基于PLS的铁路行包运量预测模型研究

在阐述基于偏最小二乘回归法(PLS)的建模原理与求解方法的基础上,通过对铁路行包运量影响因素的分析,利用2004年有关生产统计数据及影响因素的统计数据,建立了铁路行包运量预测PLS回归模型。实证结果表明:所建立的预测模型精度基本符合实际要求。该模型已应用于铁路行包运输“十一五”发展规划编制工作中。     

Demand and operating cost forecasting accuracy for toll road projects

Inaccurate forecasts represent a major source of risk in road and toll projects because they could result in financial difficulties or even bankruptcy. This paper focuses on demand and operating cost forecasting accuracy for Norwegian toll projects by comparing the forecasted and actual levels of traffic and operating costs. The differences among the types of projects and the effects of project size, time and demand ramp-up are also examined. Our study finds that traffic forecasts for Norwegian toll projects are fairly accurate, on average. However, a majority of the investigated projects experienced overestimation, and a huge general error in the forecasts suggests that this is also a source of risk that merits greater scrutiny. Inaccuracies are common among all project types and sizes. Operating costs are frequently underestimated; on average, these costs are about 30% higher than estimated.     

铁路集装箱运量预测与影响因素分析

运用时间序列的趋势外推法、灰色预测和组合预测方法对我国铁路集装箱运量进行了预测,在此基础上运用因子分析方法对影响铁路集装箱运量的因素进行了分析,得到了国民经济宏观因素和外界竞争因素对铁路集装箱运量具有影响的两个解释性因子。     

基于可靠性计算的编组站车流预估方法研究

编组站阶段计划作为编组站作业计划的核心,对编组站高效完成运输生产任务具有重要作用。然而编组站阶段计划的编制通常受限于到达车流的时间不确定性和车流信息的不准确性,为提高自动编制阶段计划的准确性,研究一种依据车流实际确报信息对预报信息进行准确性评价、并且根据站内车流和带有准确性评价的到达车流进行车流自动推算的方法。在量化车流可靠性参数评估和列车平均运行时间评估的基础上构建模型,并提出相应的算法,随着系统运行过程中车流信息的不断积累和可靠性评价参数的动态更新,通过模拟调度人员对车流分配的思考过程实现到发车流的自动推算和分配。该方法可以有效提升车流推算的准确程度,提高自动编制的阶段计划的可用性。     

对城市交通规划中交通需求预测的研究

交通需求预测工作为交通建设项目的前期规划奠定了基础。通过对交通需求预测与城市交通规划关系的论述,分析交通需求预测的准确度与可信度,说明交通需求预测的重要性。指出当前交通需求预测工作存在的问题,提出提高交通需求预测的认知度、加强影响因素的分析和开展项目后评估等建议。     

铁路客运量季节指数计算方法研究

为在铁路客运量预测中消除季节性变化的影响,采用平均数季节指数法、移动平均趋势剔除法、最小平方趋势剔除法对2002年—2004年的铁路客运量计算季节指数,通过误差分析,说明最小平方趋势剔除法能更好地反映运量的季节变动状况,是预测的最佳选择方案。     

基于客流性质的铁路客流预测方法

运用基于客流性质的铁路客流预测方法对银川—宁东铁路运营初期(2016年)、近期(2023年)和远期(2038年)客流情况进行预测。采用四阶段法对不同性质客流进行生成预测、分布预测和不同交通方式分担预测,通过各种性质客流的叠加,进行总体客流分析,得到研究区域全天客流变化和高峰情况,以及有关客流预测的主要指标。基于客流性质的铁路客流预测方法在客流性质区分明显的情况下,能够具有较好的精确度。     

旅游需求预测模型研究

建立基于月度数据的桂林漓江旅游航班、运量及游客的需求预测模型,运用指数平滑、SARIMA和Elman人工神经网络3种方法,并采用平均绝对误差(MAE)、均方百分比误差(RMSE)和平均绝对百分比误差(MAPE)评价模型预测效果。预测实例表明Elman人工神经网络模型更能反映时间序列的波动性,更适合桂林漓江旅游需求预测。     

