Efficient missing data imputing for traffic flow by considering temporal and spatial dependence

The missing data problem remains as a difficulty in a diverse variety of transportation applications, e.g. traffic flow prediction and traffic pattern recognition. To solve this problem, numerous algorithms had been proposed in the last decade to impute the missed data. However, few existing studies had fully used the traffic flow information of neighboring detecting points to improve imputing performance. In this paper, probabilistic principle component analysis (PPCA) based imputing method, which had been proven to be one of the most effective imputing methods without using temporal or spatial dependence, is extended to utilize the information of multiple points. We systematically examine the potential benefits of multi-point data fusion and study the possible influence of measurement time lags. Tests indicate that the hidden temporal–spatial dependence is nonlinear and could be better retrieved by kernel probabilistic principle component analysis (KPPCA) based method rather than PPCA method. Comparison proves that imputing errors can be notably reduced, if temporal–spatial dependence has been appropriately considered.     

Improving maritime inventory routing: application to a Brazilian petroleum case

The crude oil offloading and supply problem (COSP) is a type of operation maritime inventory routing (MIR) problem encountered by petroleum companies. In COSP, the company not only is responsible for the ship scheduling to carry the crude oil from production sites to discharge ports but also must maintain inventory levels at both ports (production and consumption) between safety operational bounds to avoid disruptions in its crude oil production and/or refining processes. We show how to improve significantly the decision-making process in a Brazilian petroleum company using a mixed-integer linear programming (MILP) model to represent COSP. Comparison tests with a current ship-scheduling method adopted in the company indicated that the use of the MILP model increased the transportation efficiency and reduced costs by 20% on average. In addition to the quantitative gains, the use of a MILP model to solve COSP has succeeded when encountering real-life events, such as variation in production or consumption rates, berth unavailability, and changes in the storage capacities at ports.     

张崇段沿线生态工程建设方案

对张崇段沿线的取土场生态环境进行评估和分析,结合不同的地理位置、环境、气候及植被等情况,提出合理的生态恢复建议,可供施工单位和建设单位参考.     

Evaluating the effects of bus design on passenger flow: Is agent-based simulation a feasible approach?

In this paper, we propose an agent-based simulation approach that is capable of simulating the flow of passengers on board buses and at bus stops. The intention is that it will be applied during vehicle development to analyze how vehicle design affects passenger flow, and thus also how it affects system performance such as dwell time. In turn, this could aid the developers in making design decisions early in the development process. Besides introducing the simulation tool itself, the paper explores the realism of the data generated by the tool. A number of passenger flow experiments featuring a full-scale bus mockup and 50 participants were carried out. The setup of these experiments mirrored a number of ‘bus journeys’ (regarding vehicle design, number of passengers boarding/alighting at each stop and so on) that had previously been simulated using the simulation tool. When the data from the simulations were compared with the data from the passenger flow experiments, it could be concluded that the tool is indeed able to generate realistic passenger flows, although with some errors when a large number of passengers board/alight. The simulated dwell times were rationally affected by the tested bus layout aspects. It was concluded that the tool makes it possible to evaluate how variations in bus layouts affect passenger flow, providing data of sufficiently high quality to be useful in early phases of vehicle design.     

基于GRNN的GSM-R场强覆盖预测算法

在比较Hata模型修正方法和GRNN算法场强覆盖预测效果的基础上,仿真分析了训练集构成和平滑因子选择对GRNN算法预测效果的影响,给出了训练集构成和平滑因子选择的方法;提出了电波传播环境相似系数来表征GRNN模型在不同环境下的适用性。仿真结果表明,两种传播环境的相似系数越大,由一种环境下测试数据确定的GRNN在另一环境下的预测精度越高。     

信号采样理论在交通流检测点布设中的应用

在对交通流检测点布设领域研究应用现状进行分析与抽象的基础上,提出交通流检测点布设本质上属于空间交通流信号采样问题。依据信号采样理论,建立了确定检测点间距或密度的方法与流程,该流程包括空间交通流信号产生、离散傅里叶变换、频谱分析、间距确定、误差分析5个步骤。对高速公路拥挤状态下的仿真分析表明:100 m的检测点间距可以满足对拥挤交通流状态的真实检测,该数值接近于实际应用中的最小值(125 m),说明该理论方法具有较好的实用性。     

暗挖大型换乘地铁车站施工关键技术及对策

结合沈阳地铁青年大街站工程实际，介绍了暗挖洞桩法的主要施工步骤及要点。青年大街站结构复杂，洞桩法施工增加了工程的安全性和稳定性，可减少施工产生的变形，有效保护临近建（构）筑物。     

基于Q学习的Agent在单路口交通控制中的应用

将Agent技术与Q学习算法相结合,应用到城市交通控制领域中,对单交叉口的交通流进行了控制研究,介绍了路口Agent的结构模型以及基于Q学习算法的学习机制的实现,提出了一种适用于交通控制的奖惩函数。即当红灯相位的饱和度大于绿灯相位的饱和度时,红灯相位的相对警界度在奖惩函数中占主导地位,此时大部分情况下会对Agent进行惩罚;在以后的决策过程中面对类似的交通状态Agent所选择的控制行为更倾向于将通行权切换给下一个相位,反之,Agent所选择的行为倾向于保持当前相位的通行权到下一决策时刻。并通过微观交通仿真软件Paramics对控制算法进行仿真研究,仿真结果表明该方法的控制效果优于定时控制,同时验证了奖惩函数的有效性。