing interest in the travel behaviour modelling community in using alternative methods to capture the behavioural mechanisms that drive our transport choices. The traditional method has been Random Utility Maximisation (RUM) and recent interest has focussed on Random Regret Minimisation (RRM), but there are many other possibilities. Decision Field Theory (DFT), a dynamic model popular in mathematical psychology, has recently been put forward as a rival to RUM but has not yet been investigated in detail or compared against other competing models like RRM. This paper considers arguments in favour of using DFT, reviews how it has been used in transport literature so far and provides theoretical improvements to further the mechanisms behind DFT to better represent general decision making. In particular, we demonstrate how the probability of alternatives can be calculated after any number of timesteps in a DFT model. We then look at how to best operationalise DFT using simulated datasets, finding that it can cope with underlying preferences towards alternatives, can include socio-demographic variables and that it performs best when standard score normalisation is applied to the alternative attribute levels. We also present a detailed comparison of DFT and Multinomial Logit (MNL) models using stated preference route choice datasets and find that DFT achieves significantly better fit in estimation as well as forecasting. We also find that our theoretical improvement provides DFT with much greater flexibility and that there are numerous approaches that can be adopted to incorporate heterogeneity within a DFT model. In particular, random parameters vastly improve the model fit.

Investigating the association between travelers’ individual characteristics and their attitudes toward weather information

The current study aims to explore the association between individual characteristics and traveler’s attitudes toward weather information. A stated adaptation survey was conducted to collect traveler’s attitudes, and hypotheses of dependence of travel attitudes on individual characteristics were formally tested. 408 samples collected in 4 businesses or service centers in urban areas of Nanjing, China, were employed in analyses. Based on the aggregated individual characteristics by factor analysis, various independence tests and strength of association analyses were conducted both on disaggregated and aggregated levels. Results confirmed that the individual characteristics mattered and that the likelihood of travelers changing their travel behaviors (or willingness to change their travel behaviors) in response to weather information they acquired was highly dependent on some of individual characteristics. For example, the attitude of changing commuting departure time indicates significant dependence on gender, age, personal income, car and non-motor ownership, while attitude of changing shopping/leisure departure time depends on age and transit accessibility. Additionally, education has a larger impact on the attitude of changing home-based mode choices than gender and age. On aggregated level, non-motor ownership and transit availability show significant effects on the attitudes toward shopping/leisure departure time change and destination change. This paper contributes to the literature by looking at the underlying association between the changes in travelers’ attitudes and individual characteristics by means of a multifaceted stated adaptation approach and combined analysis method, and by proposing a deeper understanding of traveler’s characteristics when modeling travel behavior (attitudes) in inclement weather conditions.

A practical method to test the validity of the standard Gumbel distribution in logit-based multinomial choice models of travel behavior

Most multinomial choice models (e.g., the multinomial logit model) adopted in practice assume an extreme-value Gumbel distribution for the random components (error terms) of utility functions. This distributional assumption offers a closed-form likelihood expression when the utility maximization principle is applied to model choice behaviors. As a result, model coefficients can be easily estimated using the standard maximum likelihood estimation method. However, maximum likelihood estimators are consistent and efficient only if distributional assumptions on the random error terms are valid. It is therefore critical to test the validity of underlying distributional assumptions on the error terms that form the basis of parameter estimation and policy evaluation. In this paper, a practical yet statistically rigorous method is proposed to test the validity of the distributional assumption on the random components of utility functions in both the multinomial logit (MNL) model and multiple discrete-continuous extreme value (MDCEV) model. Based on a semi-nonparametric approach, a closed-form likelihood function that nests the MNL or MDCEV model being tested is derived. The proposed method allows traditional likelihood ratio tests to be used to test violations of the standard Gumbel distribution assumption. Simulation experiments are conducted to demonstrate that the proposed test yields acceptable Type-I and Type-II error probabilities at commonly available sample sizes. The test is then applied to three real-world discrete and discrete-continuous choice models. For all three models, the proposed test rejects the validity of the standard Gumbel distribution in most utility functions, calling for the development of robust choice models that overcome adverse effects of violations of distributional assumptions on the error terms in random utility functions.

