Analysis Of Travel Mode Choice Research Articles

Joint prediction of travel mode choice and purpose from travel surveys: A multitask deep learning approach

The prediction and behavioural analysis of travel mode choice and purpose are critical for transport planning and have attracted increasing interest in research. Traditionally, the prediction of travel mode choice and trip purpose has been tackled separately, which fail to fully leverage the shared information between travel mode and purpose. This study addresses this gap by proposing a multitask learning deep neural network framework (MTLDNN) to jointly predict mode choice and purpose. We empirically evaluate and validate this framework using the household travel survey data in Greater London, UK. The results show that this framework has significantly lower cross-entropy loss than multinomial logit models (MNL) and single-task-learning deep neural network models (STLDNN). On the other hand, the predictive accuracy of MTLDNN is similar to STLDNN and is significantly higher than MNL. Moreover, in terms of behaviour analysis, the substitution pattern and choice probability of MTLDNN regarding input variables largely agree with MNL and STLDNN. This work demonstrates that MTLDNN is efficient in utilising the information shared by travel mode choice and purpose, and is capable of producing behaviourally reasonable substitution patterns across travel modes. Future research would develop more advanced MTLDNN frameworks for travel behaviour analysis and generalise MTLDNN to other travel behaviour topics.

A Random Effect Bayesian Neural Network (RE-BNN) for travel mode choice analysis across multiple regions

Travel mode choice modelling plays a critical role in predicting passengers’ travel demand and planning local transportation systems. Researchers commonly adopt classical Random Utility Models to analyse individual decision-making based on the utility theory. Recently, with an increasing interest in applying Machine Learning techniques, a number of studies have used these methods for modelling travel mode preferences for their excellent predictive power. However, none of these studies proposes machine learning models that investigate the regional heterogeneity of travel behaviours. To address this gap, this study develops a Random Effect-Bayesian Neural Network (RE-BNN) framework to predict and explain travel mode choice across multiple regions by combining the Random Effect (RE) model and the Bayesian Neural Networks (BNN). The results show that this model outperforms the plain Deep Neural Network (DNN) regarding prediction accuracy and is more robust across different datasets. In addition, in terms of interpretation, the capability of RE-BNN to learn the travel behaviours across regions has been demonstrated by offset utilities, choice probability functions and local travel mode shares.

Analysis of travel mode choice and trip chain pattern relationships based on multi-day GPS data: A case study in Shanghai, China

As the propensity to link multiple intermediate stops in a trip chain (a sequence of journeys that starts and ends at home, includes visiting one or more locations) is more prevalent, the relationship between travel mode choice and trip chain pattern aroused the attention of academics. This paper examines two distinct structures to identify the decision process of travelers between travel mode choice and trip chain pattern: one structure in which trip chain pattern organization precedes travel mode choice, another structure in which travel mode choice decision precedes the organization of trip chain pattern. To accommodate multi-day behavioral variability and unobserved heterogeneity in personal characteristics ignored by traditional travel surveys, multi-day GPS data collected in Shanghai is employed to estimate these two structures within Nested Logit (NL) model. The Monte Carlo (MC) method simulates the switch of trip-chaining and mode choice under possible Transportation Demand Management (TDM) strategies based on estimation results. The findings of this study are as follows: (1) trip chain pattern decision precedes travel mode choice, which means trip-chaining is organized first and affects travel mode choice; (2) complex trip chain is related to higher automobile dependency, and it is a barrier to the tendency to adopt public transit; (3) people who generally travel by automobiles might switch to public transit when private cars are unavailable, and an increase in household bicycle ownership enhances competition between the bicycle and public transit which leads people to turn to cycling. These findings help implement TDM strategies to develop sustainable transportation systems and optimize the urban trip structure.

Examining the Effects of the Built Environment on Travel Mode Choice across Different Age Groups in Seoul using a Random Forest Method

It is important to analyze factors that influence travel mode choice and to predict individual mode choice because this shapes people’s movement and determines their level of mobility. While there have been studies investigating how built-environment elements are associated with travel mode choice, most efforts have neglected evaluating the heterogeneity of effects that the built environment has on travel mode choice across different age groups. This study aims to examine the effects of the built environment in influencing travel mode choice across age groups in Seoul, South Korea, using a random forest approach. Our random forest model demonstrates what factors are important and how they are associated with the effects on travel mode choice. As a result, the built environment has a greater impact on the subway selection for older adults than other age groups and the random forest approach captures non-linear relationships between certain predictors and travel mode choices. Applying this approach to the travel mode choice analysis, we can examine the heterogeneous effects of the built environment on travel mode choice across different age groups.

