A reference-dependent user equilibrium model for activity-travel scheduling

Existing user equilibrium models of activity-travel scheduling generally fall short in representing travelers’ decision-making processes. The majority have either implicitly or explicitly assumed that travelers follow the principle of utility maximization. This assumption ignores the fact that individuals may be loss–averse when making activity-travel decisions. Allowing for the situation that travelers possess accurate information of the urban-transportation system due to modern technologies, studies on reference-dependent decision-making under near-perfect information are receiving increasing attention. In view of traveler heterogeneity, individuals can be divided into multiple classes according to their reference points. In this paper, we propose a reference-dependent multi-class user equilibrium model for activity-travel scheduling, which can be reformulated as a variational inequality problem. Moreover, comparative analyses are conducted on the equilibrium states between utility-maximization (no reference) and reference-dependency of exogenous and endogenous references. A numerical example regarding combined departure-time and mode choice for commuting is conducted to illustrate the proposed model. The simulated results indicate that reference points and loss aversion attitudes have significant effects on the choice of departure time and mode.     

A network equilibrium approach for modelling activity-travel pattern scheduling problems in multi-modal transit networks with uncertainty

An understanding of the interaction between individuals’ activities and travel choice behaviour plays an important role in long-term transit service planning. In this paper, an activity-based network equilibrium model for scheduling daily activity-travel patterns (DATPs) in multi-modal transit networks under uncertainty is presented. In the proposed model, the DATP choice problem is transformed into a static traffic assignment problem by constructing a new super-network platform. With the use of the new super-network platform, individuals’ activity and travel choices such as time and space coordination, activity location, activity sequence and duration, and route/mode choices, can be simultaneously considered. In order to capture the stochastic characteristics of different activities, activity utilities are assumed in this study to be time-dependent and stochastic in relation to the activity types. A concept of DATP budget utility is proposed for modelling the uncertainty of activity utility. An efficient solution algorithm without prior enumeration of DATPs is developed for solving the DATP scheduling problem in multi-modal transit networks. Numerical examples are used to illustrate the application of the proposed model and the solution algorithm.     

Machine learning applications in activity-travel behaviour research: a review

ABSTRACT

This paper reviews the activity-travel behaviour literature that employs Machine Learning (ML) techniques for empirical analysis and modelling. Machine Learning algorithms, which attempt to build intelligence utilizing the availability of large amounts of data, have emerged as powerful tools in the fields of pattern recognition and big data analysis. These techniques have been applied in activity-travel behaviour studies since the early ’90s when Artificial Neural Networks (ANN) were employed to model mode choice decisions. AMOS, an activity-based modelling system developed in the mid-’90s, has ANN at its core to model and predict individual responses to travel demand management measures. In the dawn of 2000, ALBATROSS, a comprehensive activity-based travel demand modelling system, was proposed by Arentze and Timmermans using Decision Trees. Since then researchers have been exploring ML techniques like Support Vector Machines (SVM), Decision Trees (DT), Neural Networks (NN), Bayes Classifiers, and more recently, Ensemble Learners to model and predict activity-travel behaviour. A large number of publications over the years and an upward trend in the number of published articles over time indicate that Machine Learning is a promising tool for activity-travel behaviour analysis and prediction. This article, first of its kind in the literature, reviews these studies and explores the trends in activity-travel behaviour research that apply ML techniques. The review finds that mode choice decisions have received wide attention in the literature on ML applications. It was observed that most of the studies identify the lack of interpretability as a serious shortcoming in ML techniques. However, very few studies have attempted to improve the interpretability of the models. Further, some studies report the importance of feature engineering in ML-based studies, but very few studies adopt feature engineering before model development. Spatiotemporal transferability of models is another issue that has received minimal attention in the literature. In the end, the paper discusses possible directions for future research in the area of activity-travel behaviour modelling using ML techniques.     

