An empirical study on travel demand management modeling based on discrete choice method

In view of the problem that the requirements of travel demand management and traffic policy-sensitivity are ignored during the establishment process of the travel demand forecasting model, a discrete-choice-based travel demand forecasting model is proposed to demonstrate its applicability to travel demand management. A car-bus discrete choice model is established, including three variables, i. e,, individual socioeconomic characteristics, time, and cost, and the traffic policy-sensitivity is evaluated through two kinds of traffic policies： parking charges and bus priorities. The empirical results show that travel choice is insensitive to the policy of parking charges as 88. 41% of the travelers are insensitive to parking charges; travel choice is, however, sensitive to the policy of bus priorities as 67.70% of the car travelers and 77.02% of the bus travelers are sensitive to bus priorities. The discrete-choice-based travel demand forecasting model is quite policy-sensitive and also has a good adaptability for travel demand management when meeting the basic functions of the demand forecasting model.

Big Data-Driven Residents’ Travel Mode Choice Choice: A Research Overview

The research on residents'travel mode choice mainly studies how traffic flows are shared by different traffic modes,which is the prerequisite for the government to establish transportation planning and policy.Traditional methods based on survey or small data sources are difficult to accurately describe,explain and verify residents'travel mode choice behavior.Recently,thanks to upgrades of urban infrastructures,many real-time location-tracking devices become available.These devices generate massive real-time data,which provides new opportunities to analyze and explain resident travel mode choice behavior more accurately and more comprehensively.This paper surveys the current research status of big data-driven residents'travel mode choice from three aspects:residents'travel mode identification,acquisition of travel mode influencing factors,and travel mode choice model construction.Finally,the limitations of current research and directions of future research are discussed.

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.

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.

Island Holidays Remain First Choice during Spring Festival Overseas Travel

The Chinese New Year is just around the corner.Data released by a number of travel agencies show that the Spring Festival outbound travel market is booming.The number of tickets booked have increased by 32 percent year on year,and the prices have also increased by 10 percent.In addition,data from travel agency platforms show that economy-class air tickets for some popular travel destinations during the Spring Festival period have been sold out,and up to 65 percent fares can be saved by returning home via transit.

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.

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.

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.

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.

The Sensitivity of Model Results to Specification of Network-Based Level of Service Attributes: An Application of a Mixed Logit Model to Trave Mode Choice

The need for travel demand models is growing worldwide. Obtaining reasonably accurate level of service (LOS) attributes of different travel modes such as travel time and cost representing the performance of transportation system is not a trivial task, especially in growing cities of developing countries. This study investigates the sensitivity of results of a travel mode choice model to different specifications of network-based LOS attributes using a mixed logit model. The study also looks at the possibilities of correcting some of the inaccuracies in network-based LOS attributes. Further, the study also explores the effects of different specifications of LOS data on implied values of time and aggregation forecasting. The findings indicate that the implied values of time are very sensitive to specification of data and model implying that utmost care must be taken if the purpose of the model is to estimate values of time. Models estimated on all specifications of LOS-data perform well in prediction, likely suggesting that the extra expense on developing a more detailed and accurate network models so as to derive more precise LOS attributes is unnecessary for impact analyses of some policies.

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.

基于机器学习的中型城市居民出行方式选择行为研究

为探索中型城市居民出行特征以及不同因素对出行方式选择行为的影响机制,本文以中国某中型城市居民出行数据为例,综合考虑传统离散选择模型和机器学习模型在预测精度和建模合理性上的优劣,以及机器学习模型超参数求解算法的特点和效率,引入变异程序,提出粒子群优化随机森林的中型城市居民出行方式选择预测模型,采用预测准确率、出行方式比例预测绝对误差和期望模拟误差这3项性能指标,量化对比粒子群优化随机森林模型与多种机器学习模型和多项Logit模型统计学上的预测性能差异,利用SHAP(SHapley Additive exPlanation)模型深入分析个人社会经济属性、出行属性及出行方式属性等相关因素与居民出行方式选择之间的非线性关系。结果表明:粒子群优化随机森林模型整体平均预测准确率最高,为0.856,出行方式比例预测平均绝对误差和期望模拟平均误差最低,分别为0.062和0.306,模型间指标差异在统计学检验下显著;距离对不同出行方式选择的影响最显著,步行和私家车出行对距离敏感性更高,不同距离下,两者选择概率变化超过35%;30岁以下群体不同出行方式选择概率差距大于其他年龄段;性别、是否拥有私家车或公交IC卡等因素显著改变公交车和私家车的选择概率。

