Forecasting daily passenger traffic volumes in the Moscow metro

In this paper we have developed a methodology for the medium-term prediction of daily volumes of passenger traffic in the Moscow metro. It includes three options for the forecast: (1) based on artificial neural networks (ANNs), (2) singular-spectral analysis implemented in the Caterpillar–SSA package, and (3) a combination of the ANN and Caterpillar–SSA approaches. The methods and algorithms allow the mediumterm forecasting of passenger traffic flows in the Moscow metro with reasonable accuracy.     

基于能力区域的交通状态预测方法

交通状态预测是交通流诱导和交通信息发布系统的重要依据.本文提出了一种基于能力区域的城市快速路交通状态预测方法,该方法通过构建神经网络分类器的能力区域,根据样本数据与交通状态类簇之间的空间距离,预测道路交通状态等级.神经网络分类器的能力区域能够有效融合时间、空间等多种特征,并且不需要考虑各特征之间的相关性,具有很强的适应性.实验结果表明,与经典的预测方法相比,其预测误差明显降低,均等系数增大,基于能力区域的方法预测交通状态具有较高的准确性.     

Some insights on the recent spate of accidents in Indian Railways

Indian Railways (IR), the largest rail passenger carrier in the world, has experienced 11 major accidents due to derailment or collision between trains in the year 2010, leading to several human casualties and large-scale disruptions in traffic. Alarmingly, 8 of these 11 accidents have occurred within a specific geographical region known as the Indo-Gangetic plain. In order to identify the general causes of such frequent accidents, and the specific factors leading to repeated accidents in a particular region, we systematically collect and analyze data of IR traffic over the last two decades. We find that there has been an unbalanced growth in IR traffic in the Indo-Gangetic plain over the last two decades, and consequently most of the high-traffic rail-routes presently lie in this region. However, construction of new tracks and train-routes has been nominal compared to the increase in traffic, leading to frequent congestion and over-utilization of existing tracks. Modeling the traffic-flow using computer simulations, we also show that if all trains were to travel in accordance with the IR schedule, the present infrastructure would be insufficient to handle the resultant traffic-flow in some of the high-traffic routes. Hence this study reflects some of the inherent problems in the scheduling of trains and evolution of IR, and also identifies several regions where traffic is likely to exceed safe limits.     

基于模糊神经网络的短时交通流预测方法研究

为满足交通控制和诱导系统的实时性需求,减少交通拥挤状况,降低交通事故突发频率,需要对短时交通流进行预测。当前的短时交通流预测方法是采用K-近邻的非参数回归对其进行预测,预测过程中没有将预测模型中关键因素对交通流的影响进行详细的说明,导致预测结果不准确,存在短时交通流预测误差较大的问题。为此,提出一种基于模糊神经网络的短时交通流预测方法。该方法首先以历史短时交通流数据样本序列为基础,将提取的关联维数作为短时交通流的混沌特征量,然后以该特征量为依据,对短时交通流数据进行聚类,使相同的短时交通流聚合类样本比不同的交通流聚合类样本更为贴近,采用高斯过程回归对短时交通流预测模型进行建设,建设过程中利用差分方法对短时交通流预测序列进行平稳化操作之后,对短时交通流预测模型进行训练,将GPR模型引入至短时交通流预测过程中,得到交通流预测方差估计值,并确定交通流预测值置信区间,由此实现短时交通流的预测。由此实现短时交通流的预测。实验结果证明,所提方法可以准确地预测交通运输系统的实时状况,为车辆行驶的最佳路线进行了有效引导,减少了自然影响方面和人为因素对短时交通流预测结果的干扰,为交通部门对交通路况的控制管理提供了依据。     

A Calculation Method of Passenger Flow Distribution in Large-Scale Subway Network Based on Passenger–Train Matching Probability