Greenhouse gas impacts of different modality style classes using latent class travel behavior model

This study analyzed the interconnections between urban structure and socioeconomic, demographic and lifestyle variables and direct ground transport greenhouse gas (GHG) emissions in the Helsinki metropolitan region in Finland by using a latent class choice model (LCCM). The aim of the study was to identify and improve our understanding of the latent modality styles which guide people's everyday travel choices, and the resulting GHG implications. The GHG implications for different modality style groups are particularly interesting, since such analysis has not been included in previous studies. This study used the transport survey of the Helsinki Region Transport (HSL) from 2012, including over 17,000 trips, and consisted of two parts: first, the population was divided into classes based on latent class analysis, and secondly, the mode choices and GHG emissions were modelled for each class. Seven modality style groups were defined with strongly varying GHG impacts and travel profiles. According to the class specific choice modelling the probabilities of selecting different modes also varied significantly. The study offers new information for designing effective mitigation policies for different types of modality style groups. For example, car-oriented groups would benefit from more fuel-efficient vehicles and vehicles with alternative power sources, whereas the multimodal traveler could be more receptive to policies promoting cycling and public transport. Overall, the study depicts the potential of the latent class method to study the emissions caused by heterogeneous populations and to search for efficient GHG mitigation possibilities.

Potentials of using social media to infer the longitudinal travel behavior: A sequential model-based clustering method

This study explores the possibility of employing social media data to infer the longitudinal travel behavior. The geo-tagged social media data show some unique features including location-aggregated features, distance-separated features, and Gaussian distributed features. Compared to conventional household travel survey, social media data is less expensive, easier to obtain and the most importantly can monitor the individual’s longitudinal travel behavior features over a much longer observation period. This paper proposes a sequential model-based clustering method to group the high-resolution Twitter locations and extract the Twitter displacements. Further, this study details the unique features of displacements extracted from Twitter including the demographics of Twitter user, as well as the advantages and limitations. The results are even compared with those from traditional household travel survey, showing promises in using displacement distribution, length, duration and start time to infer individual’s travel behavior. On this basis, one can also see the potential of employing social media to infer longitudinal travel behavior, as well as a large quantity of short-distance Twitter displacements. The results will supplement the traditional travel survey and support travel behavior modeling in a metropolitan area.

Forecasting travel time reliability in urban road transpo

Assessment of travel time reliability as a fundamental factor in travel behaviour has become a very important aspect in both transport modelling and economic appraisal. Improved reliability could provide a significant economic benefit if it is adequately calculated in cost-benefit analyses for which the theoretical background has already been set. However, methods to forecast travel time reliability as well as travel behaviour models including its effects are rather scarce and there is a need for development in this field. Another important aspect could be the influencing factor of reliability in travel demand management and related policy-making. Therefore, this paper intends to further analyse reliability focusing exclusively on urban road transport based on automatic measurements of journey times and traffic volumes from a dataset of the city of Budapest. The main finding and the novelty of the study is a model which can forecast the standard deviation of travel times based on the volume-capacity ratio and the free-flow travel time. The paper also provides a real-life numerical experiment in which the proposed model has been compared with other, existing ones. It proves that besides existing mean-delay-based models, travel time reliability can be forecasted based on the volume-capacity ratio with an adequate accuracy.

Modeling travel mode choice behavior with bounded rationality using Markov Logic Networks

Disaggregate choice models have been widely studied to quantify the influence of the characteristics of travelers as well as the attributes of alternatives and choices in their travel modes. However, due to their model specifications and primary assumptions on unobserved disturbances, their modeling capability is constrained. In this study, a Markov Logic Network (MLN)-based approach is developed to combine bounded rationality principles with travelers’ behavior in travel mode choices. This approach is established based on logical domain knowledge and probabilistic models. MLN can extract logical domain knowledge and represent the impacts of significant attributes using independent logical formulas that are weighted correspondingly by their relative relationships. Travel-mode choice is determined based on travelers’ personal preferences and logical domain knowledge. The numerical examples and parameter sensitivity analyses indicate this approach performs reasonably well. The research findings are helpful to better understand travel mode-choice model specifications and travel behavior interpretations.

Optimal travel information provision strategies: an agent-based approach under uncertainty

ABSTRACTInformation influences travel behavior a great deal. This paper applies and further develops an agent-based approach to modeling travel behavior under uncertainty and different information provision strategies. Artificially intelligent agents, with the capability of learning, information acquisition, searching, and decision, are constructed instead of the typical representative agents formulated by utility maximization theory. Meanwhile, the presumption of sequential behavior process is relaxed. Agents are flexible to adjust travel mode, departure time, and route in response to a stimulus. A traffic simulator is also integrated in order to simulate agents' travel experiences on a transportation network. The agent-based model is then integrated into a simulation-based optimization (SBO) framework to analyze the effects of different information provision strategies. It is found that providing real-time traffic information to agents does not always result in improved network traffic condition or higher network reliability. Thus, we employ SBO technique to identify the optimal information provision strategies to support policy/planning decision-making.