Temporal aggregation and spatio-temporal traffic modeling

Traffic forecasting is crucial for policy making in the transport sector. Recently, Selby and Kockelman (2013) have proposed spatial interpolation techniques as suitable tools to forecast traffic at different locations. In this paper, we argue that an eventual source of uncertainty over those forecasts derives from temporal aggregation. However, we prove that the spatio-temporal correlation function is robust to temporal aggregations schemes when the covariance of traffic in different locations is separable in space and time. We prove empirically this result by conducting an extensive simulation study on the spatial structure of the Milan road network.     

基于Holt-Winter模型的铁路货运量预测研究

建立Holt-Winter预测模型，将具有线性趋势、季节变动和随机波动的时间序列进行分解研究，并与指数平滑法相结合，分别对长期趋势、趋势的增量和季节波动做出估计。介绍该模型的3个平滑方程和1个预测公式，以及初始值的计算和最优加权系数值的确定。通过实证分析，将预测结果与常用模型进行比较，说明该模型的预测精度较高。     

铁路行包运量预测模型研究

铁路行包运量预测是以运输需求和内部供给为导向,综合考虑各种影响因素,对行包运量现状和发展的正确把握.探讨利用人工神经网络结合主成分分析的方法,建立铁路行包运量预测模型,解释并预测行包专列开行后铁路行包运量的增长趋势.实例分析的仿真结果表明,采用主成分分析法的广义回归神经网络模型结构简洁、预测精度高、收敛速度快,对相关铁路部门和企业的决策具有参考意义.     

Air transportation demand forecast through Bagging Holt Winters methods

This paper expands the fields of application of combined Bootstrap aggregating (Bagging) and Holt Winters methods to the air transportation industry, a novelty in literature, in order to obtain more accurate demand forecasts. The methodology involves decomposing the time series into three adding components: trend, seasonal and remainder. New series are generated by resampling the Remainder component and adding back the trend and seasonal ones. The Holt Winters method is used to modelling each time series and the final forecast is obtained by aggregating the forecasts set. The approach is tested using data series from 14 countries and the results are compared with five methodology benchmarks (SARIMA, Holt Winters, ETS, Bagged.BLD.MBB.ETS and Seasonal Naive) using Symmetric Mean Absolute Percentage Error (sMAPE). The empirical results obtained with Bagging Holt Winters methods consistently outperform the benchmarks by providing forecasts that are more accurate.     

基于IPSO-BP神经网络的铁路客运量预测

在分析有关铁路客运量预测方法的基础上,针对BP神经网络模型存在的不足,提出基于粒子群优化算法(PSO)优化BP神经网络的参数,即改进的PSO方法(IPSO)。以我国1990—2007年的铁路客运量为研究对象,确定输入样本和输出样本,以及训练集和测试集,建立基于IPSO的BP神经网络优化模型预测铁路客运量。预测结果表明,IPSO-BP网络的算法训练时间短,收敛速度快,预测精度高。     

A zonal level safety investigation of pedestrian crashes in Riyadh,Saudi Arabia

In the recent decade, walking has been encouraged as an active mode of transportation, which could reduce congestion and air pollution and also improve community health. However, pedestrians are more vulnerable to traffic crashes compared with other road users, especially in developing countries such as Saudi Arabia. This paper examines the association among traffic volume, land-use, socio-demographic and roadway characteristics factors, and the frequency of pedestrian crashes based on macro-level safety analysis using data from Riyadh, the Capital of Saudi Arabia. Two Bayesian spatial Poisson-lognormal models for total and severe pedestrian crashes are developed in this study. The results show that the factors that affect total pedestrian crash occurrence are different from those affecting severe pedestrian crash. Several implications for pedestrian safety policies in Riyadh are suggested based on the results.     