The ever-increasing travel demand has brought great challenges to the organization, operation, and management of the subway system. An accurate estimation of passenger flow distribution can help subway operators design corresponding operation plans and strategies scientifically. Although some literature has studied the problem of passenger flow distribution by analyzing the passengers’ path choice behaviors based on AFC (automated fare collection) data, few studies focus on the passenger flow distribution while considering the passenger–train matching probability, which is the key problem of passenger flow distribution. Specifically, the existing methods have not been applied to practical large-scale subway networks due to the computational complexity. To fill this research gap, this paper analyzes the relationship between passenger travel behavior and train operation in the space and time dimension and formulates the passenger–train matching probability by using multi-source data including AFC, train timetables, and network topology. Then, a reverse derivation method, which can reduce the scale of possible train combinations for passengers, is proposed to improve the computational efficiency. Simultaneously, an estimation method of passenger flow distribution is presented based on the passenger–train matching probability. Finally, two sets of experiments, including an accuracy verification experiment based on synthetic data and a comparison experiment based on real data from the Beijing subway, are conducted to verify the effectiveness of the proposed method. The calculation results show that the proposed method has a good accuracy and computational efficiency for a large-scale subway network.     

Passenger management strategy and evacuation in subway station under Covid-19

Under the background of Covid-19 sweeping the world, safe and reasonable passenger flow management strategy in subway stations is an effective means to prevent the spread of virus. Based on the social force model and the minimum cost model, the movement and path selection behavior of passengers in the subway station are modeled, and a strategy for passenger flow management to maintain a safe social distance is put forward. Take Qingdao Jinggangshan Road subway station of China as the simulation scene, the validity of the simulation model is verified by comparing the measured value and simulation value of the time required for passengers from getting off the train to the ticket gate. Simulation results indicate that controlling the time interval between incoming passengers at the entrance can effectively control the social distance between passengers and reduce the risk of epidemic infection. By comparing the evacuation process of passengers under different initial densities, it is found that the greater the initial density of passengers is, the longer the passengers are at risk social distance. In the process of passenger emergency evacuation, the stairs/escalators and ticket gates are bottleneck areas with high concentration of passenger density, which should be strictly disinfected many times on the basis of strictly checking the health code of incoming passengers and controlling the arrival time interval. The simulation results of this paper verify the harmfulness of passenger emergency evacuation without protective measures, and provide theoretical support for the operation and management of subway station under the epidemic situation.     

固定闭塞系统中列车流的特性分析

在NS模型的基础上，针对轨道交通的特点，本文提出一种用于模拟四显示固定闭塞系统的元胞自动机模型.应用该模型模拟四显示固定闭塞系统中的列车延迟的交通现象，分析了四显示固定闭塞系统中的发车时间间隔、客货车比例、车站停靠时间、停靠站台数量等因素对列车平均延迟时间的影响.结果表明：客、货车混行时，货车对后行客车的运行会产生抑制作用，调整客、货车在车站的停靠时间可有效缓解这种抑制作用，减少客车的延迟时间；增加停靠站台的数量可提高线路上的车流密度，缓解车流延误，但在较大的发车时间间隔时，站台的利用率会降低. 关键词： 元胞自动机 固定自动闭塞系统 列车延迟     

典型城市地铁站台噪声满意度*

地铁是城市轨道交通重要组成部分,地铁站台噪声对乘客身心健康有重要影响。以合肥轨道交通一号线为例,具体选择地下侧式、地下双岛式和地下岛式3个典型空间类型的地铁站台为研究对象,通过噪声测量和问卷调查相结合的方法,针对地铁在不同运营时段的乘客站台噪声满意度与噪声声元素舒适度进行评价,探讨性别、声元素舒适度以及站台噪声对乘客噪声满意度的影响。结果表明：对地铁站台噪声满意度评价,乘客性别差异不显著;在乘车高峰期时段,地铁站台广播提示声、地铁工作人员吹哨声、列车进站声和列车出站声是影响乘客站台噪声满意度主观评价的主要噪声声元素;乘客噪声满意度主观评价与站台噪声值呈强负相关,噪声值越高,满意度越低;乘客噪声满意度为可接受时的地铁站台噪声阈值,在乘车高峰期时段为74 dB(A),非高峰期时段为67 dB(A)。该文工作可为城市地铁站台噪声满意度评价及其空间结构设计提供科学参考。     

Phase states of traffic flows in linear tunnels. Analysis of empirical data

The empirical data on traffic flows collected in the linear portion of the Lefortovsky tunnel of the third Moscow transport ring were analyzed. It was shown that the crowded traffic observed in the tunnel is indeed characterized by the synchronized vehicular traffic. In particular, long-range spatial correlations in their motion velocities and the region of “widely scattered states”, i.e., two typical properties of the synchronized vehicular traffic phase, were detected in the fundamental diagram. Moreover, the phase diagram of the traffic flow dynamics showed two regions with essentially different properties, which are separated by a narrow layer with a virtually fixed vehicle density. One of them corresponds to synchronized vehicular traffic and contains a core of chaotic dynamics. Another region corresponds to irreversible formation of wide moving jams.     