Modeling Social Distance and Activity-Travel Decision Similarity to Identify Influential Agents in Social Networks and Geographic Space and Its Application to Travel Mode Choice Analysis

Because humans are social beings, people are members of social networks and interact with other members. As a result of social interaction, people can be influenced by the behavior of others. The present study addresses conformity behavior in activity-travel decisions, implying that in making such decisions people mimic the behavior of other members of their social networks. The presence of conformity behavior in social networks implies that sustainable behavior can be dispersed through networks. Therefore, knowing which people in a network are influential can help make a sustainable transportation policy more effective. In particular, information about the topology of social networks and geographical distribution can help maximize the policy’s spill-over effects in social and geographic spaces. This study suggests a framework to locate influential agents in relation to activity-travel decisions using three procedures: (1) estimating social distance associated with similarity in activity-travel decisions, (2) identifying influential agents by measuring centralities, and (3) exploring the spatial and activity-travel characteristics of the influential agents. The suggested framework is applied using the travel mode choices of people who had recently taken trips by road beside/alongside the Han River in Seoul, South Korea.

A Nested Ensemble Approach with ANNs to Investigate the Effect of Socioeconomic Attributes on Active Commuting of University Students.

Analysis of travel mode choice is vital in policymaking and transportation planning to comprehend and forecast travel demands. Universities resemble major trip attraction hubs, with many students and faculty members living on campus or nearby. This study aims to investigate the effects of socioeconomic characteristics on the travel mode choice of university students. A nested ensemble approach with artificial neural networks (ANNs) was used to model the mode choice behavior. It was found that students generally prefer motorized modes (bus and car). A more detailed analysis revealed that teenage students (aged 17–19 years) had an approximately equal probability of selecting motorized and non-motorized modes. Graduate students revealed a higher tendency to select motorized modes compared with other students. The findings of this study demonstrate the need to promote non-motorized modes of transport among students, which is possible by providing favorable infrastructure for these modes.

Prediction and behavioral analysis of travel mode choice: A comparison of machine learning and logit models

Some recent studies have shown that machine learning can achieve higher predictive accuracy than logit models. However, existing studies rarely examine behavioral outputs (e.g., marginal effects and elasticities) that can be derived from machine-learning models and compare the results with those obtained from logit models. In other words, there has not been a comprehensive comparison between logit models and machine learning that covers both prediction and behavioral analysis, two equally important subjects in travel-behavior study. This paper addresses this gap by examining the key differences in model development, evaluation, and behavioral interpretation between logit and machine-learning models for mode-choice modeling. We empirically evaluate the two approaches using stated-preference survey data. Consistent with the literature, this paper finds that the best-performing machine-learning model, random forest, has significantly higher predictive accuracy than multinomial logit and mixed logit models. The random forest model and the two logit models largely agree on several aspects of the behavioral outputs, including variable importance and the direction of association between independent variables and mode choice. However, we find that the random forest model produces behaviorally unreasonable arc elasticities and marginal effects when these behavioral outputs are computed from a standard approach. After the introduction of some modifications that overcome the limitations of tree-based models, the results are improved to some extent. There appears to be a tradeoff between predictive accuracy and behavioral soundness when choosing between machine learning and logit models in mode-choice modeling.

Applying a random forest method approach to model travel mode choice behavior

The analysis of travel mode choice is important in transportation planning and policy-making in order to understand and forecast travel demands. Research in the field of machine learning has been exploring the use of random forest as a framework within which many traffic and transport problems can be investigated. The random forest (RF) is a powerful method for constructing an ensemble of random decision trees. It de-correlates the decision trees in the ensemble via randomization that leads to an improvement of forecasting and reduces the variance when averaged over the trees. However, the usefulness of RF for travel mode choice behavior remains largely unexplored. This paper proposes a robust random forest method to analyze travel mode choices for examining the prediction capability and model interpretability. Using the travel diary data from Nanjing, China in 2013, enriched with variables on the built environment, the effects of different model parameters on the prediction performance are investigated. The comparison results show that the random forest method performs significantly better in travel mode choice prediction for higher accuracy and less computation cost. In addition, the proposed method estimates the relative importance of explanatory variables and how they relate to mode choices. This is fundamental for a better understanding and effective modeling of people’s travel behavior.