Incorporating space–time constraints and activity-travel time profiles in a multi-state supernetwork approach to individual activity-travel scheduling

Activity-travel scheduling is at the core of many activity-based models that predict short-term effects of travel information systems and travel demand management. Multi-state supernetworks have been advanced to represent in an integral fashion the multi-dimensional nature of activity-travel scheduling processes. To date, however, the treatment of time in the supernetworks has been rather limited. This paper attempts to (i) dramatically improve the temporal dimension in multi-state supernetworks by embedding space–time constraints into location selection models, not only operating between consecutive pairs of locations, but also at the overall schedule at large, and (ii) systematically incorporate time in the disutility profiles of activity participation and parking. These two improvements make the multi-state supernetworks fully time-dependent, allowing modeling choice of mode, route, parking and activity locations in a unified and time-dependent manner and more accurately capturing interdependences of the activity-travel trip chaining. To account for this generalized representation, refined behavioral assumptions and dominance relationships are proposed based on an earlier proposed bicriteria label-correcting algorithm to find the optimal activity-travel pattern. Examples are shown to demonstrate the feasibility of this new approach and its potential applicability to large scale agent-based simulation systems.     

Modeling duration choice in space–time multi-state supernetworks for individual activity-travel scheduling

Multi-state supernetworks have been advanced recently for modeling individual activity-travel scheduling decisions. The main advantage is that multi-dimensional choice facets are modeled simultaneously within an integral framework, supporting systematic assessments of a large spectrum of policies and emerging modalities. However, duration choice of activities and home-stay has not been incorporated in this formalism yet. This study models duration choice in the state-of-the-art multi-state supernetworks. An activity link with flexible duration is transformed into a time-expanded bipartite network; a home location is transformed into multiple time-expanded locations. Along with these extensions, multi-state supernetworks can also be coherently expanded in space–time. The derived properties are that any path through a space–time supernetwork still represents a consistent activity-travel pattern, duration choice are explicitly associated with activity timing, duration and chain, and home-based tours are generated endogenously. A forward recursive formulation is proposed to find the optimal patterns with the optimal worst-case run-time complexity. Consequently, the trade-off between travel and time allocation to activities and home-stay can be systematically captured.     

Women’s mode and trip structure choices in daily activity-travel: a developing country perspective

ABSTRACT

In this paper, we analyze the travel patterns of Iranian women, where typical patriarchal views and specific social and cultural norms may differ from the patterns of those in western societies. In addition to inherent psycho-physical gender differences, women in Iran can face special constraints forcing them not to be involved in all activity-travel patterns that people in developed countries usually undertake. We pay special attention to the role of marital and employment status on women’s activity-travel patterns. To this end, we develop a joint mode and daily activity pattern (DAP) discrete choice model, which is a two-level mixed nested Logit. The upper nest of the proposed model embodies women’s DAP choices, and the lower nest belongs to the mode choices. In this paper, we try to show how different factors in a patriarchal Muslim society like Iran affect or restrict women’s type and structure of activity-travel patterns.     

Interactive geovisualization of activity-travel patterns using three-dimensional geographical information systems: a methodological exploration with a large data set

A major difficulty in the analysis of disaggregate activity-travel behavior in the past arises from the many interacting dimensions involved (e.g. location, timing, duration and sequencing of trips and activities). Often, the researcher is forced to decompose activity-travel patterns into their component dimensions and focus only on one or two dimensions at a time, or to treat them as a multidimensional whole using multivariate methods to derive generalized activity-travel patterns. This paper describes several GIS-based three-dimensional (3D) geovisualization methods for dealing with the spatial and temporal dimensions of human activity-travel patterns at the same time while avoiding the interpretative complexity of multivariate pattern generalization or recognition methods. These methods are operationalized using interactive 3D GIS techniques and a travel diary data set collected in the Portland (Oregon) metropolitan region. The study demonstrates several advantages in using these methods. First, significance of the temporal dimension and its interaction with the spatial dimension in structuring the daily space-time trajectories of individuals can be clearly revealed. Second, they are effective tools for the exploratory analysis of activity diary data that can lead to more focused analysis in later stages of a study. They can also help the formulation of more realistic computational or behavioral travel models.     

