A computationally efficient two-stage method for short-term traffic prediction on urban roads

Abstract

Short-term traffic prediction plays an important role in intelligent transport systems. This paper presents a novel two-stage prediction structure using the technique of Singular Spectrum Analysis (SSA) as a data smoothing stage to improve the prediction accuracy. Moreover, a novel prediction method named Grey System Model (GM) is introduced to reduce the dependency on method training and parameter optimisation. To demonstrate the effects of these improvements, this paper compares the prediction accuracies of SSA and non-SSA model structures using both a GM and a more conventional Seasonal Auto-Regressive Integrated Moving Average (SARIMA) prediction model. These methods were calibrated and evaluated using traffic flow data from a corridor in Central London under both normal and incident traffic conditions. The prediction accuracy comparisons show that the SSA method as a data smoothing step before the application of machine learning or statistical prediction methods can improve the final traffic prediction accuracy. In addition, the results indicate that the relatively novel GM method outperforms SARIMA under both normal and incident traffic conditions on urban roads.     

Converting mixed pedestrian flows into equivalent commuters using standard pedestrian equivalent factors

This paper develops the concept of standard pedestrian equivalent (SPE) factors for converting a mixed pedestrian flow into an equivalent commuter flow. After a comprehensive review of passenger car equivalent (PCE) methodologies, the equal total travel time method is utilised for SPE estimation. A micro-simulation approach is employed for the formulation of the total travel time–flow relationship. Field data collected on walking speed distributions for commuters and older adults in Australia are used as model inputs. An independent samples t-test confirms the significant difference between walking speeds of commuters and older adults. For this paper, a unidirectional flow on flat walkways is initially considered and evaluated across proportions of older people, different flows and different walkway widths. The introduction of older adults significantly increases total travel time especially under congested conditions. Results of this investigation can be used for evaluation or design of pedestrian facilities experiencing similar flow conditions.     

Using Focus and NomiNal Group Techniques for a Better Understanding of the Transit Disadvantaged Needs

The research presented in this paper explores the context, method, and value of focus group research in transit needs assessments. Group participatory research can generate data that are not easily obtained by other methods. The paper focuses on lessons from three Nebraska communities whose transit disadvantaged rely on community-based paratransit services. Because of the size of the paratransit population and the inability to control who showed up to the focus group sessions, a modified group research protocol was adopted in order to garner information from whomever attended the session. The population parameters and the number of people at the meetings were anticipated by the researchers and mitigated by incorporating nominal group techniques. Research findings from the focus group sessions are discussed paying particular attention to the candid and policy-specific comments made by the focus group participants. The paper concludes with an application of focus group research in transit planning.     

Competition and ownership in land passenger transport: the fourth international conference — Part 2

In the rail industry worldwide, there has been a search for new solutions, including restructuring, corporatization, and outright privatization, but the complexity of the rail industry offers special problems. In the Workshop we looked in detail at the British, Swedish, German, Australian (New South Wales) and New Zealand experiences, as well as considering more general issues such as cost structures, vertical separation and competitive tendering. Whilst it was agreed that some developments, such as greater contracting out, were clearly beneficial, other developments such as the separation of infrastructure from operations remained of uncertain value until the issues of efficient pricing and slot allocation were resolved.     

Sample size requirements for stated choice experiments

Stated choice (SC) experiments represent the dominant data paradigm in the study of behavioral responses of individuals, households as well as other organizations, yet in the past little has been known about the sample size requirements for models estimated from such data. Traditional orthogonal designs and existing sampling theories does not adequately address the issue and hence researchers have had to resort to simple rules of thumb or ignore the issue and collect samples of arbitrary size, hoping that the sample is sufficiently large enough to produce reliable parameter estimates, or are forced to make assumptions about the data that are unlikely to hold in practice. In this paper, we demonstrate how a recently proposed sample size computation can be used to generate so-called S-efficient designs using prior parameter values to estimate panel mixed multinomial logit models. Sample size requirements for such designs in SC studies are investigated. In a numerical case study is shown that a D-efficient and even more an S-efficient design require a (much) smaller sample size than a random orthogonal design in order to estimate all parameters at the level of statistical significance. Furthermore, it is shown that wide level range has a significant positive influence on the efficiency of the design and therefore on the reliability of the parameter estimates.     