学生通学出行的家长接送方式的选择

研究家长接送方式选择的影响因素,对于早晚高峰交通出行政策的制定具有重要意义.考虑家长、学生的个人属性与家庭属性,以及后续行程目的、生理成本与延误时间等出行属性因素,基于多项logit(multinomial logit,MNL)模型分析对于家长接送学生交通方式选择的影响因素,并通过中国海宁市居民出行数据进行验证.研究结果表明,家长年龄越大,选择步行接送的可能性越大;学生性别对于家长接送方式的选择没有显著影响;家长性别和学生年龄对接送方式具有显著影响,其中,女性接送者更偏向于选择非机动车接送,学生年龄越小,家长更偏向于选择非机动车接送;后续行程目的为上班的家长更偏向于选择机动车接送;小汽车接送者的接送时间相对较长,但该接送方式承担的生理成本和延误时间相对较少;电动车接送者承担的生理成本和时间成本都较低.依据研究结果,从家庭、学校和交通管制等维度对学生通学出行提出相关改善建议,能够为相关部门从学生通学的角度制定交通规划管理政策、方案提供指导.

不确定环境下收费与信息对路径选择行为影响的实验研究

在不确定环境下考虑信息发布与拥挤收费两种措施,基于交通网络均衡,推导了两路径简单路网的最优收费模型,并推广至一般路网。基于两路径路网设计逐日路径选择行为实验,分析了两种措施对路径选择行为的影响。结果表明:完美信息与收费的实施均能减少流量波动,单独实施收费的效果最佳,但只有两种措施相结合时,路网流量趋于用户均衡的趋势最稳定;完美信息会增加路径切换行为,而收费可有效抑制大幅的路径切换;无收费时路径切换往往会造成出行成本增加,而收费时则相反;收费与信息结合时的出行时间比两种措施单独实施时小。

A Constrained Time-Dependent K Shortest Paths Algorithm Addressing Overlap and Travel Time Deviation

Theoretical research often assumes all users arc homogeneous in their route choice decision and will always pick the route with the shortest travel cost,which is not necessarily the case in reality.This paper documents the research effort in developing a Constrained Time-Dependent K Shortest Paths Algorithm inorder to find K Shortest Paths between two given locations.The goal of this research is to provide sound route options to travelers in order to assist their route choice decision process,during which the overlap and travel time deviation issues between the K paths will be considered.The proposed algorithm balancing overlap and travel time deviation is developed in this research.A numerical analysis is conducted on the Tucson 1-10 network,the outcome of the case study shows that our proposed algorithm is able to find different shortest paths with a reasonable degree of similarity and close travel time,which indicates that the result of the proposed algorithm is satisfactory.

基于出行选择的旅客联程运输服务定价

在多模式运输竞争条件下,将旅客联程运输看作一个由多个任意运输方式联合提供服务的独立运营商参与市场竞争,并通过设立旅客满意度参数量化联程运输特有属性对旅客出行选择的影响,构建同时考虑旅客出行选择和运营商收益的“一票制”联运双层定价模型。针对下层模型中旅客出行选择参数标定需要大量数据,而联程运输处于初步发展阶段,存在缺乏相关数据的现实矛盾,通过运用层次分析法对相关因素的重要性程度进行标定。针对双层模型求解NP难问题,采用灵敏度分析法对模型求解过程进行简化。并以空铁联运为例对算法的有效性进行验证,结果表明:该定价模型可提升通道内总客流量,促进旅客出行,比补贴式定价有更强的可操作性和可持续性。