Networked analysis of the Shanghai subway network,in China

Recently, cities have become larger and larger, and more and more people are living in large cities. This phenomenon has caused serious traffic congestion which is very detrimental to the development of large cities. In this context, the subway has become the most effective solution for relieving traffic congestion and subways have been constructed in many cities, so the reliability and robustness of subways should be guaranteed. In this paper, Shanghai subway network, in China, will be analyzed and investigated; the topological characteristics and functional properties can be studied in order to assess the reliability and robustness. The topological characteristics can be measured using several parameters; meanwhile the fraction of removed nodes of Shanghai subway network is discussed and compared against that for a random network, and the critical threshold of this fraction is obtained. Two novel parameters called the functionality loss and connectivity of subway lines are proposed for measuring the transport functionality and the connectivity of subway lines. Subway lines 4 and 7 are selected as examples for evaluating the connectivity of lines subjected to different attack protocols. This study indicates that the subway network is robust against random attacks but fragile for malicious attacks, and the highest betweenness node-based attacks can cause the most serious damage to subway networks among the different attack protocols.     

Navigation in large subway networks: An informational approach

The structural properties of the subway network are crucial in effective transportation in cities. This paper presents an information perspective of navigation in four different subway networks: New York City, Paris, Barcelona and Moscow. We addressed our study to investigate what is that makes it complicated to navigate in these kinds of networks and we carried out a comparison between them and their intrinsic constraints. Our methodological approach is based on a set of cost/efficiency indicators which are defined in the complex networks literature. We find that the overall complexity in finding stations measured by the average search information S linearly increases as a function of the network size N. The direct implication of this finding is that from these basic levels of required information, the average value H(k) can be represented as a function of the node degree k. Finally, through analyzing subway networks in space P, we reveal the existing service modularity among subway routes using a rescaled expression of S.     

大数据环境下地铁自动售检票系统设计与实现

近年来,随着经济领域蓬勃发展,我国加快了现代化建设进程,交通设施建设不断推进;受互联网大数据技术变革的影响,传统地铁售检票系统无法满足高客流量、大数据流处理的高强度工作要求;在日常实践应用中,传统地铁售检票系统经常出现检票识别率低、售票信息运算处理响应速度慢、多人员、多任务操作执行准确率差的问题;针对上述问题,结合大数据资源运算能力,提出大数据环境下地铁自动售检票系统设计;采用大数据实名高检处理引擎(VBDKG)、多路分处运算模组(ICGRU)与动态身份比对算法(DBTDE),针对传统地铁自动售检票系统存在的问题进行解决;通过仿真实验测试证明,提出的大数据环境下地铁自动售检票系统设计具有较强的实施性与可操作性;同时,运行处理准确性高,运行稳定。     

Statistical analysis of the Metropolitan Seoul Subway System: Network structure and passenger flows

The Metropolitan Seoul Subway system, consisting of 380 stations, provides the major transportation mode in the metropolitan Seoul area. Focusing on the network structure, we analyze statistical properties and topological consequences of the subway system. We further study the passenger flows on the system, and find that the flow weight distribution exhibits a power-law behavior. In addition, the degree distribution of the spanning tree of the flows also follows a power law.     

An optimal network for passenger traffic

The optimal solution of an inter-city passenger transport network has been studied using Zipf’s law for the city populations and the Gravity law describing the fluxes of inter-city passenger traffic. Assuming a fixed value for the cost of transport per person per kilometer we observe that while the total traffic cost decreases, the total wiring cost increases with the density of links. As a result the total cost to maintain the traffic distribution is optimal at a certain link density which vanishes on increasing the network size. At a finite link density the network is scale-free. Using this model the air-route network of India has been generated and an one-to-one comparison of the nodal degree values with the real network has been made.     

