Investigating preference heterogeneity in Value of Time (VOT) and Value of Reliability (VOR) estimation for managed lanes

This paper presents an empirical study in investigating user heterogeneity of Value of Time (VOT) and Value of Reliability (VOR). Combined Revealed Preference (RP) and Stated Preference (SP) data were used to understand traveler choice behavior regarding the usage of managed lanes (MLs). The data were obtained from the South Florida Expressway Stated Preference Survey, which focused on automobile drivers who had traveled on the I-75, I-95, or SR 826 corridors in South Florida. Mixed logit modeling was applied and indicated an average value of $13.55 per hour for VOT and $16.13 per hour for VOR. Potential sources of heterogeneity in user sensitivities to time, reliability, and cost were identified and quantified by adding interaction effects of the variables in the mixed logit model. The findings indicated that various socioeconomic demographic characteristics and trip attributes contributed to the variations in VOT and VOR at different magnitudes. The results of this study contribute to a better understanding on what attributes lead to higher or lower VOT and VOR and to what extent. These findings can be incorporated into the demand forecasting process and lead to better estimates and enhanced analytical capabilities in various applications, such as toll feasibility studies, pricing strategy and policy evaluations, and impact analysis.     

考虑决策过程与潜在异质性的居民通勤选择行为研究

传统研究对居民通勤决策过程的动态性及微观心理偏好关注不足，为此利用潜在类别模型表征居民通勤决策的潜在异质性，从动态决策角度出发，构建可以体现偏好动态演进过程的决策场理论模型。该模型对不同潜在类别设置差异化的属性注意力权重，表征不同子市场用户动态偏好的差异性和相同子市场用户偏好似而不同的特征，同时实现用户分类和动态决策过程分析，改进传统决策场理论对个体偏好异质性表征不足的缺陷。对成都市轨道交通车站附近居民进行实证研究，结果表明，通勤居民可以细分为“商务需求型”“追求效率型”“经济环保型”“保守型”这4类，各类别间的备选方案初始偏好、属性关注程度均呈现显著差异。通过Matlab仿真实现对个体决策结果、微观偏好进化过程及非理性效应的预测和分析，验证了本文方法的有效性。     

公交驾驶员违规类型同交通事故间的关联分析

公交车驾驶员违规行为是引起交通事故的重要原因之一,以往文献在研究驾驶员违规行为与事故频率之间的关系时,未能深入探究违规行为类型差异及其异质性。为了进一步揭示不 同违规行为的差异化影响并为行为管控措施提供依据,利用某市2019—2020年4532起公交违规及事故数据,将驾驶员事故频率作为研究对象,将17类违规行为及人口统计学因素作为解释变量,综合考虑数据特征及异质性分析需求,构建考虑均值与方差异质性的随机参数零膨胀泊松模型。模型分析结果表明：不同类型的违规行为对于驾驶员事故频率影响存在明显区别,当驾驶员同时存在若干特定违规行为时,事故频率明显高于其他驾驶员。具体包括：未走公交专用道等行 为次数越多,则该驾驶员事故频率越高;未系安全带、未礼让斑马线次数和及时更换失效驾照等行为的影响具有随机特征,其作用效果具有随机波动的属性;未礼让斑马线行为影响参数的均值和方差受到其他变量的影响,即当驾驶员未礼让斑马线次数和越线行驶次数均较多时,期望事故率愈高。     

基于多源异构和XGBOOST模型的销量预测

随着中国经济的快速发展,中国汽车市场已经发展成为世界第一大汽车消费市场和全球最大的消费潜力市场3面对规模越来越大的市场,准确预测铕量是汽车产生面临的重要课题。本文在主成分分析的技术之上探讨了多源异质性大数据和XGBOOST算法在汽车销量预测模型中的应用首先选取一些社会经济结构变量、相关政策以及某汽车企业汽车销量为样本数据;其次为了去除多重共线性问题利用主成分分析分析出权重占比累积超过90%的样本特征;再次利用多维度控制变量法确定了XGBOOST糢型的最佳参數组合;最后利用训练好的模型对验证集进行测试,结果表明,多个月的预测销量与实际销量之间的平均准确率为88.52%,平均差异仅为11.48%。这为企业预测汽车销量提供参考.     

