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.

Spatial Accessibility to Shopping Malls in Nanjing,China:Comparative Analysis with Multiple Transportation Modes

This study attempts to evaluate the rationality of the spatial layout of shopping malls and identify the urban area with poor shopping mall accessibility,as well as to provide a reference and assist decision-making for planning.Using the case of Nanjing,China,this study developed a method to evaluate the accessibility of shopping malls by three transport modes(car traffic,public transit,and bicycle).Specially,we divide the urban space into a regular hexagonal grid and harvest the total travel time from each of 7204 hexagon centroids to each of 129 shopping malls using the Baidu Internet map.The door-to-door travel time approach is used to evaluate all travel stages(walking,waiting,transfer,and transportation)based on travel time calculations.We further divide the shopping malls into two levels(super-regional and regional)based on the Dianping App’s information and develop the indicator of accessibility to shopping malls:the number of shopping malls within tolerance time thresholds and apply the closest facility and cumulative opportunities methods to measure accessibility scores.The results show that the accessibility estimations vary greatly with transport modes.The accessibility of shopping malls presents a concentric ring trend centered on the city center under the car traffic and bicycle modes.And public transit accessibility tends to axially extend due to the topology of bus routes and metro lines.In particular,we observe that the accessibility of shopping malls in Nanjing has an uneven spatial distribution pattern,with high accessibility values in the central urban areas and lots of underserved areas in urban fringe regions.Based on the accessibility measurements,we finally map the poor accessibility area and propose corresponding implications for urban planning.

Review and evaluation of methods in transport mode detection based on GPS tracking data

Mobility data,based on global positioning system(GPS)tracking,have been widely used in many areas,such as analyzing travel patterns,investigating transport safety and efficiency,and evaluating travel impacts.Transport modes are essential factors in understanding mobility within the transport system.Therefore,in this study,a significant number of algorithms were tested for transport mode detection.However,no conclusive recommendations can be drawn regarding which method should be used.The evaluation of the performance of the algorithms was not discussed systematically either in current literature.This paper aims to provide an in-depth review of the methods applied in transport mode detection based on GPS tracking data.The performances of the reviewed methods are then compared and evaluated to provide guidance in choosing algorithms for transport mode detection based on GPS tracking data.The results indicate that the majority of current studies are based on a supervised learning method for transport mode detection.Many of the reviewed methods first require manual dataset labeling,which can produce major drawbacks,such as inefficiency and human errors.It was also found that deep learning approaches have the potential to deal with large amounts of unlabeled raw GPS datasets and increase the accuracy and efficiency of transport mode detection.

Empirical Analysis of Multiple-Criteria Decision-Making (Mcdm) Process for Freight Transportation Mode Selection

In Ghana, freight transport is growing continuously every year due to its location and business processes. However, road transport carries 86% of freight despite its numerous negative impacts. Hence, the government has invested in rail transport, with 70% of its capacity is for freight transport in her busy freight transport corridor (eastern transport regions of Ghana). Thus, awareness of criteria considered when deciding on freight transport becomes vital. Hence, this study aims to improve the understanding of the factors of freight transport mode selection in Ghana from the decision-making process by identifying criteria that affect their decisions on mode transportation. The combination of Fuzzy AHP and Topsis is used to find the weights and suggest suitable alternatives for the decision-makers in the Eastern transport regions of Ghana. The result of this study shows that the criteria to consider when selecting freight transport mode in the regions are prioritized in other of Transport cost (0.6544), transport Time factors (0.2562), reliability, and flexibility (0.0605), and security, Risk of damage and lose factors (0.0287). Additionally, the suitable mode(s) of transportation in the stated corridor is owned truck carrier transport compared to the railroad, road-barge, and Contracted Carrier, thus, in descending order. The results provide organizations to prioritize these factors when deciding to select freight transport mode. At the same time, the government must remove some inputs that result in high transport costs, enforce policies, and invest in the appropriate mode.