考虑空间异质性的短距离上学方式选择机理

短距离出行是学生日常出行的重要组成部分,合理引导短距离上学群体交通方式选择对于促进学生健康发展和缓解高峰期间道路交通拥堵具有重要意义.本研究以中国南京市为例,利用贝叶斯分类法识别出南京市学生的短距离出行阈值为2.7 km,在此基础上,分别构建多项logit(multinomial logit,MNL)模型与地理加权多项logit(geographically weighted multinominal logit,GWMNL)模型,探讨个人属性、出行特征、家庭特征及建成环境对短距离学生群体上学方式选择的影响及其空间异质性.结果表明,相比MNL模型,GWMNL模型具有更好的拟合度和解释能力,说明学生上学交通方式选择行为因居住位置不同存在明显差异.与居住在学校附近的低龄学生相比,核心区与近郊区较短出行距离的高龄学生更倾向于乘坐小汽车上学,而远郊区(六合区和江宁区)的高龄学生更倾向于选择积极出行(步行和自行车)和电动自行车上学.小汽车数量对学生选择积极出行、电动自行车及公共交通上学均有消极影响,且这种消极影响从市中心向外围区域逐渐增强.最近公交站距离对居住在核心区与近郊区的学生选择公共交通具有明显促进作用,而对部分远郊地区的学生选择公共交通具有抑制作用,且在南京市的北部和东部地区尤为明显.研究结果可为不同区域学生群体短距离积极出行引导策略的制定提供参考.

拥挤信息下基于Logit模型的公共交通 方式选择行为研究

人们对出行方式的舒适性要求越来越高,出行信息能为出行者提供有效帮助。采用正交试验对公共交通方式选择特性变量进行情景组合设计,并结合公共交通出行特征进行问卷调查设计,对提供拥挤信息条件下出行者对公共交通方式选择意愿进行调查,据此建立公共交通方式选择Logit模型。结果表明,拥挤信息对公共交通方式选择有显著影响,对公交出行选择影响较大。

考虑心理偏好的枢纽抵站旅客接续出行方式选择模型

为掌握枢纽抵站旅客的出行方式选择特征,解决接续运输运力配置协同优化与效率提升问题,基于高铁枢纽接续出行问卷调查数据,引入上次接续属性、接续方式主观重要度、枢纽服务满意度、接续出行选择倾向特征等潜在变量因素,构建考虑心理倾向的结构方程模型(Structural Equation Model,SEM)和抵站旅客接续出行方式选择多项Logit(Multinomial Logit,MNL)模型相融合的SEM-MNL模型,定量计算枢纽抵站旅客接续出行分方式选择效用函数,预测不同时段旅客接续出行方式选择概率,并对比分析SEM-MNL模型与MNL模型命中率.研究结果表明:引入心理倾向潜在变量后,模型的整体命中率提升了4.6%;对枢纽环境服务满意度越高、接续方式服务重视程度越高、上次出行的时间和距离更短且使用公共交通的出行者,更倾向于选择公共交通方式.通过方式选择模型预测分方式的接续出行需求,开展对外客运枢纽接续运输保障和多模式运力的协调调度,对于实现枢纽接续客流与运力资源的供需平衡,继而提升接续服务质量具有重要意义.

考虑低碳出行意愿的地铁公交接驳满意度分析

现如今,城市地铁建设规模日益增大,公交作为最常见的接驳方式,接驳满意度直接影响着居民的出行体验。文章通过问卷调查分析城市居民低碳出行的意愿和对地铁与公交接驳的满意度,在处理问卷数据后,对量表进行信效度检验,并对变量进行相关性分析。结果表明:绝大部分居民倾向于使用低排放的交通方式出行,当小汽车拥有数量越多,居民对当前低碳出行的接受意愿和环境满意度、地铁公交接驳的满意度、接驳的需求程度和优化意愿均有所降低。