Exploring spatial variety in patterns of activity-travel behaviour: initial results from the Toronto Travel-Activity Panel Survey (TTAPS)

Studies of urban travel behaviour typically focus on weekday activities and commuting. This is surprising given the rising contribution of discretionary activities to daily travel that has occurred during the last few decades. Moreover, current understanding of the relationship between travel behaviour and land use remains incomplete, with little research carried out to explore spatial properties of activity-travel behaviour during the off-peak and weekend time periods. Weekend behaviours, for example, influenced by the availability of time and the spatiotemporal distribution of “weekend” destinations, likely produce spatially and temporally distinct activity-travel patterns. Using data from the first wave of the Toronto Travel-Activity Panel Survey (TTAPS), this paper examines an area of research that has received little attention; namely, the presence of spatial variety in activity-travel behaviour. The paper begins by looking at the extent to which individuals engage in spatially repetitive location choices during the course of a single week. Area-based measures of geographical extent and activity dispersion are then used to expose differences in weekday-to-weekend and day-to-day activity-travel patterns. Examination of unclassified activities carried out over a 1 week period reveals a level of spatial repetition that does not materialise across activities classified by type, travel mode, and planning strategy. Despite the inherent spatial flexibility offered by the personal automobile, spatial repetition is also found to be surprisingly similar across travel modes. The results also indicate weekday-to-weekend, and day-to-day fluctuations in spatial properties of individual activity-travel behaviour. These findings challenge the utility of the short-run survey as an instrument for capturing archetypal patterns of spatial behaviour. In addition, the presence of a weekday-to-weekend differential in spatial behaviour suggests that policies targeting weekday travel reduction could have little impact on travel associated with weekend activities.

Social networks,social influence and activity-travel behaviour: a review of models and empirical evidence

ABSTRACT

The study of social networks in activity-travel research has recently gained momentum because social activities and social influence were relatively poorly explained in activity-based models of travel demand. Over the last decade, many scholars have shown interest in identifying personal social networks that constitute an important source of explanation of activity-travel behaviour. This paper seeks to review two research streams: social networks and activity-travel behaviour, and social influence and travel decisions. We classify models, summarise empirical findings and discuss important issues that require further research.     

Dynamic activity-travel assignment in multi-state supernetworks

The integration of activity-based modeling and dynamic traffic assignment for travel demand analysis has recently attracted ever-increasing attention. However, related studies have limitations either on the integration structure or the number of choice facets being captured. This paper proposes a formulation of dynamic activity-travel assignment (DATA) in the framework of multi-state supernetworks, in which any path through a personalized supernetwork represents a particular activity-travel pattern (ATP) at a high level of spatial and temporal detail. DATA is formulated as a discrete-time dynamic user equilibrium (DUE) problem, which is reformulated as an equivalent variational inequality (VI) problem. A generalized dynamic link disutility function is established with the accommodation of different characteristics of the links in the supernetworks. Flow constraints and non-uniqueness of equilibria are also investigated. In the proposed formulation, the choices of departure time, route, mode, activity sequence, activity and parking location are all unified into one time-dependent ATP choice. As a result, the interdependences among all these choice facets can be readily captured. A solution algorithm based on the route-swapping mechanism is adopted to find the user equilibrium. A numerical example with simulated scenarios is provided to demonstrate the advantages of the proposed approach.     

Representing mental maps and cognitive learning in micro-simulation models of activity-travel choice dynamics

This paper develops a model, based on Bayesian beliefs networks, for representing mental maps and cognitive learning into micro-simulation models of activity-travel behavior. Mental maps can be used to address the problem that choice sets in models of travel demand are often ad hoc specified. The theory underlying the model is discussed, a specification is derived and numerical simulation is used to illustrate the properties of the model.     