FUZZY COMPREHENSIVE EVALUATION OF CONTAINER TRANSPORTATION MODES ALONG THE CHANGJIANG RIVER MAIN LINE AND ITS DELTA AREA

The Changjiang River (Yangtze) is one of the fastest growth areas of container transportation in China. Rail, road and water transportation have competed against each other for container transportation in the Chang-jiang River main line and its delta area. It is of significance to assess these different transportation modes scientifically in order to organize container transportation efficiently in this area and make decision for integral plan and construction of transportation system in this area. This paper outlines application of fuzzy comprehensive evaluation to appraise different modes of typical direction of containers. Twelve assessment indexes were decided. Membership functions were formulated. Evaluation results indicated that road transportation was optimal mode in the Changjiang River delta area, however water transportation was the primary way in the Changjiang River main line.

A comparison of the energy consumption and carbon emissions for different modes of transportation in open-cut coal mines

Transportation accounts for 80% of open-cut coal mine carbon emissions. With regard to the energy con- sumption and carbon emissions of transportation within an open-cut mine, this paper systematically compared the work and energy consumption of a truck and belt conveyor on a theoretical basis, and con- structed a model to calculate the energy consumption of open-cut mine transportation. Life cycle carbon emission factors and power consumption calculation model were established through a Process Analysis- Life Cycle Analysis （PA-LCA）. The following results were obtained： （1） the energy consumption of truck transportation was four to twelve times higher than that of the belt conveyor; （2） the C02 emissions from truck transportation were three to ten times higher than those of the belt conveyor; （3） with the increase in the slope angle for transportation, the ratio of truck to belt conveyor for both energy consumption and carbon emissions gradually decreased; （4） based on 2013 prices in China, the energy cost of transportation using a belt conveyor in open-cut coal mines could save 0.6-2.4 Yuan/（t kin） compared to truck transportation.

Stability of tokamak plasmas with internal transport barriers against high n ideal magnetohydrodynamic ballooning mode

A ballooning mode equation for tokamak plasma, with the toroidicity and the Shafranov shift effects included, is derived for a shift circular flux tokamak configuration. Using this equation, the stability of the plasma configuration with an internal transport barrier （ITB） against the high n （the toroidal mode number） ideal magnetohydrodynamic （MHD） ballooning mode is analysed. It is shown that both the toroidicity and the Shaftanov shift effects are stabilizing. In the ITB region, these effects give rise to a low shear stable channel between the first and the second stability regions. Out of the ITB region towards the plasma edge, the stabilizing effect of the Shaftanov shift causes the unstable zone to be significantly narrowed.

Contribution of Mesoscale Eddies to the Subduction and Transport of North Pacific Eastern Subtropical Mode Water

This study investigates the contribution of mesoscale eddies to the subduction and transport of North Pacific Eastern Subtropical Mode Water(ESTMW)using the high-frequency output of an eddy-resolved ocean model spanning the period 1994–2010.Results show that the subduction induced by mesoscale eddies accounts for about 31%of the total subduction of ESTMW formation.The volume of ESTMW trapped by anticyclonic eddies is slightly larger than that trapped by cyclonic eddies.The ESTMW trapped by all eddies in May reaches up to about 2.8×1013m3,which is approximately 16%of the total ESTMW volume.The eddy-trapped ESTMW moves primarily westward,with its meridional integration at 18°–30°N reaching about 0.17Sv,which is approximately 18%of the total zonal ESTMW transport in this direction,at 140°W.This study highlights the important role of eddies in carrying ESTMW westward over the northeastern Pacific Ocean.

考虑出行偏好的城市群交通方式选择行为影响因素研究

针对城市群旅客出行方式选择行为影响机理不够明晰的问题,开展旅客城市群交通方式选择行为影响因素研究.设计问卷对关中城市群内出行行为进显性偏好(Revealed Preference,RP)调查,并对调查数据的效度、信度进行检验,基于调查所得出行数据,采用梯度提升决策树(Gradient Boosting Decision Tree,GBDT)模型构建了考虑出行偏好的出行方式选择预测模型,并采用可解释机器学习框架SHapley Additive exPlanations(SHAP)模型对预测结果进行解析,所构建模型结合旅客实际决策逻辑将出行方式多元选择行为解构为多次二元选择行为,以增强模型的可解释性.研究结果表明:所构建考虑出行偏好的GBDT预测模型能有效预测旅客城市群出行方式选择行为;私家车与公共交通之间的二元选择行为,会受到小汽车拥有状况,旅客对方便性、安全性、快捷性、舒适性的偏好程度、家庭居住区位、出行距离的显著影响;高速巴士与铁路系统、普通铁路与高铁动车之间的二元选择行为,均会受到出行距离、旅客对舒适性、安全性、快捷性、准时性的偏好程度的显著影响;小汽车拥有状况、家庭居住区位会显著影响高速巴士与铁路系统的选择行为,收入状况会显著影响普通铁路与高铁动车的选择行为.研究成果可为决策者从旅客出行偏好的角度进行更加切实有效的决策提供参考.

