Discrete Choice Models and Artificial Intelligence Techniques for Predicting the Determinants of Transport Mode Choice--A Systematic Review

Forecasting travel demand requires a grasp of individual decision-making behavior.However,transport mode choice(TMC)is determined by personal and contextual factors that vary from person to person.Numerous characteristics have a substantial impact on travel behavior(TB),which makes it important to take into account while studying transport options.Traditional statistical techniques frequently presume linear correlations,but real-world data rarely follows these presumptions,which may make it harder to grasp the complex interactions.Thorough systematic review was conducted to examine how machine learning(ML)approaches might successfully capture nonlinear correlations that conventional methods may ignore to overcome such challenges.An in-depth analysis of discrete choice models(DCM)and several ML algorithms,datasets,model validation strategies,and tuning techniques employed in previous research is carried out in the present study.Besides,the current review also summarizes DCM and ML models to predict TMC and recognize the determinants of TB in an urban area for different transport modes.The two primary goals of our study are to establish the present conceptual frameworks for the factors influencing the TMC for daily activities and to pinpoint methodological issues and limitations in previous research.With a total of 39 studies,our findings shed important light on the significance of considering factors that influence the TMC.The adjusted kernel algorithms and hyperparameter-optimized ML algorithms outperform the typical ML algorithms.RF(random forest),SVM(support vector machine),ANN(artificial neural network),and interpretable ML algorithms are the most widely used ML algorithms for the prediction of TMC where RF achieved an R2 of 0.95 and SVM achieved an accuracy of 93.18%;however,the adjusted kernel enhanced the accuracy of SVM 99.81%which shows that the interpretable algorithms outperformed the typical algorithms.The sensitivity analysis indicates that the most significant parameters influencing TMC are the age,total trip time,and the number of drivers.

Influence of land use characteristics and trip attributes on commuting mode choice: a case of Nanjing

The effects of socio-demographics, land use characteristics and trip attributes on the commute mode choice are studied with a nested logit （NL） model. Based on the random utility maximum theory, the NL model is formulated. The analysis is carried out in the main area of Nanjing. Direct and cross elasticities are calculated to analyze the effects of travel time and travel cost on the selection of travel mode choice. The results reveal that the non-motorized travel modes are more attractive in the areas with higher housing and employment accessibility and car owners are found to be more likely to commute to work by car. The bus and subway choice probabilities are more sensitive to changes in travel times than to changes in travel costs. In conclusion, a comprehensive public transit system and effective integration of land use and transportation policies help to relieve the traffic congestion levels caused by the increasing urban sprawl.

Investigation on transformation process of trip mode choice for planned special events

This paper aims to provide a decision-making method for the transportation management strategies in guiding the transformation of trip mode choice during planned special events. The Expo 2010 Shanghai is taken as an example, and a structural equation model is employed to analyze the dynamic mechanism of trip mode choice behavior and the effectiveness of the transportation management measures at different stages. Based on the difference between the objective-oriented stated preference （SP） survey results and the objectives, together with the feedback from the previous stage survey, some adjustments on the transportation management measures are made in the next stage of the planning process until the objectives are eventually achieved. The results indicate that the adjustments on transportation management measures at different stages can effectively raise the transit share to 88.6%. Nonlocal visitors are inclined to choose nonstop modes of transportation and the companion attributes have the most significant effects on the trip mode choices of visitors. The research method is proved to be an effective way to support the decision making process of transportation management measures during planned special events in the future.

Joint analysis of urban shopping destination and travel mode choice accounting for potential spatial correlation between alternatives

In recent years,there have been important developments in the joint analysis of the travel behavior based on discrete choice models as well as in the formulation of increasingly flexible closed-form models belonging to the generalized extreme value class.The objective of this work is to describe the simultaneous choice of shopping destination and travel-to-shop mode in downtown area by making use of the cross-nested logit(CNL) structure that allows for potential spatial correlation.The analysis uses data collected in the downtown areas of Maryland-Washington,D.C.region for shopping trips,considering household,individual,land use,and travel-related characteristics.The estimation results show that the dissimilarity parameter in the CNL model is 0.37 and significant at the 95% level,indicating that the alternatives have high spatial correlation for the short shopping distance.The results of analysis reveal detailed significant influences on travel behavior of joint choice shopping destination and travel mode.Moreover,a Monte Carlo simulation for a group of scenarios arising from transportation policies and parking fees in downtown area,was undertaken to examine the impact of a change in car travel cost on the shopping destination and travel mode switching.These findings have important implications for transportation demand management and urban planning.

