Understanding Of Travel Behavior Research Articles

Correlation of the Socio-Demographic Variables to Travel Behaviour and Mode Choice in Cities of Least Developed Countries- Case Study, Urban Neighbourhoods in Aden, Yemen

This case study focuses on the city of Aden, Yemen, where a large segment of the population relies on the semi-formal public transportation due to various sociodemographic and economic factors. The study specifically investigates the inner urban area of Al Mansoura in Aden. To understand travel behavior and mode choice in this area, the research employs a mixed methodology that combines qualitative and quantitative approaches through a case study design. Primary data about the area of interest were collected through field observations, interviews, questionnaires, GIS mapping, and street audits. In addition, a novel mapping of the semi-formal transportation lines was produced for the first time in the city. Both quantitative and qualitative data were analyzed using statistical analysis methods. The results indicate a correlation between sociodemographic variables and travel behavior and mode choice, particularly in terms of income and gender. Low-income individuals tend to use public transport, while those with higher incomes prefer private vehicles. Additionally, females generally drive less than males and generally have less mobility due to cultural and educational factors; fewer responsibilities outside the home. However, a small number of females who use private vehicles tend to work.

Interpretable Machine Learning for Mode Choice Modeling on Tracking-Based Revealed Preference Data

Mode choice modeling is imperative for predicting and understanding travel behavior. For this purpose, machine learning (ML) models have increasingly been applied to stated preference and traditional self-recorded revealed preference data with promising results, particularly for extreme gradient boosting (XGBoost) and random forest (RF) models. Because of the rise in the use of tracking-based smartphone applications for recording travel behavior, we address the important and unprecedented task of testing these ML models for mode choice modeling on such data. Furthermore, as ML approaches are still criticized for leading to results that are hard to understand, we consider it essential to provide an in-depth interpretability analysis of the best-performing model. Our results show that the XGBoost and RF models far outperform a conventional multinomial logit model, both overall and for each mode. The interpretability analysis using the Shapley additive explanations approach reveals that the XGBoost model can be explained well at the overall and mode level. In addition, we demonstrate how to analyze individual predictions. Lastly, a sensitivity analysis gives insight into the relative importance of different data sources, sample size, and user involvement. We conclude that the XGBoost model performs best, while also being explainable. Insights generated by such models can be used, for instance, to predict mode choice decisions for arbitrary origin–destination pairs to see which impacts infrastructural changes would have on the mode share.

A hybrid method for intercity transport mode identification based on mobility features and sequential relations mined from cellular signaling data

AbstractThe proliferation of mobile phones has generated vast quantities of cellular signaling data (CSD), covering extensive spatial areas and populations. These data, containing spatiotemporal information, can be employed to identify and analyze intercity transport modes, providing valuable insights for understanding travel distribution and behavior. However, CSD are primarily intended for communication purposes and are not directly suitable for transportation research due to issues such as low spatial precision, sparse sampling granularity, and lacking traffic semantic features. This article proposes a Hybrid model for identifying individual intercity transport modes based on CSD. Several multidimensional mobility features are proposed that extract interpretable motion characteristics from CSD. A preliminary transport mode probability judgment is made based on the mobility features. Then, the complete transport mode is confirmed considering the temporal continuity correlation of the entire trace. Experiments confirm the Hybrid model's superior precision in identifying transport modes over baseline models, with an average F1 score of 0.92, maintaining high accuracy across various trajectory lengths. This model would support further studying individual intercity travel behavior patterns, aiding transportation planning and operational management decisions using CSD.

Which factors influence the use of shared and privately-owned e-scooters in the city of Madrid? Implications for urban mobility

Micromobility using fully-electric two-wheeled vehicles is increasing in cities worldwide. E-scooters, whether shared or privately-owned, provide short door-to-door trips by facilitating the first/last mile stage of the journey. They are expected to improve livability in cities by reducing harmful emissions and space occupation. In this respect, understanding travel behavior and usage patterns is essential to regulate them appropriately. The purpose of this study is to determine individuals' sociodemographic variables, mobility-related attributes, and latent constructs influencing e-scooter usage. To that end, an individual-level model is estimated to explain the adoption and frequency of use of both shared and private e-scooters based on survey data. The research takes the city of Madrid as a case study, and contributes to a deeper understanding of the differences in the use of privately-owned and shared e-scooters, with a particular focus on the influence of mobility habits and attitudinal variables. The study is complemented with some insights on shared e-scooter usage at the trip-level, which shows the substitution caused on walking trips, and their limited ability to promote modal shifts from the private car. Finally, the research provides valuable implications for urban dynamics and feedback for policymakers and transport planners.