基于手机信令HMM轨迹映射的交通方式识别算法

为解决手机信令数据稀疏性限制和重构轨迹特征提取与融合能力不足问题,提出一种出行轨迹重构与多源特征融合的交通方式精准识别算法。构建刻画基站信号传播路径损耗与信号强度的无线信号损耗模型,利用隐马尔可夫模型(hidden markov model,HMM)将手机信令轨迹由基站序列重构为路段节点序列,提出基于无线信号传播隐马尔可夫模型(wireless signal propagation hidden markov model,WP-HMM)的出行轨迹重构方法,用以描述信号强度与距离作用关系。基于出行重构后的轨迹,结合路段类型特征,提出了时空标准化相似性度量算法,以融合导航轨迹特征,并构建了基于随机森林(random forest,RF)的交通方式识别算法。实证分析表明:通过出行轨迹的重构,模型的平均识别精度提高了8%以上,且对新样本具有优异的泛化能力;相较于现有方法,时空标准化相似性度量算法能更准确捕捉轨迹间的移动模式;在不同环境下的轨迹识别中,模型在郊区区域的表现显著高于城区。所提算法在大规模手机信令数据的出行方式识别领域具有重要的应用价值。

基于出行剩余理论的旅游出行方式选择研究

为揭示旅游出行需求主体选择出行服务方式的规律,研究旅游出行特性,提升研判运输通道上旅游客流选择出行服务方式的准确性,构建基于出行剩余理论的休闲旅游出行方式选择模型。从需求独立价值角度刻画旅游出行人群的出行行为,在旅游出行价值特征方面强调出行服务方式的情感价值和游客空间行为价值,在出行剩余理论基础上对旅游出行方式选择进行细化分析。以西安和成都为旅游出行的OD点进行情境模拟算例研究,根据游客对沿途旅游资源的偏好差异将出行需求主体分为3类,分别计算其出行剩余,根据出行剩余最大化原则讨论其最佳出行服务方式。研究结果表明,由于3类游客对特定旅游资源数量、品质情感响应、偏好等存在差异,所对应的最佳出行服务方式有所不同。

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.

深圳市公共住房居民就医可达性——基于互联网地图服务和改进两步移动搜索法

基于互联网地图服务测算人才住房、经济适用房、公共租赁房在步行、公共交通和驾车3种出行方式下到达不同等级医院的通勤时间,通过引入高斯距离衰减函数、设立多级搜索半径、考虑供给和需求方竞争效应并利用实时交通大数据改进两步移动搜索法,对深圳市公共住房居民就医可达性进行多维度评价。研究发现:1)紧急就医情境下15%公共住房点驾车30 min内不可抵达三甲医院,普通就医情境下仅10%公共住房点实现15 min就医目标;2)可达性由老经济特区向非经济特区逐渐衰减;3)人才住房可达性最优,其次是经济适用房,最后是公共租赁房;4)公共交通和步行相比于驾车模式下的可达性空间分异更显著。

项目驱动与合作学习主导的交通类专业教学模式研究

如今,我国的教育事业正面临着全面的发展及改革,在教学过程中,必须强调培养学生的学科理论知识及专业应用能力,强调理论与实践相结合的教学目标,加大学生的学科思维培养力度,并让教学从“教师教,学生学”转变为“教学生如何学”。基于这一背景,项目驱动教学法与合作学习教学法取得了不错的成果。文章讨论了以项目驱动教学法和合作学习教学法主导的交通类专业教学模式,致力于创新教学方法,强调培养高素质、专业化的应用型人才,以便为国家的建设及发展贡献力量。