Tour Level Mode Choice Analysis of Madison Area in Wisconsin

This study is to investigate what factors and how they affect tours (trip chains) behavior. The key issue is the understanding and definition of tour and tour level mode. Also, these definitions should fit for the data. A semi-home based tour definition is stated, and a competing mode based tour mode is defined. Based on the definition, this study used Madison Area Data from National Household Survey to estimate a MNL structured model. It is found that travel distance could be a positive factor for car mode. Meanwhile, the number of trips is also a positive factor for choosing car.

Suburban travel mode choice considering transit accessibility of stops in public transport

To analyze the influence of the transit accessibility of stops on the travel mode choices of suburban residents,the number of the lines passing by the stops within an accessible range of the resident origin and destination(OD)points and the average waiting time are used as the indexes of the transit accessibility of stops.Due to the correlation between travel time and accessible range,the transit accessibility of stops is contrasted as piecewise variables constrained by travel time.Taking the Jimei District of Xiamen,China,as an example,a binary logistic regression model of the suburban travel mode choice is constructed.The results show that it is necessary to construct transit accessibility of stops as piecewise variables.With a higher transit accessibility of stops,more residents will choose public transport.The choice of the travel mode is correlated with family attributes and personal characteristics.Morning and evening peak hours and travel distance have little effect on the choice of travel mode.Compared with the travel in urban areas,residents often chose public transport for travel within the suburbs.This research provides a basis for encouraging public transportation priority policies and decision making for transport planners in the suburbs.

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.

Kriging Geostatistical Methods for Travel Mode Choice: A Spatial Data Analysis to Travel Demand Forecasting

This paper aims to compare the results of two techniques of Kriging (Ordinary Kriging and Indicator Kriging) that are applied to estimate the Private Motorized (PM) travel mode use (car or motorcycle) in several geographical coordinates of non-sampled values of the concerning variable. The data used was from the Origin/Destination and Public Transportation Opinion Survey, carried out in 2007/2008 at S?o Carlos (SP, Brazil). The techniques were applied in the region with 110 sample points (households). Initially, Decision Tree was applied to estimate the probability of mode choice in surveyed households, thus determining the numeric variable to be used in Ordinary Kriging. For application of Indicator Kriging it was used the variable “main travel mode” in a discrete manner, where “1” represented the use of PM travel mode and “0” characterized others travel modes. The results obtained by the two spatial estimation techniques were similar (Kriging maps and cross-validation procedure). However, the Indicator Kriging (KI) obtained the highest number of hit rates. In addition, with the KI it was possible to use the variable in its original form, avoiding error propagation. Finally, it was concluded that spatial statistics was thriving in travel demand forecasting issues, giving rise, for the both Kriging methods, to a travel mode choice surface on a confirmatory way.

Factors Influence Hanoians’ Choice of Non-Motorized Transport Mode to Access Bus Stations

Hanoi’s rapid urbanization has led to a surge in private vehicle ownership, particularly motorcycles, amidst inadequate public transportation infrastructure. Despite government efforts, many still prefer motorized transport, citing mobility and safety concerns, exacerbated by insufficient pedestrian infrastructure. This study examines the motivations behind this reliance on motorized vehicles, particularly motorcycles, in Hanoi. Findings reveal safety and convenience as primary factors driving motorized transport use, especially for accessing bus stations. Economic incentives could promote non-motorized travel and public transport adoption. Policy implications highlight the importance of addressing economic factors and improving access infrastructure to manage motorized vehicle reliance and foster sustainable urban mobility in Hanoi.

Comparison of Travel Mode Choice Between Taxi and Subway Regarding Traveling Convenience

In this study, we investigate travel mode choice behavior between taxi and subway with an emphasis on the influence of traveling convenience. In the first stage, we examine the Origin-Destination(OD) points of Beijing taxi trips and compare these locations with the respective nearest subway station. Statistics reveal several interesting conclusions. First, for approximately 24.89% of all trips, no convenient subway connections exist between the OD pairs. As such, a taxi becomes the only viable choice. Second, for 80.23% of the remaining 75.11%of trips(equivalent to 60.26% of all trips), access distance from either the origin or the destination to the nearest subway station is greater than 500 meters. This phenomenon indicates that walking distance plays an important role in travel mode choice. In the second stage, we examine groups of taxi trips with similar travel distances and travel times to reveal common features. We establish a preference rule in terms of travel distance and travel time.This determines whether an individual driver will take a taxi or the subway, using a pairwise comparison-based preference regression model. Tests indicate that more than 95% of taxi trips can be correctly predicted by this preference rule. This conclusion reveals that traveling convenience dominates the travel model choice between taxi and subway. All these findings shed light on the factors that influence travel mode choice behavior.