含有误差校正的小波神经网络交通流量预测

交通流量的准确预测对于高速路管理者进行决策至关重要。建立了小波神经网络(WNN)交通流量预测模型,并通过预测训练误差和测试误差校正预测结果来提高预测精度。首先构建WNN模型对交通流量进行初步预测,然后利用经验模态分解(EMD)和WNN模型对训练误差和测试误差进行预测。分别用训练误差预测值、测试误差预测值和两种误差预测值的加权对流量初步预测结果进行修正得到最终预测值。采用四川省成灌高速路交通流量数据进行了仿真对比实验,仿真结果表明含有误差校正的小波神经网络模型能有效提高交通流量预测精度,并且利用两种误差加权修正模型的预测精度高于利用测试误差的修正模型和利用训练误差的修正模型。     

混合交通流元胞自动机FI模型的能耗研究

研究了在周期边界条件下,最大速度、混合比例、车辆长度、随机减速概率对(fukui-ishibashi,FI)交通流模型能耗的影响.数值模拟结果表明,FI交通流模型的能耗随着车辆最大速度的增大而增加;随着混合比C的增大而增加,长车的比例越多能耗越大;随长车车长的增长而增加.FI交通流模型的能耗不同于NaSch模型能耗,对于FI交通流模型,在最大流量之处交通能耗发生下降的突变趋于零,其左右各存在交通能耗极大值.     

双出口房间人群疏散的实验研究和数学建模

本文设计了一个双出口房间内人群疏散的实验方案,通过不同条件下疏散过程的实况录像及视频检测,得到不同人数疏散时间的许多定量结果.提出了双出口房间吸引区间的概念,证明了较小出口吸引区间的边界总是一段圆弧,可以解释行人流出口处的圆形成拱现象.通过类比地铁候车厅内人群疏散过程,建立了双出口房间内疏散时间的二次函数模型,成功拟合不同条件下的实测数据.疏散人数较少时,疏散时间随着人数增加而线性增长;人数较多,在出口附近出现待行区域时,疏散时间则呈二次函数增长.与一些已知疏散时间数学模型相比,本文模型对出口宽度变化的反应更敏感.     

元胞自动机混合交通流模型的能耗研究

基于元胞自动机交通流NaSch模型,提出元胞自动机混合交通流能耗公式,对混合交通流的能耗进行研究,通过数值模拟研究不同最大速度、不同车长的混合交通流的能耗;研究表明不同车长、不同最大速度以及混合比对混合交通流能耗均有不同的影响. 关键词： 交通流 元胞自动机 能耗 混合交通     

Comparison of efficiency of artificial neural networks for forecasting the geomagnetic activity index Dst

Using artificial neural networks (ANN), we study problems of forecasting the evolution of the geomagnetic D _st index on the basis of parameters of the solar-wind plasma and magnetic field obtained from the OMNI satellite system. Using this sample problem, we compare the neural network modifications with error backpropagation, such as classic network and feedback network. We analyze the efficiency of a feedback in the hidden layer of the Elman neural network which has a dynamic memory due to the time delay. The role of a delay in the input layer of a neural network is studied. It is shown that the forecasting efficiency increases significantly if a feedback in the hidden layer and the time delay in the input layer are used. The hidden-layer feedback and the input-layer time delay reproduce the time delay in the physical problem considered. Using thresholds in activation functions does not influence the ANN efficiency. The solar-wind parameters that have the strongest influence on the geomagnetic-storm formation are found. The influence of the number of hidden-layer neurons on the quality of forecasting the global disturbances in the near-Earth magnetic field is studied. It is pointed out that the networks with error backpropagation allow, after the relevant tuning and learning, fairly efficient forecasting of phenomena similar to geomagnetic storms several hours before a large-scale magnetospheric event. Pedagogical University, Nizhny Novgorod, Russia. Translated from Izvestiya Vysshikh Uchebnykh Zavedenii, Radiofizika, Vol. 43, No. 5, pp. 385–394, May, 2000.