Comparison of advanced imputation algorithms for detection of transportation mode and activity episode using GPS data

Global Positioning System (GPS) technologies have been increasingly considered as an alternative to traditional travel survey methods to collect activity-travel data. Algorithms applied to extract activity-travel patterns vary from informal ad-hoc decision rules to advanced machine learning methods and have different accuracy. This paper systematically compares the relative performance of different algorithms for the detection of transportation modes and activity episodes. In particular, naive Bayesian, Bayesian network, logistic regression, multilayer perceptron, support vector machine, decision table, and C4.5 algorithms are selected and compared for the same data according to their overall error rates and hit ratios. Results show that the Bayesian network has a better performance than the other algorithms in terms of the percentage correctly identified instances and Kappa values for both the training data and test data, in the sense that the Bayesian network is relatively efficient and generalizable in the context of GPS data imputation.     

The relationship between urban street networks and private motorized trips at the city level

There are factors that impact car usage in urban areas, such as density, diversity and design, but there have been few studies that examine the relationship between street network factors and car usage at the city level (macro level). This paper focuses on this relationship by introducing urban street network variables, such as blocks per area, nodes per block and length of roads and motorways, as independent variables and the percentage of daily trips by private motorized modes as the dependent variable. The street network in this study includes interconnecting lines and points that present streets, roads, motorways, intersections and blocks. The strength of the relationship in this study is found using multiple linear regression. The findings of this research indicate that an increase in car usage is correlated with an increasing number of blocks per area, number of nodes per block and length of motorways. In addition, because the urban street network is the result of macro-scale planning decisions, considering this relationship can lead to better planning decisions.     

Short‐term traffic flow prediction with linear conditional Gaussian Bayesian network

Traffic flow prediction is an essential part of intelligent transportation systems (ITS). Most of the previous traffic flow prediction work treated traffic flow as a time series process only, ignoring the spatial relationship from the upstream flows or the correlation with other traffic attributes like speed and density. In this paper, we utilize a linear conditional Gaussian (LCG) Bayesian network (BN) model to consider both spatial and temporal dimensions of traffic as well as speed information for short‐term traffic flow prediction. The LCG BN allows both continuous and discrete variables, which enables the consideration of categorical variables in traffic flow prediction. A microscopic traffic simulation dataset is used to test the performance of the proposed model compared to other popular approaches under different predicting time intervals. In addition, the authors investigate the importance of spatial data and speed data in flow prediction by comparing models with different levels of information. The results indicate that the prediction accuracy will increase significantly when both spatial data and speed data are included. Copyright © 2016 John Wiley & Sons, Ltd.     

A self-regulation traffic-condition-based route guidance strategy with realistic considerations: Overlapping routes,stochastic traffic,and signalized intersections

Variable message signs that provide various types of route guidance information have been widely deployed in large cities. To release proper information only using easily collected data, a simple traffic-condition-based (TCB) route guidance strategy was recently proposed. The strategy works based on the estimation of free-flow and congested traffic conditions and is capable of approximating user optimal equilibrium stably. Due to little consideration of the complexity of urban road networks, the TCB strategy is still away from field applications in urban areas. To further push the strategy toward field tests, this article improves the TCB strategy in the following aspects: supplementing the strategy with a self-regulation ability by considering existing traffic conditions; decomposing link capacity to solve the problem of overlapping routes by comparing link capacity on alternative routes; coping with stochastic traffic; and the impact of signalized intersections by utilizing aggregated data. A scenario for an urban road network in Beijing, China, is simulated to test the improved strategy, and the simulation results clearly indicate the effectiveness of the proposed improvements. The improvements extend the TCB strategy on moderately complicated urban road networks, and still have the advantages of simple diversion rules, easily obtained input data, and stable and effective diversion processes.     

优化爆破参数进行地铁车站隧道控制爆破

为减小爆破振动速度和提高炮眼利用率,以青岛地铁2号线车站主体Ⅰ部上台阶的爆破开挖为背景,从理论上分析了由于掏槽区域爆破效果差引起爆破振动过大,由于掏槽眼不对称、掏槽区域布置不当、掏槽眼间排距过大、辅助眼排距过大、未封堵炮孔等原因造成炮眼利用率较低。结合理论计算和工程前期施工经验对楔形掏槽参数进行了优化,同时在校核单段最大起爆药量时考虑了多自由面的影响。结果表明： 优化后的复式楔形掏槽使炮眼利用率提高到90.5%,爆破振动速度控制在0.7 cm/s以内。     

过饱和道路交通控制信号周期优化解分析

分析了过饱和交通条件下城市道路信号控制交叉口周期参数值的优化解。以拥挤消散时间和路网总延误为控制目标,采用定时信号控制策略,基于元胞传输模型建立了路网优化控制模型,并采用遗传算法优化信号配时,对比了不同信号周期条件下拥挤消散时间和路网总延误的变化规律。最后,本文以某市L路为算例分析了周期值与消散时间及路网总延误的关系,结论表明路网在过饱和拥堵条件下,当控制周期大于某一临界周期值时,相位差和绿信比的优化将无法抑制消散时间的持续增长趋势;最优配时结果的路网总延误值比采用传统最大周期控制策略的路网总延误值降低17％以上。     

一种区域公路交通线圈检测器优化布设的简捷方法

利用数学方法优化布设交通检测器难在求解困难。提出根据检测器布设的目的从总体上把握区域公路网的交通状况,可以简单快速的实现区域公路交通线圈检测器的优化布设。     

多用户多准则城市交通网络非稳定均衡分析

为了反映现实中交通出行者实施出行与否的决策过程,通过对实际城市交通网络状态的分析,引入了非稳定均衡网络状态的概念。同时通过对出行者出行选择行为的深入分析,引入了多用户多准则非稳定均衡网络状态的非线性互补问题模型和变分不等式模型,并利用超级网络的概念证明了两者的等价性。新模型能够将出行者的路径选择决策、目的地选择决策、出行方式选择决策以及出行与否决策合理的整合在一起,从而可完整的反映城市交通流的形成模式。给出了求解多用户非稳定均衡态的变分不等式模型的修正投影算法,并通过一个数值例子验证了算法的有效性。结论部分给出了多个可进一步深入研究的方向。     

BP神经网络在路面模量反分析中的应用

使用MATLAB神经网络工具箱研究了BP神经网络在路面模量反分析中的应用。研究结果表明,只要合理的处理输入和输出参数,利用BP神经网络可以较好的预测路面各层的弹性模量,并且相对于其他分析方法,该方法运算速度非常快,适合于实际工程中应用。     

基于神经网络的公交客流预测

公交客流量具有动态性,受多种因素的影响,不能或无法用精确的数学模型进行预测。通过对公交客流量预测的Elman和BP神经网络的建立、学习和训练。并以前三年的公交客流量、国内生产总值、工业总产值、城市人口数作为两种神经网络的输入神经元,第四年的公交客流量作为输出神经元,同时以合肥市公交客流量为例进行分析,结果表明：所建的Elman模型比EBP模型的预测精度高,效果好。