Combinatorial Model Involving Stochastic Choices of Destination, Mode and Route

Traffic assignment models are one of the basic tools for the analysis and design of transportation systems. However, the existing models have some defects. Considering the characteristics of Chinese urban mixed traffic and the randomness of transportation information, the author develops a combinatorial model involving stochastic choices of destination, mode and route. Its uniqueness and equivalance are also proved by the optimization theory.

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.

Recent Transition in Transportation Environment in Jakarta Metropolitan Area Over Years

The Jakarta metropolitan area of Indonesia with more than 24 million populations is the capital region of one of the emerging countries.Along with economic development,the number of motorized trips,especially,use of motorcycles has been rapidly increasing.Two surveys that were conducted in 2002 and 2010,Household Travel Survey(HTS)and Commuter Travel Survey(CTS),revealed significant alteration in,for example,transportation pattern,income,mode share,mode choice,and so on in Jakarta metropolitan area.Number of population as well as number of registered vehicle is increasing.Existence of BRT also indicated changes in mode choice before and after the introduction of the BRT system in 2004.The characteristics of these preferences were also identified.

Calibration of a rule-based intelligent network simulation model

This paper is focused on calibration of an intelligent network simulation model （INS1M） with reallife transportation network to analyse the INSIM＇s feasibility in simulating commuters＇ travel choice behaviour under the influence of real-time integrated multimodal traveller information （IMTI）. A transportation network model for the central and western areas of Singapore was simulated in PARAMICS and integrated with INSIM expert system by means of an application programming interface to form the INSIM. Upon calibration, INSIM was able to realistically present complicated scenarios in which real-time IMTI was provided to commuters and the network performance measures being recorded.

Transportation Users’ Attitudes and Choices of Ride-Hailing Services in Two Cities with Different Attributes

The rapid technological developments in the 21st century created new opportunities for shared-use economy applications around the globe. Among other services, Transportation Network Companies (TNCs) like Uber and Lyft emerged in the US as a transportation alternative that offered a higher level of availability, reliability, and convenience than traditional modes. However, TNCs deployment was also blamed for increases in vehicle miles traveled (VMT) in large cities that embraced TNC services early on. Concerns about TNC adoption are also magnified by the current controversy in policy and legislation as to the regulation of TNCs. These new realizations create a need to examine the transportation users’ attitudes and perceptions regarding ride-hailing service, after nearly a decade of service in the Unites States market. In doing so, this paper compares and contrasts results from two recently completed studies aiming at creating links between socio-demographic factors and TNC use. The paper describes the methods employed to collect the data and presents findings from the analysis of 790 users’ responses in the Birmingham, AL and Miami Beach, FL markets. The study documents preferences and attitudes toward TNCs and highlights similarities and differences in travel behaviors related to local considerations. Moreover, the study uses the Least Absolute Shrinkage and Selection Operator (Lasso) method to identify predictors for TNC use based on the users’ responses in Birmingham and Miami Beach case studies. Vehicle availability and waiting time emerged as the only significant predictors for the Birmingham region whereas vehicle ownership, vehicle use, residency, and prior use of transit and TNC where some of the predictors identified for the Miami Beach area. Understanding the characteristics of TNC users and the leading reasons that drive people towards the use of TNCs services is expected to help transportation agencies and TNC providers in their efforts to plan for transportation services that meet customer needs in the future.

Integrated Network Design and Demand Forecast for On-Demand Urban Air Mobility

Urban air mobility(UAM)is an emerging concept proposed in recent years that uses electric vertical takeoff and landing vehicles(eVTOLs).UAM is expected to offer an alternative way of transporting passengers and goods in urban areas with significantly improved mobility by making use of low-altitude airspace.In addition to other essential elements,ground infrastructure of vertiports is needed to transition UAM from concept to operation.This study examines the network design of UAM on-demand service,with a particular focus on the use of integer programming and a solution algorithm to determine the optimal locations of vertiports,user allocation to vertiports,and vertiport access-and egress-mode choices while considering the interactions between vertiport locations and potential UAM travel demand.A case study based on simulated disaggregate travel demand data of the Tampa Bay area in Florida,USA was conducted to demonstrate the effectiveness of the proposed model.Candidate vertiport locations were obtained by analyzing a three-dimensional(3D)geographic information system(GIS)map developed from lidar data of Florida and physical and regulation constraints of eVTOL operations at vertiports.Optimal locations of vertiports were determined to achieve the minimal total generalized cost;however,the modeling structure allows each user to select a better mode between ground transportation and UAM in terms of generalized cost.The outcomes of the case study reveal that although the percentage of trips that switched from ground mode to multimodal UAM was small,users choosing the UAM service benefited from significant time saving.In addition,the impact of different parameter settings on the demand for UAM service was explored from the supply side,and different pricing strategies were tested that might influence potential demand and revenue generation for UAM operators.The combined effects of the number of vertiports and pricing strategies were also analyzed.The findings from this study offer in-depth planning and managerial insights for municipal decision-makers and UAM operators.The conclusion of this paper discusses caveats to the study,ongoing efforts by the authors,and future directions in UAM research.