A comparative study of machine learning classifiers for modeling travel mode choice

The analysis of travel mode choice is an important task in transportation planning and policy making in order to understand and predict travel demands. While advances in machine learning have led to numerous powerful classifiers, their usefulness for modeling travel mode choice remains largely unexplored. Using extensive Dutch travel diary data from the years 2010 to 2012, enriched with variables on the built and natural environment as well as on weather conditions, this study compares the predictive performance of seven selected machine learning classifiers for travel mode choice analysis and makes recommendations for model selection. In addition, it addresses the importance of different variables and how they relate to different travel modes. The results show that random forest performs significantly better than any other of the investigated classifiers, including the commonly used multinomial logit model. While trip distance is found to be the most important variable, the importance of the other variables varies with classifiers and travel modes. The importance of the meteorological variables is highest for support vector machine, while temperature is particularly important for predicting bicycle and public transport trips. The results suggest that the analysis of variable importance with respect to the different classifiers and travel modes is essential for a better understanding and effective modeling of people’s travel behavior.

A tour-based analysis of travel mode choice accounting for regional transit service

The aim of this work is to explore the impact of regional transit service on tour-based commuter travel behavior by using the Bayesian hierarchical multinomial logit model, accounting for the spatial heterogeneity of the people living in the same area. With two indicators, accessibility and connectivity measured at the zone level, the regional transit service is captured and then related to the travel mode choice behavior. The sample data are selected from Washington-Baltimore Household Travel Survey in 2007, including all the trips from home to workplace in morning hours in Baltimore city. Traditional multinomial logit model using Bayesian approach is also estimated. A comparison of the two different models shows that ignoring the spatial context can lead to a misspecification of the effects of the regional transit service on travel behavior. The results reveal that improving transit service at regional level can be effective in reducing auto use for commuters after controlling for socio-demographics and travel-related factors. This work provides insights for interpreting tour-based commuter travel behavior by using recently developed methodological approaches. The results of this work will be helpful for engineers, urban planners, and transit operators to decide the needs to improve regional transit service and spatial location efficiently.

Research on Environmental Protection and Environmental Analysis of Travel Mode Choice under the Guidance of Environmental Protection Ideas

Abstract. Green travel has rich connotation, which refers to all kinds of ways that can save energy, reduce pollution, do good to heath and improve efficiency. At the same time, green travel can reduce the citizens’ demand for urban roads, parking facilities, reduce the construction and maintenance costs, reduce the transportation and fuel consumption directly, and reduce the operating costs of the whole city. In addition, green travel can also reduce the use of the car that can reduce air pollution, and help to create livable urban environment. Therefore, the research of green travel mode choice is of great value.The transport industry must foster the mind of sustainable development, and must take account of environmental protection.

Application of radial basis function and generalized regression neural networks in non-linear utility function specification for travel mode choice modelling

Application of soft computational methods, especially artificial neural networks, in examining individual traveller behaviour is not encountered frequently. In most of the relevant cited papers, the feed-forward back propagation neural network (FFBPNN) models or hybrid models of FFBPNNs are proposed. However the feed-forward back propagation algorithm has some drawbacks, which can easily lead the model to develop in an inaccurate direction. Throughout this study, two different algorithms, radial basis function neural network (RBFNN) and generalized regression neural network (GRNN), are employed to propose a new calibration process for travel mode choice analysis in a transportation modelling framework. The neural network methods are not applied directly to calibrate models but are used as a sub-process for alternative non-linear model specification on utility function. Results show both the surpassing of RBFNNs and GRNNs over frequently used FFBPNNs, and the superiority of neural network methods over a conventional statistical model, multivariate linear regression, during mode choice calibrations. Also having experienced the existence of a claim that ANNs can tackle the problem of travel choice modelling as well as, if not better than, the discrete choice approach [D.A. Hensher, T.T. Ton, A comparison of the predictive potential of artificial neural networks and nested logit models for commuter mode choice, Transp. Res., Part E Logist. Trans. Rev. 36 (3) (2000) 155–172], use of such soft computing tools in studying traveller behaviour should be an autonomous part of a calibration process.

ANALYSIS OF NON-HOME-BASED TRIPS IN THE DALLAS-FORT WORTH METROPOLITAN AREA

In the metropolitan area of Dallas-Fort Worth, the two cities have many different public policies in addition to other differences. One purpose of this study was to test the methodology of individual mode choice analysis to determine the feasibility of evaluating the two areas separately in the travel mode choice analysis. The determination that the region is not homogeneous in terms of public policies, population distributions, and employment distributions makes it improper to treat the area in one model. The paper describes preliminary non-home-base individual mode choice models in the form of multinomial logit function for the Dallas segment and the Fort Worth part of the region to assist in further exploration of the different mode characteristics of the two areas.