Capturing correlation with a mixed recursive logit model for activity-travel scheduling

Representing activity-travel scheduling decisions as path choices in a time–space network is an emerging approach in the literature. In this paper, we model choices of activity, location, timing and transport mode using such an approach and seek to estimate utility parameters of recursive logit models. Relaxing the independence from irrelevant alternatives (IIA) property of the logit model in this setting raises a number of challenges. First, overlap in the network may not fully characterize perceptual correlation between paths, due to their interpretation as activity schedules. Second, the large number of states that are needed to represent all possible locations, times and activity combinations imposes major computational challenges to estimate the model. We combine recent methodological developments to build on previous work by Blom Västberg et al. (2016) and allow to model complex and realistic correlation patterns in this type of network. We use sampled choices sets in order to estimate a mixed recursive logit model in reasonable time for large-scale, dense time-space networks. Importantly, the model retains the advantage of fast predictions without sampling choice sets. In addition to estimation results, we present an extensive empirical analysis which highlights the different substitution patterns when the IIA property is relaxed, and a cross-validation study which confirms improved out-of-sample fit.     

The effects of activity-travel context and individual attitudes on car-sharing decisions under travel time uncertainty: A hybrid choice modeling approach

People’s daily decision to use car-sharing rather than other transport modes for conducting a specific activity has been investigated recently in assessing the market potential of car-sharing systems. Most studies have estimated transport mode choice models with an extended choice set using attributes such as average travel time and costs. However, car-sharing systems have some distinctive features: users have to reserve a car in advance and pay time-based costs for using the car. Therefore, the effects of activity-travel context and travel time uncertainty require further consideration in models that predict car-sharing demand. Moreover, the relationships between individual latent attitudes and the intention to use car-sharing have not yet been investigated in much detail. In contributing to the research on car-sharing, the present study is designed to examine the effects of activity-travel context and individual latent attitudes on short-term car-sharing decisions under travel time uncertainty. The effects of all these factors were simultaneously estimated using a hybrid choice modeling framework. The data used in this study was collected in the Netherlands, 2015 using a stated choice experiment. Hypothetical choice situations were designed to collect respondents’ intention to use a shared-car for their travel to work. A total of 791 respondents completed the experiment. The estimation results suggest that time constraints, lack of spontaneity and a larger variation in travel times have significant negative effects on people’s intention to use a shared-car. Furthermore, this intention is significantly associated with latent attitudes about pro-environmental preferences, the symbolic value of cars, and privacy-seeking.     

Semiparametric specification of the utility function in a travel mode choice model

We propose a semiparametric approach that can capture the nonlinearity of deterministic components of the utility functions in discrete choice models and demonstrate it by analyzing travel mode choice behaviour for an interregional trip. The proposed smoothing spline-based specification method can be used to make ex ante evaluations regarding the parametric specifications of the deterministic utility functions in discrete choice models.     

A structural equation model based analysis of non-workers’ activity-travel behaviour from a city of a developing country

This paper presents an empirical analysis of non-workers’ activity-travel behaviour from Bangalore city, India. The paper builds a causal model—to describe the relationships among socio-demographics, activity-participation, and travel behaviour of non-workers—following structural equation modelling methodology. The results indicate that in-home maintenance activity-duration drives the time allocation decisions of non-workers. The model also shows the presence of ‘time-budget’ effects i.e., excess travel time cuts into in-hhome discretionary activity duration, implying the trade-off between daily travel time and in-home discretionary activity duration. The out-of-home activity durations of non-workers are found to be insensitive to travel time—an important finding of this research. The model also suggests that mixed residential development reduce travel distance and indirectly contribute to more trips. An indirect effect of mixed residential development on daily travel distance offsets the direct effect, which leads to a limited total effect of this variable on travel distance. The basic model was expanded further by separating the time spent on others’ activity (children and elders) from in-home maintenance activity duration. The stable model reveals that the time spent on others’ activity also influences in-home and out-of-home activities, and travel behaviour. This indicates that the time spent on others’ activity is an important time allocation of its own.     