城市多模式公共交通网络优化及仿真

城市公共交通网络优化对于提高城市出行效率,方便乘客出行具有重要意义。基于Space L建模方法构建城市多模式公共交通网络,定义了网络中节点和弧段阻抗计算方法。以多模式公共交通网络全局效率最大为目标,考虑常规公交线路设计规则为约束,构建了上述问题的数学规划模型。针对该问题的组合爆炸特点,采用了遗传退火算法进行求解。最后选取成都市锦江区所属的公共交通网络进行实例分析,结果表明,上述方法成功地降低公共交通网络节点间的出行阻抗、提升公共交通网络全局效率,而且可以在较短时间内求得满意解。

多式联运运行机制、发展模式及演化趋势——基于SCI、北大核心和CSSCI来源期刊的分析(2013—2023)

为了更好地支撑我国多式联运高质量发展,促进实现《交通强国建设纲要》中提出的2035年发展目标,亟需厘清多式联运的内涵、特征及发展机理。基于CNKI数据库和WOS核心数据库,聚焦2013—2023年,梳理多式联运国内外研究成果,并与行业发展相结合,可以帮助厘清多式联运起因、演化过程、运行机制及发展模式。研究发现:多式联运研究与行业发展相互促进,且与时俱进。文献研究主题经历了从关注“运输组合和体系构建”,转向“经济与环境关系平衡”,再到聚焦“技术革新”的变化。行业发展经历了集装箱推动下的被动发展和追求多样化、经济性和稳定性的主动探索发展。未来我国多式联运发展应以区域经济发展为着力点、以货物集散枢纽为中心、以协调运输方式为重点,在培育联运主体和布局枢纽点的基础上,建设多式联运标准化体系,完善大数据平台和深化“一单制”。

“人-车-桩-路-网”深度耦合下的配电网协同规划与运行优化

电动汽车(EV)作为连接交通电气化和电网清洁化的纽带和桥梁,可实现电力-交通-信息之间的深度耦合,形成电力-交通一体化的规划及运行架构。配电-交通融合系统(DTIS)中,EV充放电行为多时空动态交织、电能流-交通流-信息流深度融合、多利益主体动态博弈等大量不确定性因素使配电网的规划及运行优化的边界都将发生重大转变,但同时也给挖掘利用EV的移动储能特性和提升配电网灵活性带来了契机。为此,在分析“人-车-桩-路-网”深度耦合下配电网的形态演化特征基础上,剖析了新形态下配电网协同规划与运行优化所面临的新挑战,进而针对“人-车-桩-路-网”耦合下的EV灵活性建模、灵活域高效构建及预测、协同规划、运行优化4个方面关键技术展开讨论,并对相关技术问题的研究方向进行了展望。

基于“岗位·技能”能力矩阵的城市轨道专业人才培养模式研究与实践——浙江交通职业技术学院为例

针对城市轨道交通运营管理专业人才培养与城市轨道交通服务员岗位需求脱节,多元化生源专业人才分层分类培养实施不充分的问题,创新理念创立“四能共生六岗共育”专业人才培养模式,构建城市轨道交通服务员“岗位·技能”能力矩阵,开发专业课程体系和实践教学体系,对行业教育专业教学资源整合提供有效思路,同时实现专业人才精准培养,对提升专业人才培养与岗位需求的匹配度有重要指导意义。

基于校企协作的交通运输人才培养模式改革与实践

针对土木工程及交通运输专业人才培养过程中存在的理论与实践联系不紧密、技术更新滞后、缺乏实践性综合素质培养等问题,以产教融合校企协作的理论基础和研究对象,探究了校企合作在交通运输专业人才培养中的应用和优化。提出了适用于当前高等教育和交通运输行业发展的"教育+合作"产教融合模式,对于解决交通运输专业教育体系中的问题具有一定的实践指导意义。应继续深化产教融合校企协作,加强合作机制建设,推动产学研一体化发展,培养更多高素质、适应社会需求的交通运输专业人才。