Cyclists’ perception of streetscape and its influence on route choice: A pilot study with a mixed-methods approach

To encourage behavioural changes that reduce car use, understanding travel behaviour and interventions in infrastructure are necessary. Understanding the route choices of cyclists and their motivation based on their preferences regarding their trip attributes is essential to improve cycling infrastructure and encourage active travel modes such as cycling. This research aims to explore the influence of streetscape design features (SDFs) on cyclists' route choices by developing a mixed-method approach to collect objective and subjective data from 22 volunteers. We used a survey (Maptionnaire) with a virtual reality (VR) and eye-tracking experiment to simulate a bicycle trip in Enschede, The Netherlands. Results showed that despite differences between usual and ideal routes regarding SDFs (such as the presence of vegetation, water bodies, and road intersections), factors such as infrastructure provision and quality have a more significant impact when choosing a route. The novelty of the proposed methodology lies in combining data from the different methods to improve understanding regarding the influence of SDFs in cyclists' route choices and raise awareness among the participants about the influence of SDFs on their route choices. These results may encourage future studies to develop and implement alternative mixed-methods approaches to increase understanding of cyclists' travel behaviour. From a practitioner's perspective, implementing such mixed-method for data collection may increase the efficiency of the process to aid in the development of contextual data-driven interventions that encourage the use of bicycles.

Identifying the Nature of Travel by Different Transport Modes as Consummatory or Instrumental

Attitudes are crucial in understanding people’s travel behavior. In this paper, affective and cognitive components are simultaneously considered, where affective attitude refers to feelings and emotions that are evoked from traveling by particular mode, and the cognitive component of an attitude contains the attributes and beliefs associated with that mode. Based on a mobility survey for the Longitudinal Internet Studies for the Social Sciences (LISS) panel, this study endeavors to identify the relative importance of attitude components on travel behavior related to car, public transport, and bike, based on which the nature of mode-specific travel behavior could be determined. Being confined to the psychosocial sphere, the target mode-specific travel behavior will be defined as instrumental if a comparatively strong impact from cognitive attitude is observed and as consummatory if affective attitude has a larger influence on travel behavior. The identified behavioral nature is further examined across people with diverse characteristics. The dominant role of affective attitude suggests car travel behavior to be highly consummatory, which applies for most groups. Public transport travel is performed as an instrumental behavior basically determined by cognitive attitude, and this outcome considerably varies across population groups. Travel by bike is carried out by all the groups firmly as consummatory, and the negative effect of cognitive attitude on bike travel basically reflects people’s motivation to fulfill social desirability, which leads to a behavioral violation. The analysis offers a further understanding of travel behavior, which might provide useful implications for transportation administration.

Understanding Ride-Hailing Sharing and Matching in Chicago Using Travel Time, Cost, and Choice Models

Ride-hailing data is sparingly available throughout the U.S., which limits researchers’ understanding of the mode. Chicago is one of a few cities that have mandated ride-hailing companies to submit detailed trip data to their local transportation agency. The dataset is one of the few to contain trip-level attributes such as fare, travel time, and trip length. Most research using the Chicago dataset has focused on understanding why people use ride-hailing. This study focuses on why ride-hailing passengers choose shared over private trips and what influences the shared trips to be matched. Trips to/from airports are less likely to be shared. Trips to/from low-income areas are more likely to be shared. Longer shared trips are more likely to be matched, shared trips to/from dense areas are more likely to be matched, and shared trips between areas with a high number of shared trips are more likely to be matched. Matching an additional shared trip with another adds approximately 4 min to a trip. Ride-hailing users’ value of time is found to be $48.23 per hour. Understanding travel behavior is important for all modes of transportation including ride-hailing. The results of this paper can be applied to guide polices aiming to promote more sustainable transportation modes.