Analysis of Transportation Users’ Preferences and Attitudes for Identifying Micro-Level Determinants of Transportation Network Companies’ (TNCs) Growth

Over the last decade, the popularity of Transportation Network Companies (TNCs) as a mode of travel has been increasing at a steady pace. This trend highlights the importance of identifying the determinants that influence transportation users to adopt TNCs as a preferred mode choice and the impacts of such preferences on their travel patterns and transportation network operation. This paper reports on a recent study undertaken in Birmingham, AL aiming at understanding and documenting the factors that influence transportation users to select TNCs (such as Uber/Lyft) for completing typical day trips. In doing so, a travel diary questionnaire survey was developed in accordance with the Institute of Transportation Engineers (ITE) Manual on Transportation Engineering Studies using the Qualtrics Research Core platform. The questionnaire was used to survey over 450 transportation users in the Birmingham Metro area. The survey participants provided detailed trip information for a typical 24-hr day along with demographic data and travel preference information. The survey responses provide high-resolution micro-level indicators of travel preferences and behaviors in a TNC-served area, which is a much-needed type of information for researchers and transportation planning agencies.

Microscopic Fuzzy Urban Traffic Simulation with Variable Demand

Some microscopic traffic simulations on urban road network are developed up to now. However, the effect of urban transport policy in the local city is influenced with the complex interaction of automobile traffic and public transport traffic. Particularly, behaviours of vehicles should be described with the fuzziness of the subjective recognition and operation. On the other hand, the trip makers are influenced by various transport policies in terms of mode choice behaviour. The change in mode choice behaviour and number of public transport mode users would eventually affect traffic flow conditions on road network. Modal spilt and traffic conditions of a network are interrelated. Therefore, the present study mainly aims to integrate mode choice model and microscopic traffic simulation model based on fuzzy logic. In the study, the fuzzy logic based mode choice model is proposed. The proposed mode choice model and the existing microscopic traffic simulation model are combined. The developed model has been applied on real urban network to demonstrate the effectiveness of the installation of LRT system. Finally, it is helpful for evaluation of transport policy that the fuzzy logic based microscopic traffic simulation with modal choice model has been constructed.

Hanoi Public TransportmTransformation by Management Using Action Research and Behavior Setting Theory

After the economic reforms in Vietnam, the number of motorbikes surged while public transport lost its passengers. No funds for investment available TRAMOC （Transport Management and Operation Centre）, the Transport Management and Operation Center started the experiment of transforming Hanoi Public Transport by management based on action research, introducing some interventions, which had shown to be effective in Europe. Phase I of the experimental approach was carried out with the smallest company that operated Line 32. The number of daily passengers surged from 1,700 to 8,000. In Phase II, the experiment was extended to the whole net. In 2001, there were 35,000 passengers per day, in 2010, there were 1 million; this is an increase of 3,000%. The result surpassed by far the expectations. The key for understanding the surprising results is the mode choice. 53% of the users are riders by choice; they have access to a car or motorbike. Simulation of the decisions as rational choice based on time needed for trips was proved to be quite accurate. Behavior was analyzed in the frame of behavior setting theory, which brings together urban structure and the design of the transport system. Success with introducing public transport needs a self-reliant leadership, which works with people in their real life situation. An urban transport system is part of the organized behavior of the people, who make use of the technical opportunities offered.

基于地理加权回归模型探索小学生通勤方式选择的区域异质性

Commuting is an important part of primary school students' travel behavior, which has been concerned for a long time. We found that the commute-mode choice behavior of primary school students in the context of regional segmentation shows strong characteristics in space, but has not yet been considered in traditional research. To fill this gap, this study summarizes the commute-mode choices of primary school students with different characteristics based on the Beijing School Commute Survey. And the geographically weighted regression(GWR) model is built to analyze the zonal heterogeneity of the impact of personal characteristics, family factors and school factors on the primary school students' commutemode choices from a low-carbon perspective. The results demonstrate that the possibility of primary school students choosing low-carbon commuting modes is positively correlated with the grade, commuting time, commuting escort type and housing category, but is inversely related with the commuting distance and the distance from the school to the city center. The coefficient estimates of explanatory variables vary across regions. Finally, we put forward policy suggestions regarding promoting the low-carbon commuting structure, such as developing the urban slow traffic system, which serve as a reference for policymakers.