Performance analysis of rail transit investments in Turkey: İstanbul,Ankara, İzmir and Bursa

Rail transit investments require the highest amount of investment costs of all modes. Considering the high cost involved, it is particularly important that their performance justifies this high cost and that expectations from these investments are met. Therefore, in the world, it has become an important field of research to study the gap between the expectations from and outcomes of these investments in order to assess the performances.In Turkey, there is a growing interest in constructing rail transit systems in the cities. However, there has been a limited number of studies on the performance of these investments. It is not clear with what expectations these systems are built or whether these expectations are met. There seems to be an urgent need to study these rail investments, with a particular focus on their planning/investment objectives and outcomes.This paper compares the expectations with the actual outcomes. A sample group was selected among the cities currently operating rail transit systems: ?stanbul, Ankara, ?zmir and Bursa. Semi-structured interviews were made with the officers and planners that have involved in the planning or implementation phase of the systems. As the primary indicators of performance, cost and ridership forecast and outcome data are collected and considered in the comparison.It is found that systems performed rather poor in terms of expectations, such as attaining ridership forecasts, being built within budget etc. Hence there is a gap between expectations and outcomes.     

A review of Delphi forecasting research in tourism

The Delphi technique is the most popular judgemental forecasting method in tourism studies, but theoretical and empirical developments in this area (especially for forecasting purposes) have been slow. This paper analyses published research on Delphi forecasting in tourism and hospitality, explores how the Delphi forecasting method has progressed over the past four decades in terms of topical areas, empirical applications, and issues of reliability and validity, and is thus expected to advance understanding of the Delphi technique, providing topical and methodological recommendations for researchers and industry practitioners for producing accurate forecasts. The literature concerning the qualitative and quantitative applications of Delphi forecasting in tourism is mainly divided into three research themes: event forecasting, forecasting tourism demand, and forecasting future trends/market conditions (the most popular application). Issues of accuracy, reliability, and validity, as well as a group of Delphi-specific characteristics, such as panel size, panel selection, consensus measures, and analysis of results, are summarized and discussed. This study also examines the accuracy of Delphi forecasts as well as exploring the role of the Delphi approach in integrating human judgement into quantitative forecasts.     

Airport-specific traffic forecasts: a critical perspective

This paper offers some comments on the nature of airport-specific traffic forecasting. While the argument acknowledges the importance of reconciling local hinterland-derived and global macro-economic forces in such projections, it is argued that the primary causative factors in airport forecasts relate primarily to supply as distinct from demand. In particular, the discussion examines the effects of deregulation on airline and airport strategies. It concludes that future forecasting methodologies have to build on the role and viability of specific airlines at specific airports, rather than prolong an increasingly timeworn dependence on hinterland-derived factors and related assumptions of consumer choice.     

基于季节调整模型的我国铁路客运量波动分析

在研究TRAMO/SEATS季节调整模型计算方法的基础上,基于我国铁路2002年1月—2010年2月的客运量月度数据,应用Demetra软件,通过季节调整模型参数设置、模型的估计和检验,得到2010年3月—2012年2月的铁路客运量预测值,并对预测结果进行趋势性和季节性分析。研究结果表明,Tramo/Seats季节调整模型的预测精度较高。     

基于广义回归神经网络的铁路货运量预测

针对BP神经网络预测存在局部极小缺陷和收敛速度慢的问题,提出基于广义回归神经网络(GRNN)的预测模型。基于我国1999—2008年铁路货运量的历史统计数据,应用GRNN模型和混沌BP神经网络模型对铁路货运量进行预测。通过两种预测模型的计算结果比较说明,GRNN模型具有良好的收敛性和较高的精度,而且模型结构简单、计算速度快,具有良好的实用性。     

综合交通枢纽内换乘班次衔接优化研究

综合交通枢纽内换乘衔接的合理、有效程度是影响整个综合运输体系效率的关键。针对既有研究中对换乘衔接建立模型存在的问题,参照复杂网络理论以结构解释网络功能的思想,建立综合交通枢纽内部的换乘班次衔接网络。以换乘班次衔接网络自身特点为基础,提出反映换乘网络结构的平均路径长度、聚类系数、度3个统计特征,并通过算例对换乘网络整体存在的问题和能力不匹配、时间不接续等实际情况给出解决方案。