Toward regional transportation governance: a case study of Greater Vancouver

This paper discusses the evolving institutional structure and governance of transportation planning, policy development and transit delivery within one major North American city-region, the Greater Vancouver area. Various methods of transportation governance are explored from complete independence to full regional integration. The move away from a direct provincial role in transportation management to a greater regional transit authority is discussed and critiqued. This revised version was published online in June 2006 with corrections to the Cover Date.     

正向浪作用下离岸高桩墩台结构波浪总浮托力计算

波浪总浮托力是离岸高桩墩台结构设计时需要注意的重要外荷载之一。根据具体工程实例计算结果和试验结果的对比,分析正向波浪作用下离岸高桩墩台结构波浪总浮托力不同计算公式的适用性,研究工程实际计算波浪总浮托力需要注意的条件,并提出建议。     

面向大型活动的交通应急预案快速生成与动态优化方法

现阶段大型活动突发事件下的交通组织应急预案多依赖人工经验,缺少针对性和定量化应急措施。针对预案的快速匹配问题,提出利用交通应急预案库中的历史案例提取突发事件特征属性,基于案例推理和朴素贝叶斯分类快速生成初始预案,并依据贝叶斯分类算法所得后验概率选取属性不完备情况下的最佳匹配预案。在此基础上,基于改进的规则推理建立交通应急预案库知识库和规则库,并采用正向推理修改预案内容。为构建评价指标体系,基于模糊层次分析法对预案应急能力水平和突发事件严重程度进行模糊评价。以北京2022年冬奥会为仿真案件,试验结果表明该方法可以快速生成最佳匹配预案并完成动态调整与完善。     

卡尔曼滤波短时交通流预测普通国省道适应性研究

短时交通流预测是提高普通国省道交通运行效率和安全的关键技术之一。普通国省道具有分布地域广、情况复杂的特点,要求短时交通流预测方法具有良好的适应性,然而,针对短时交通流预测算法适应性及其机制的系统性研究尚不多见。选取1种自适应卡尔曼滤波算法,系统分析其适应性和适应机制。获取江苏省徐州市普通国省道路网中8个交通调查站所采集的实际交通流数据开展实例分析,结果表明：在不同的交通流量水平下,所选算法均值预测的平均绝对百分比误差在10.98%~15.92%之间,区间预测的无效覆盖率在5.21%~6.15%之间,表明所选的自适应卡尔曼滤波算法在不同交通流水平下都具有良好的预测性能;对所选算法的参数进行分析发现,算法参数能够随交通流水平的变化而自动调整,具有良好的自适应机制;所选算法能够在预测初期实现有效的性能调整和收敛。

     

基于互信息贝叶斯网络的交通事故严重程度分析

为掌握省际客运行业事故严重程度影响因素, 采用互信息及贝叶斯网络方法构建模型, 分析各因素变化与事故严重程度的定量互动关系。鉴于行业样本量较小及专家知识建模存在主观性, 采用改进离散算法挖掘数据, 提出结合互信息与交叉验证的先验网络构造方法。以上海市2005—2019年741起省际客运事故数据为例进行模型分析。结果表明: 对事故最敏感的影响因素为驾驶员性别、天气和车辆类型; 其中“女性驾驶员”“雪、大风、雾”“中型客车”对事故严重性的权重占比分别为13.5%, 8.8%和5.7%;此外, 驾驶员年龄对群死群伤事故贡献较小; 客车尺寸与安全性非单调关系; 00:00—05:00引发7人以上受伤的概率同比上升9%;季节、天气、时间因素与财产损失无直接关联。模型泛化能力优于对比模型, AUC均值为0.644 588, 命中率达到97.3%。