DeepTrip: A Deep Learning Model for the Individual Next Trip Prediction With Arbitrary Prediction Times

The increasing availability of travel trajectory data allows for a better understanding of travel behavior. In the individual mobility analysis, the problem of next trip prediction assumes a central role and is beneficial for applications such as personalized services and mobility management. This paper addresses the next trip prediction problem with arbitrary prediction times (the time when the prediction is made). This problem has not been studied adequately in the literature and it is important for applications driven by system events, such as proactive travel recommendations under disruptions or crowding in transport systems. It predicts an individual’s next trips given their historical trip sequences and the prediction time. We formulate the next trip prediction problem as on-board and off-board predictions depending on an individual’s travel status (i.e. on-board/off-board). Using historical/real-time travel trajectories, a DeepTrip model is proposed based on a trip sequence-to-sequence deep learning structure coupled with an attention mechanism. A novel overlapped embedding method is proposed to represent continuous travel attributes capturing simultaneously the categorical and numerical feature information. We also develop a random-sampling training algorithm to learn the impact of the prediction time. The model is validated using trip data in urban rails. The results show that DeepTrip outperforms statistical-based models by more than 10% in terms of accuracy and other deep learning models by 2%-3%. The impact analysis shows that different representations are appropriate for the two prediction cases (on-board/off-board), and the prediction performance does not monotonically improve as the prediction time approaches the next trip.

Understanding Travel Behavior of Electric Car-Sharing Users under Impact of COVID-19

The outbreak of the COVID-19 pandemic has raised concerns about the use of public transport, with a surge in people considering personal car usage. However, owning private cars is costly and wasteful of resources. Electric car-sharing (ECS) is considered a safer and more private mode of transportation compared with public transportation. The COVID-19 pandemic has affected transport on transportation policies and travel willingness. What is the effect of the COVID-19 pandemic on CS travel, especially considering the safety issues during the COVID-19 pandemic? This study analyses the differences in the travel characteristics of private car owners and nonowners while using CS under the influence of the COVID-19 pandemic. Quantitative analysis during four months before and four months after the outbreak of the COVID-19 pandemic is conducted based on CS order data in Lanzhou, China. It was found that the number of CS orders fell by 55.8% during the COVID-19 pandemic. Travel behavior during the pandemic is different from that before the outbreak of the pandemic. Additionally, both private car owners and nonowners use CS while having differences in travel characteristics. Based on the results, business suggestions are introduced on the distribution of vehicles to help improve the profit of CS operators.

Understanding Travel Behavior Change during COVID-19 Using Spatio-temporal Cluster Analysis

Understanding Travel Behavior Change during COVID-19 Using Spatio-temporal Cluster Analysis

Modelling of Active and Latent Attributes Based on Traveler Perspectives: Case of Port City of Douala

A growing stream of study stresses the relevance of subjective elements in understanding the hierarchy of preferences that underpin individual travel behavior. The purpose of this study is to evaluate the impact of various factors on mode choice. To achieve this, a multinomial logit model (MNL) was used to analyze the relationships between mode choice and three classes of attributes; Combined Active and Latent, Active only and Latent only attributes. The data used are derived from surveys in the port city of Douala, Cameroon as a case study. Results stipulated that, the combined attributes model performed better than both active only attributes and latent only attributes models. Likewise, latent only attributes model performed better than active only attributes model. The advantage of modelling all three groups is for better selection of the most relevant attributes, and this is very relevant in understanding travel behavior of individuals and mode choice decisions.

Emerging trends in household travel survey programs

Transportation planners use household travel surveys to understand travel behavior, whether to develop forecasts of travel activity using travel demand or simulation models, to analyze personal motivations that drive the decision to travel, to identify users of existing transportation infrastructure and services, or to determine responsiveness to available or future travel options. Large urban area transportation planning organizations are faced with making decisions on their next household travel surveying effort to meet growing data needs. The New York Metropolitan Transportation Planning Council (NYMTC) has focused attention on surveying options, including conducting a pilot study to evaluate the ability to collect household travel data using a smartphone app. This research reviews current travel surveying strategies aimed at improving timeliness and accuracy, while reducing participant burden (e.g., using smartphone technologies). It also includes a vision for a long-term data program, facilitated by the establishment of a regional Community of Practice (CoP) to support multi-agency data collection efforts.

A supervised machine learning model for imputing missing boarding stops in smart card data.

