改进支持向量回归机的短时交通流预测

短时交通流预测是实施智能交通控制的基础和保障.针对目前短时交通流预测方法拟合交通数据的能力偏弱，以及过分依赖历史数据的不足，提出一种基于深度学习回归机的短时交通流预测方法.首先构建深度学习回归机算法模型，包括受限玻尔兹曼机的显层节点输入端，受限玻尔兹曼机的若干中间层，以及径向基支持向量回归机输出端.通过实验将深度学习回归机预测方法与其他典型的短时交通流预测算法进行比较，结果表明，在相同的数据和计算平台下，本文提出的深度学习回归机预测方法精度更高，且预测实时性也能满足实际的需求.     

基于偏最小二乘回归的疏浚产量预测方法

针对绞吸式挖泥船产量预测困难的问题,对挖泥船作业实时反馈的数据进行研究。利用Relief权重算法提取出影响挖泥船产量的主要工艺参量,并在此基础上采用偏最小二乘回归,建立主要工艺参量与产量之间的数学模型,实现对挖泥船产量的预测。结果表明,利用偏最小二乘回归建立的数学模型能够很好地对挖泥船的产量进行预测,可为预测挖泥船的产量提供一种有效的方法。     

天气因素对福州地铁客流的影响分析

地铁作为一种绿色出行方式，是缓解城市交通拥堵的重要手段。地铁客流受到多种因素影响，其中天气因素变化较快，会造成地铁客流的快速变化。了解天气因素对地铁客流的影响，有助于建立相应的运输组织响应措施。本文旨在量化分析天气因素对福州地铁客流量的影响，并考虑原始天气指标的局限性，引入体现舒适度的指标。建立地铁客流与天气因素(包括气压、相对湿度、风力、降水、风寒指数等级、综合舒适度指数等级等)之间的多元线性回归模型，量化影响方向和影响程度。此外，工作日与非工作日的客流模式差异较大，将两者分别建模分析。研究发现：工作日，降水、风寒指数等级和综合舒适度指数等级对地铁客流有显著影响；非工作日，降水、气压、相对湿度、风寒指数等级和综合舒适度指数等级对地铁客流有显著影响。总体而言，非工作日地铁客流对天气因素更加敏感。     

Exploring the issue of integrating logistics and traffic control in urban areas

This paper proposes an optimization framework for urban transportation networks’ (re-)design which explicitly takes into account the specific decision-making processes of ordinary users and logistic operators. Ordinary users are typically commuters whose travels consist of well-defined pairs of origin and destination points, while logistic operators make deliveries at multiple locations. Obviously, these two user classes have different objectives and scopes of action. These differences are seldom considered in traffic research since most models aggregate the flow demand in OD matrices and use assignment models to predict the response of all users as if the dynamics of their optimization processes were of the same nature. This work demonstrates that better results can be achieved if the particular features of each user class are included in the models. It potentially improves the estimation of the responses and allows managers to shape their control measures to address specific user needs.     

Analyzing passenger train arrival delays with support vector regression

We propose machine learning models that capture the relation between passenger train arrival delays and various characteristics of a railway system. Such models can be used at the tactical level to evaluate effects of various changes in a railway system on train delays. We present the first application of support vector regression in the analysis of train delays and compare its performance with the artificial neural networks which have been commonly used for such problems. Statistical comparison of the two models indicates that the support vector regression outperforms the artificial neural networks. Data for this analysis are collected from Serbian Railways and include expert opinions about the influence of infrastructure along different routes on train arrival delays.     

Factors affecting public transportation usage rate: Geographically weighted regression

As the number of private vehicles grows worldwide, so does air pollution and traffic congestion, which typically constrain economic development. To achieve transportation sustainability and continued economic development, the dependency on private vehicles must be decreased by increasing public transportation usage. However, without knowing the key factors that affect public transportation usage, developing strategies that effectively improve public transportation usage is impossible. Therefore, this study respectively applies global and local regression models to identify the key factors of usage rates for 348 regions (township or districts) in Taiwan. The global regression model, the Tobit regression model (TRM), is used to estimate one set of parameters that are associated with explanatory variables and explain regional differences in usage rates, while the local regression model, geographically weighted regression (GWR), estimates parameters differently depending on spatial correlations among neighbouring regions. By referencing related studies, 32 potential explanatory variables in four categories, social-economic, land use, public transportation, and private transportation, are chosen. Model performance is compared in terms of mean absolute percentage error (MAPE) and spatial autocorrelation coefficient (Moran’ I). Estimation results show that the GWR model has better prediction accuracy and better accommodation of spatial autocorrelation. Seven variables are significantly tested, and most have parameters that differ across regions in Taiwan. Based on these findings, strategies are proposed that improve public transportation usage.     