基于 K-means 的北京地铁路网重要度聚类分析

以图论为基础,以北京地铁为研究对象,结合地铁运营客流时空分布的特点, 构建北京地铁有向加权路网模型;采用 K-means 聚类分析方法,根据地铁路网中车站和区 间的两个基本的物理拓扑属性（度、介数）,以及客运量对其进行分类,确定关键车站和区 间.其中,度反映的是节点的局部聚集能力,介数反映的是节点和边对全局的影响能力,而 客运量则反映了不同时间段节点和边在运输中的重要性.实证分析表明,该方法可以从系 统网络的角度动态辨识系统中的关键车站和区间.     

考虑异质出行者的随机瓶颈模型

研究早高峰期内通勤者由生活区开车通过高速公路到达工作区的交通行为.假 设出行者是异质的,其时间价值（VOT）按照递增的顺序排列,并假设高速公路上瓶颈的 通行能力在某一区间内随机变化,基于经典瓶颈模型对出行者的均衡出发时间选择行为 进行解析求解,给出了模型的均衡性质和个人出行总成本.结果显示,随着瓶颈通行能力 随机性的增大,出行者的期望等价出行时间和高峰期长度增加.当瓶颈通行能力的随机性 降低时,个体均衡出行成本下降,时间价值越大的出行者,其成本降低的收益越大.算例结 果验证了理论分析结论.     

一种基于节点异质性降低跳图维护代价的方法

Skip Graphs提供了一种新的P2P查找算法,但是其系统查询和维护的消息流量巨大,限制了其应用.本文通过构造节点异质性模型,充分考虑节点异质性和节点负载的关系,提出新的Skip Graphs＋＋算法,有效降低系统的维护代价10%～30%,并从理论和仿真两方面进行证明.     

Morning commute problem considering route choice, user heterogeneity and alternative system optima

This paper extends the bottleneck model to study congestion behavior of morning commute and its implications to transportation economics. The proposed model considers simultaneous route and departure time choices of heterogenous users who are distinguished by their valuation of travel time and punctual arrival. Moreover, two dynamic system optima are considered: one minimizes system cost in the unit of monetary value (i.e., the conventional system optimum, or SO) and the other minimizes system cost in the unit of travel time (i.e., the time-based SO, or TSO). Analytical solutions of no-toll equilibrium, SO and TSO are provided and the welfare effects of the corresponding dynamic congestion pricing options are examined, with and without route choice. The analyses suggest that TSO provides a Pareto-improving solution to the social inequity issue associated with SO. Although a TSO toll is generally discriminatory, anonymous TSO tolls do exist under certain circumstances. Unlike in the case with homogenous users, an SO toll generally alters users’ route choices by tolling the poorer users off the more desirable road, which worsens social inequity. Numerical examples are presented to verify analytical results.     

Multilevel analysis of daily time use and time allocation to activity types accounting for complex covariance structures using correlated random effects

In this paper multilevel analysis is used to study individual choices of time allocation to maintenance, subsistence, leisure, and travel time exploiting the nested data hierarchy of households, persons, and occasions of measurement. The multilevel models in this paper examine the joint and multivariate correlation structure of four dependent variables in a cross-sectional and longitudinal way. In this way, observed and unobserved heterogeneity are estimated using random effects at the household, person, and temporal levels. In addition, random coefficients associated with explanatory variables are also estimated and correlated with these random effects. Using the wide spectrum of options offered by multilevel models to account for individual and group heterogeneity, complex interdependencies among individuals within their households, within themselves over time, and within themselves but across different indicators of behavior, are analyzed. Findings in this analysis include large variance contribution by each level considered, clear evidence of non-linear dynamic behavior in time-allocation, different trajectories of change in time allocation for each of the four dependent variables used, and lack of symmetry in change over time characterized by different trajectories in the longitudinal evolution of each dependent variable. In addition, the multivariate correlation structure among the four dependent variables is different at each of the three levels of analysis.     

出行方式选择行为的个体时间感知差异性建模分析

采用系统捕捉和随机捕捉两类捕捉形式对出行方式的时间感知差异进行建模分析，以验证出行方式选择中时间认识的个体差异性，为更准确的交通方式划分预测提供模型参考。系统捕捉通过在Logit模型中分别设置性别、收入与出行时间的交叉变量以捕捉性别和收入不同导致时间价值认识的差异；随机捕捉通过假定出行时间参数分别服从正态分布、均匀分布、对数正态分布以及约翰逊分布4种随机分布形式，利用Mixed Logit模型捕捉出行者对时间感知的差异。结果表明：出行方式选择中出行者对时间重要性认识存在差异，男性比女性对时间要求高，高收入者比低收入者对时间估值更高；随机捕捉较系统捕捉更能捕捉到出行时间的感知差异，且约翰逊分布较其他分布对时间感知差异性的模拟更优。