Short-term forecasting of high-speed rail demand: A hybrid approach combining ensemble empirical mode decomposition and gray support vector machine with real-world applications in China

Short-term forecasting of high-speed rail (HSR) passenger flow provides daily ridership estimates that account for day-to-day demand variations in the near future (e.g., next week, next month). It is one of the most critical tasks in high-speed passenger rail planning, operational decision-making and dynamic operation adjustment. An accurate short-term HSR demand prediction provides a basis for effective rail revenue management. In this paper, a hybrid short-term demand forecasting approach is developed by combining the ensemble empirical mode decomposition (EEMD) and grey support vector machine (GSVM) models. There are three steps in this hybrid forecasting approach: (i) decompose short-term passenger flow data with noises into a number of intrinsic mode functions (IMFs) and a trend term; (ii) predict each IMF using GSVM calibrated by the particle swarm optimization (PSO); (iii) reconstruct the refined IMF components to produce the final predicted daily HSR passenger flow, where the PSO is also applied to achieve the optimal refactoring combination. This innovative hybrid approach is demonstrated with three typical origin–destination pairs along the Wuhan-Guangzhou HSR in China. Mean absolute percentage errors of the EEMD-GSVM predictions using testing sets are 6.7%, 5.1% and 6.5%, respectively, which are much lower than those of two existing forecasting approaches (support vector machine and autoregressive integrated moving average). Application results indicate that the proposed hybrid forecasting approach performs well in terms of prediction accuracy and is especially suitable for short-term HSR passenger flow forecasting.     

短时段交通流预测的RBF神经网络模型

介绍了基于RBF神经网络的短时段交通量预测模型,并利用该模型对高速公路所采集的数据进行仿真预测分析。预测结果表明RBF神经网络预测方法通过定义合理的网络结构参数可以获得较高的预测精度,能够满足路网调度对短时段交通流预测的需求。     

交通预测原则和预测模型评价方法

在总结已有研究成果的基础上,提出了交通预测应遵循的原则,并对交通预测评价方法和模型选择等问题进行了探讨,以期更好地指导交通实际预测工作。     

一般收费道路通行费收入实用预测方法研究

重点探讨实际道路规划项目中一般收费道路的收费收入预测方法,目的在于尽可能使收费收入预测更为精确。在我国,高速公路通常采用依靠征收通行费以偿还投资借贷的方式进行建设,因此在规划的过程中需要对通行费收入进行预测,并进行财务分析,以保证决策者做出正确的投资决策。以笔者在日本从事的高速公路建设项目为例,分析研究了基于实用型交通量增量分配方法结合使用车种转换矩阵的高速公路路网中一般收费道路通行费收入的预测方法,并将其应用到实际道路项目财务评价中。结果表明通过控制收费道路出入口间交通量预测精度,以及采用需求相关性较大的车种转换调查数据可以提高通行费预测精度。研究表明这一方法具有很强的实用性,该方法对我国的高速公路需求预测有着借鉴作用。     

基于非参数回归的快速路行程速度短期预测算法

基于北京市快速路上的检测器所采集的历史数据，经过数据筛选，剔除判别，小波滤噪平稳处理，聚类分析等过程，建立了交通状态演变系列的历史样本数据库。基于所构建的历史数据库，通过数值试验，确定了状态向量、距离匹配原则，K近邻值等参量，构建了一种基于K近邻的非参数回归短时交通预测模型，实现了对路段行程速度的短时预测。最后，利用随机选取的历史数据系列对预测模型的精度进行了检验。结果表明，预测算法的精度可以达到90％以上，可以很好地满足ITS应用系统对于交通预测数据的精度要求。     

诱增交通量特点、发展阶段及计算模型分析

分析了诱增交通量的特点和发展阶段，根据交通需求预测理论对诱发交通量预测方法进行了初步探讨，提出了诱增交通量的计算模型。结合实例分析了诱增交通量的定量计算。     

交通冲突量的BP神经网络预测方法

交通冲突预测是进行交通事故预防和制定安全改善措施的有效手段，节约观测时间和人力。针对BP网络的缺点，提出了改进的快速BP算法，建立了交通冲突量的BP神经网络预测方法，并应用该方法对具体的交叉口交通冲突量的预测实例进行了研究，实践验证了该方法的有效性。     

基于三弯矩样条函数插值模型的非等距时序灰色预测方法

给出了三弯矩样条函数插值模型,用以解决非等距时序GM（1,1）的灰色预测问题.在国际平整度指数IRI的非等距时序样条灰色预测应用实例表明,该方法在作非等距时序列向等距时序列转换中保留了原有数据序列所呈现出的阶段性规律,具有精度高、实用性强的特点.     

隧道底部溶洞顶板安全厚度预测模型

以某公路岩溶隧道为背景,采用二维弹塑性有限元方法对隧道开挖进行数值模拟计算,分析隧道底部溶洞顶板安全厚度的影响因素,研究各影响因素与安全厚度的相关变化规律,并用多元回归和支持向量机方法建立能综合体现各影响因素的溶洞顶板安全厚度预测模型,从而为岩溶隧道设计施工提供一定的科学依据和指导。     

Demand for rail travel to and from airports

Rail access to airports is becoming increasingly important for both train operators and the airports themselves. This paper reports analysis of inter-urban rail demand to and from Manchester and Stansted Airports and the sensitivity of this market segment to growth in air traffic and the cost and service quality of rail services. The estimated demand parameters vary in an expected manner between outward and inward air travellers as well as between airport users and general rail travellers. These parameters can be entered into the demand forecasting framework widely used in the rail industry in Great Britain to provide an appropriate means of forecasting for this otherwise neglected market segment. The novel features of this research, at least in the British context, are that it provides the first detailed analysis of aggregate rail flows to and from airports, it has disaggregated the traditional generalised time measure of rail service quality in order to estimate separate elasticities to journey time, service headway and interchange, and it has successfully explored departures from the conventional constant elasticity position.