Towards data-driven car-following models

Car following models have been studied with many diverse approaches for decades. Nowadays, technological advances have significantly improved our traffic data collection capabilities. Conventional car following models rely on mathematical formulas and are derived from traffic flow theory; a property that often makes them more restrictive. On the other hand, data-driven approaches are more flexible and allow the incorporation of additional information to the model; however, they may not provide as much insight into traffic flow theory as the traditional models. In this research, an innovative methodological framework based on a data-driven approach is proposed for the estimation of car-following models, suitable for incorporation into microscopic traffic simulation models. An existing technique, i.e. locally weighted regression (loess), is defined through an optimization problem and is employed in a novel way. The proposed methodology is demonstrated using data collected from a sequence of instrumented vehicles in Naples, Italy. Gipps’ model, one of the most extensively used car-following models, is calibrated against the same data and used as a reference benchmark. Optimization issues are raised in both cases. The obtained results suggest that data-driven car-following models could be a promising research direction.     

Cellpath: Fusion of cellular and traffic sensor data for route flow estimation via convex optimization

A new convex optimization framework is developed for the route flow estimation problem from the fusion of vehicle count and cellular network data. The issue of highly underdetermined link flow based methods in transportation networks is investigated, then solved using the proposed concept of cellpaths for cellular network data. With this data-driven approach, our proposed approach is versatile: it is compatible with other data sources, and it is model agnostic and thus compatible with user equilibrium, system-optimum, Stackelberg concepts, and other models. Using a dimensionality reduction scheme, we design a projected gradient algorithm suitable for the proposed route flow estimation problem. The algorithm solves a block isotonic regression problem in the projection step in linear time. The accuracy, computational efficiency, and versatility of the proposed approach are validated on the I-210 corridor near Los Angeles, where we achieve 90% route flow accuracy with 1033 traffic sensors and 1000 cellular towers covering a large network of highways and arterials with more than 20,000 links. In contrast to long-term land use planning applications, we demonstrate the first system to our knowledge that can produce route-level flow estimates suitable for short time horizon prediction and control applications in traffic management. Our system is open source and available for validation and extension.     

交通可达性与城市经济活动的空间特征分析：以北京市为例

借助开源大数据平台，提出交通可达性及城市经济活动数据采集策略，利用全局常参数和局部变参数回归模型研究北京市六环区域内两者的空间特征.相比于全局模型，局部模型能够较好地刻画交通可达性与城市经济活动间的空间异质性特征.结果表明，私人交通可达性呈现以天安门为中心径向递减的多圈层结构，公共交通呈现轨道交通沿线区域高的特点.交通可达性与经济活动匹配度具有空间非平稳性，空间分离和匹配现象并存.西北部、中部区域空间匹配特征显著，东北部、东部区域次之，西南区域空间分离现象最为严重.丰台及良乡等分离区域，宜重视道路及轨道线网等基础设施建设工作；未来科学城等私人交通匹配，公共交通分离的区域，可考虑修建轨道线路，并增加公交运营服务水平；中关村科学城、北京经济技术开发区等匹配区域，以调整交通运营管理政策为主.     

基于符号回归算法的地铁盾构刀盘扭矩预测研究

为了提高盾构机工作效率、降低施工成本,依托深圳地铁8号线某盾构区间段工程,基于符号回归(Symbolic Regression)算法,对不同掌子面的刀盘扭矩进行了预测。分析了推力、土仓压力以及贯入度变化及换刀对扭矩的影响。结果表明,贯入度增大会导致扭矩增加,但是土仓压力的增加可能会降低扭矩。扭矩模拟数学模型具有较高精度,模型中自变量变动引起因变量变化的趋势与现实情况一致。