An integrated framework to jointly model decisions of activity time allocation and work-related travel

Five activity-travel choice dimensions, including three activity time allocation decisions and two work-related travel choices, are jointly modeled using the structural equation model in order to accommodate the complex interactions among them. Via a two-step estimation approach, the behavioral pattern underlying activity-travel decisions is explicitly revealed. For example, it demonstrates the priority with respect to subsistence activity, maintenance activity, and recreation activity due to a limited time budget; and bus commuting behavior positively influences the time allocated to the maintenance activity. In addition, two attitudinal factors are constructed and confirmed to have important effects on the five behavioral dimensions, which contribute to reveal the decision-making process from the perspective of psychology. This comprehensive framework is expected to provide important implications for mobility management and urban planning.     

Integrating parking behaviour in activity-based travel demand modelling: Investigation of the relationship between parking type choice and activity scheduling process

Traditionally, the parking choice/option is considered to be an important factor in only in the mode choice component of a four-stage travel demand modelling system. However, travel demand modelling has been undergoing a paradigm shift from the traditional trip-based approach to an activity-based approach. The activity-based approach is intended to capture the influences of different policy variables at various stages of activity-travel decision making processes. Parking is a key policy variable that captures land use and transportation interactions in urban areas. It is important that the influences of parking choice on activity scheduling behaviour be identified fully. This paper investigates this issue using a sample data set collected in Montreal, Canada. Parking type choice and activity scheduling decision (start time choice) are modelled jointly in order to identify the effects of parking type choice on activity scheduling behaviour. Empirical investigation gives strong evidence that parking type choice influences activity scheduling process. The empirical findings of this investigation challenge the validity of the traditional conception which considers parking choice as exogenous variable only in the mode choice component of travel demand models.     

The prevalence of context-dependent adjustment of activity-travel patterns in energy conservation strategies: results from a mixture-amount stated adaptation experiment

People’s adaptive behaviour to increasing energy prices has been studied at length in transportation research. Prior research however has not addressed research questions concerning the contribution of travel-related changes in more encompassing energy conservation strategies. Moreover, context-dependency and choice under constraints has not been studies at any length. In this paper, we therefore report the results of a context-dependent elaboration of a mixture amount choice experiment to measure context-dependent responses to accumulative energy charges under budget constraints. Accounting for consumer heterogeneity in adaptive response behaviour, mixed logit analysis is used to analyse the extent and nature of adaptations of activity-travel behaviour and resource allocation in response to increasing energy costs. The results indicate that individuals are inclined to compensate for increased expenditures on energy due to price increases. Moreover, results show the existence of significant heterogeneity among respondents in terms of their adaptation strategies to various energy-saving choices.     

Modeling learning and adaptation processes in activity-travel choice A framework and numerical experiment

This paper develops a framework for modeling dynamic choice based on a theory of reinforcement learning and adaptation. According to this theory, individuals develop and continuously adapt choice rules while interacting with their environment. The proposed model framework specifies required components of learning systems including a reward function, incremental action value functions, and action selection methods. Furthermore, the system incorporates an incremental induction method that identifies relevant states based on reward distributions received in the past. The system assumes multi-stage decision making in potentially very large condition spaces and can deal with stochastic, non-stationary, and discontinuous reward functions. A hypothetical case is considered that combines route, destination, and mode choice for an activity under time-varying conditions of the activity schedule and road congestion probabilities. As it turns out, the system is quite robust for parameter settings and has good face validity. We therefore argue that it provides a useful and comprehensive framework for modeling learning and adaptation in the area of activity-travel choice.     

Micro-simulation of daily activity-travel patterns for travel demand forecasting

The development and initial validation results of a micro-simulator for the generation of daily activity-travel patterns are presented in this paper. The simulator assumes a sequential history and time-of-day dependent structure. Its components are developed based on a decomposition of a daily activity-travel pattern into components to which certain aspects of observed activity-travel behavior correspond, thus establishing a link between mathematical models and observational data. Each of the model components is relatively simple and is estimated using commonly adopted estimation methods and existing data sets. A computer code has been developed and daily travel patterns have been generated by Monte Carlo simulation. Study results show that individuals' daily travel patterns can be synthesized in a practical manner by micro-simulation. Results of validation analyses suggest that properly representing rigidities in daily schedules is important in simulating daily travel patterns. This revised version was published online in June 2006 with corrections to the Cover Date.