道路交通量数列预测模型

应用灰色系统理论对道路交通量进行数列预测,并结合实例建立相应的模型予以验证,通过精度分析及与实际情况的比较,说明数列预测模型应用于道路交通量预测精度较高,而且方法简便.     

高速公路项目的交通量预测方法探讨

从高速公路项目的自身特点出发,探讨了在建设项目工程可行性研究中,应用区域经济学分区理论,在区域社会经济发展预测的基础上,用四阶段法进行交通量预测的方法。     

基于小波变换的交通流数据集成灵敏度分析

道路上的交通流数据通常是以20-30秒间隔采集并传递到交通管理中心的，为了使这些数据能够广泛地运用于各种交通用途，必须采用合理高效的集成方法对其进行处理。传统的数据集成方法基于数理统计的理论，该方法不能有效地去除数据中的噪音。近年来迅速发展的基于小波变换的交通流数据集成方法克服了这一缺点，通过对交通流数据的频率特性进行详细分析能够使集成更加高效，准确满足不同的交通用途对集成的需求。但该方法尚未作进一步的灵敏度分析，本文通过对数据集成中小波函数和数据样本量这两个重要参数的分析，从理论的角度探讨了这两个参数变化对数据集成的影响。然后以北京市三环上的交通流数据为例，计算得到了数据集成建议采用的小波族和小波阶数，以及合理的最小样本量。该结论对数据集成在将来的实际应用具有指导意义。     

区域大规模道路施工交通组织研究——以上海世博配套道路施工交通组织为例

对于日益增多的城市道路施工,现有的交通组织设计缺乏科学、定量的方法,尤其是对于大规模同时进行的道路施工。基于交通仿真模型平台,以定量的交通分析为依据,探讨区域大规模道路施工交通组织、优化的方法;为合理、有效地进行大规模道路施工交通组织提供依据,同时对一般道路施工交通组织具有一定的借鉴意义和参考价值。     

多模式交通网络的交通出行、讫点、方式和路径分配与收费定价模型

本文研究多模式交通网络中出行选择、讫点选择、方式选择、路径选择和拥挤道路收费的组合模型。模型被表示为双层规划。上层模型确定道路收费以达到系统收益最大、成本最小，下层表示出行、讫点、方式和路径选择的随机均衡模型，最后用算例说明。     

TDM措施的经济研究

结合交通需求管理措施的实施,介绍了交通需求管理的概念和基本目标,并且阐述了其经济原理,通过结合对长沙实施交通需求管理措施说明了交通需求管理在交通规划和交通改善上的巨大作用。     

交通监控系统在高速公路的应用

介绍了运行于高速公路中的交通监控系统,以实例阐述了交通监控系统硬件的结构、功能以及监控系统软件的组成。文中给出了监控中心硬件结构图和CCTV系统设备连接图,并说明了交通监控系统的运行意义。     

Will a higher free-flow speed lead us to a less congested freeway?

An approach based on cell transmission model (CTM) is proposed to estimate the impact of variable free-flow speeds (FFS) on the performance of a freeway system. Based on the basic CTM, four typical freeway control strategies consisting of non control, local ramp metering, coordinated ramp metering and global control are first formulated. Then the method of adjusting model parameters to the changed free-flow speeds is presented. Among the adjustments, an experimental function based on Fan and Seibold (2014) is proposed to change the jam density. Several useful measures are defined to estimate and compare the performances of different freeways. The following three main observations are obtained from numerical experiments. (a) With the gradually increasing FFS, the throughput of freeway will increase at the beginning and then change to decrease. (b) With the increasing FFS, the average delay of vehicles will decrease at the beginning and then change to increase. (c) A series of free-flow speeds associate with the best performance of freeway. These observations are theoretically analyzed through investigating the location and capacity of bottleneck. Study shows that in general the actual bottleneck capacity will increase at the beginning and then change to decrease with the continually increasing FFS. In view of the positive correlation between traffic delay and bottleneck capacity, the theoretical analysis confirms the numerical observations. The findings of this study can deepen the understanding of freeway systems and help management agents adopt proper measures to improve the performance of the whole system.     

An efficient realization of deep learning for traffic data imputation

Traffic data provide the basis for both research and applications in transportation control, management, and evaluation, but real-world traffic data collected from loop detectors or other sensors often contain corrupted or missing data points which need to be imputed for traffic analysis. For this end, here we propose a deep learning model named denoising stacked autoencoders for traffic data imputation. We tested and evaluated the model performance with consideration of both temporal and spatial factors. Through these experiments and evaluation results, we developed an algorithm for efficient realization of deep learning for traffic data imputation by training the model hierarchically using the full set of data from all vehicle detector stations. Using data provided by Caltrans PeMS, we have shown that the mean absolute error of the proposed realization is under 10 veh/5-min, a better performance compared with other popular models: the history model, ARIMA model and BP neural network model. We further investigated why the deep leaning model works well for traffic data imputation by visualizing the features extracted by the first hidden layer. Clearly, this work has demonstrated the effectiveness as well as efficiency of deep learning in the field of traffic data imputation and analysis.     

Influence of avenue trees on traffic pollutant dispersion in asymmetric street canyons: Numerical modeling with empirical analysis

The dispersion of traffic-related pollutants in urban street canyons is of importance for the health and quality of lives. To reveal the inherent principle, researchers have performed a lot of investigations; many dispersion phenomena have also been assessed during recent years. However, the presence of avenue trees in street canyons and their capacity for pollutant dispersion remains partly addressed. In this study, we investigated the effects of avenue trees in urban street canyons on traffic pollutant dispersion. The dispersion of CO concentration in asymmetric street canyons was simulated under varied situations. The computational results showed a good agreement with the experimental data, and the numerical model was validated to be adequate for investigating the pollutant dispersion in street canyons. Then, the numerical simulations were extended to explore the impacts of the effects of avenue trees on CO dispersion; the results indicated that avenue trees generally increase CO concentrations in asymmetric street canyons. When the wind direction is perpendicular to the street axis, a terraced building raises pollutant concentrations at the windward wall and reduces concentration at the leeward wall on the pedestrian levels. Findings of this study are expected to provide significant insight into urban road design and strategy making for avenue tree planting, particularly under the existing worldwide sustainable low-carbon urban development.