Public transport has become an essential part of urban existence with increased population densities and environmental awareness. Large quantities of data are currently generated, allowing for more robust methods to understand travel behavior by harvesting smart card usage. However, public transport datasets suffer from data integrity problems; boarding stop information may be missing due to imperfect acquirement processes or inadequate reporting. This study introduces a supervised machine learning method to impute missing boarding stops based on ordinal classification using GTFS timetable, smart card, and geospatial datasets. A new metric, Pareto Accuracy, is suggested to evaluate algorithms where classes have an ordinal nature. The results are based on a case study in the city of Beer Sheva, Israel, consisting of one month of smart card data. We show that our proposed method is robust to irregular travelers and significantly outperforms well-known imputation methods without the need to mine any additional datasets. The data validation from another Israeli city using transfer learning shows the presented model is general and context-free. The implications for transportation planning and travel behavior research are further discussed.

Understanding Travel Behavior and Sustainability of Current Transportation System for Older Adults in Malaysia: A Scoping Review

Rapid transportation development may be welcomed by many, but older adults might find it difficult to keep up with their transportation uses and remain active. This study reviewed published articles on the travel behavior of older adults in Malaysia and associated transportation determinants to explore how sustainable the transportation system is for this vulnerable cohort. The authors searched four databases: PubMed, Scopus, ProQuest, and EBSCOhost. Inclusion criteria were older respondents, living in a community in Malaysia, addressing any travel behavior characteristics, and being written in English. Review papers, letters, book citations, comments, editorials, and experimental and animal studies are excluded from this study. A total of seven studies were included in this review extending from 2007 to 2020. The result showed that the transportation use of older adults has shifted from relying on public transport to driving their own vehicles to move around. According to the findings of this study, besides personal and health factors, the transport use of older adults is affected mainly by cost, public transport availability, road traffic and safety, the complexity of the transportation system, distance to public transit, availability of parking space, as well as road conditions and signage. It is concluded that an effective strategy to improve the transportation system is needed to prevent the unmet travel needs of older adults in Malaysia.

Understanding travel behavior adjustment under COVID-19

The outbreak and spreading of the COVID-19 pandemic have had a significant impact on transportation system. By analyzing the impact of the pandemic on the transportation system, the impact of the pandemic on the social economy can be reflected to a certain extent, and the effect of anti-pandemic policy implementation can also be evaluated. In addition, the analysis results are expected to provide support for policy optimization. Currently, most of the relevant studies analyze the impact of the pandemic on the overall transportation system from the macro perspective, while few studies quantitatively analyze the impact of the pandemic on individual spatiotemporal travel behavior. Based on the license plate recognition (LPR) data, this paper analyzes the spatiotemporal travel patterns of travelers in each stage of the pandemic progress, quantifies the change of travelers' spatiotemporal behaviors, and analyzes the adjustment of travelers' behaviors under the influence of the pandemic. There are three different behavior adjustment strategies under the influence of the pandemic, and the behavior adjustment is related to the individual's past travel habits. The paper quantitatively assesses the impact of the COVID-19 pandemic on individual travel behavior. And the method proposed in this paper can be used to quantitatively assess the impact of any long-term emergency on individual micro travel behavior.

Assessing the role of geographic context in transportation mode detection from GPS data

The increasing availability of health monitoring devices and smartphones has created an opportunity for researchers to access high-resolution (spatial and temporal) mobility data for understanding travel behavior in cities. Although information from GPS data has been used in several studies to detect transportation modes, there is a research gap in understanding the role of geographic context in transportation mode detection. Integrating the geography in which mobility occurs, provides context clues that may allow models predicting transportation modes to be more generalizable. Our goals are first, to develop a data-driven modeling framework for transportation mode detection using GPS mobility data along with geographic context, and second, to assess how model accuracy and generalizability varies upon adding geographic context. To this extent we extracted features from raw GPS mobility data (speed, altitude, turning angle and net displacement) and integrated context in the form of geographic features to classify active (i.e. walk/bike), public (i.e. bus/train), and private (i.e. car) transportation modes in three different Canadian cities - Montreal, St. Johns, and Vancouver. To assess the role of integrating geographic context in mode detection, we adopted two different modeling approaches – generalized and context-specific, and compared results using random forests, extreme gradient boost, and multilayer perceptron classifiers. Our results indicate that for context-specific models the highest classification accuracy improved by 64% for Montreal, by 74% for St. John's and by 77% for Vancouver compared to the generalized model. We also found that the multilayer perceptron (96%) achieved the highest classification accuracy upon adding contextual variables compared to random forests (94.6%) and extreme gradient boost (93.3%) classifier. Our study highlights that adding contextual information specific to a city's geography can improve the predictive accuracy of transportation mode detection models, however, in case of limited knowledge about the geographic setting of a study area, a generalized model combining GPS data from several cities may still be useful for predicting modes from trip data.

What lies beyond the built environment? Exploring “walkability” across the Detroit region

Despite a long history of research on the influence of the built environment on travel, studies on urban form and pedestrian activity in neighborhoods characterized by rapid decline, as evident across U.S. Midwest cities, remain under-represented in the literature. Moreover, detailed exploration of travel inequities experienced by the socioeconomically disadvantaged is even rare. In examining travel, this research measures precise variations in the built environment—with the use of Road Network Buffers—across Detroit (Michigan) region neighborhoods, including in those experiencing severe disinvestment. This study reconfirms that compact urban form promotes non-automobile travel, and reaffirms the importance of a more balanced residential, retail and commercial land use mix in encouraging pedestrian activity, although it also identifies caveats for those neighborhoods experiencing decline. The research also contributes to expanding our understanding of travel behaviors within the context of amenity disparities and abandonment in neighborhoods experiencing severe disinvestment and extreme income divergence. Intersecting the sociodemographic dimensions and the built environment allows a deeper understanding of much disregarded nuance of travel amongst lower-income, racial minorities in highly segregated urban neighborhoods.

Using weighted multilayer networks to uncover scaling of public transport system

The public transport system is considered as one of the most important subsystems in metropolises for achieving sustainability objectives by mediating resources and travel demand. Representing the various urban transport networks is crucial in understanding travel behavior and the function of the transport system. However, previous studies have ignored the coupling relationships between multi-mode transport networks and travel flows. To address this problem, we constructed a multilayer network to illustrate two modes of transport (bus and metro) by assigning weights of travel flow and efficiency. We explored the scaling of the public transport system to validate the multilayer network and offered new visions for transportation improvements by considering population. The proposed methodology was demonstrated by using public transport datasets of Shanghai, China. For both the bus network and multilayer network, the scaling of node degree versus Population were explored at 1 km * 1 km urban cells. The results suggested that in the multilayer network, the scaling relations between node degree and population can provide valuable insights into quantifying the integration between the public transport system and urban land use, which will benefit sustainable improvements to cities.

How to Promote New Metro Use Among Older People? Understanding Travel Behaviour Change by Transtheoretical Model of Change and Socio-Ecological Model

How to Promote New Metro Use Among Older People? Understanding Travel Behaviour Change by Transtheoretical Model of Change and Socio-Ecological Model

Travel Mode Choice Modeling: Predictive Efficacy between Machine Learning Models and Discrete Choice Model

Background: A complex travel behaviour among users is intertwined with many factors. Traditionally, the exploration in travel mode choice modeling has been dominated by the Discrete Choice model, nonetheless, owing to the advancement in computational techniques, machine learning has gained traction in understanding travel behavior. Aim: This study aims at predicting users’ travel model choice by means of machine learning models against a conventional Discrete Choice Model, i.e., Binary Logistic Regression. Objective: To investigate the comparison between machine learning models, namely Neural Network, Random Forest, Decision Tree, and Support Vector Machine against the Discrete Choice Model (Binary Logistic Regression) in the prediction of travel mode choice amongst Kuantan City. Methodology: The dataset was collected in Kuantan City, Malaysia, through the Revealed/Stated Preferences (RP/SP) Survey. The data collected was split into a ratio of 80:20 for training and testing before evaluating them between the aforesaid models. The hyperparameters of the models were set to default. The performance of the models is evaluated based on classification accuracy. Results: It was shown in the present study that the Neural Network Model is able to attain a higher prediction accuracy as compared to Binary Logistic Regression (Discrete Choice Model) in classifying mode choice of Kuantan users either to choose public transport or private vehicles as daily transportation. Feature importance technique is crucial for identifying the significant features in modelling travel mode choice. It is demonstrated that the Neural Network Model can yield exceptional classification of mode choice up to 73.4% and 72.4% of training and testing data, respectively, by considering the features identified via the feature importance technique, suggesting the viability of the proposed technique in supporting an informed decision. Conclusion: The findings highlight the strengths and limitations of the Machine Learning Technique as well as the Discrete Choice Model in modeling travel mode choice. It was shown that Machine Learning models have the capability to provide better prediction that could assist the urban transportation planning among policymakers. Meanwhile, it could be also demonstrated that the Discrete Choice Model (Binary Logistic Regression) is helpful in getting a better understanding in expressing the inference relationship between variables for improvising the future transportation system.