Analyzing passenger train arrival delays with support vector regression

We propose machine learning models that capture the relation between passenger train arrival delays and various characteristics of a railway system. Such models can be used at the tactical level to evaluate effects of various changes in a railway system on train delays. We present the first application of support vector regression in the analysis of train delays and compare its performance with the artificial neural networks which have been commonly used for such problems. Statistical comparison of the two models indicates that the support vector regression outperforms the artificial neural networks. Data for this analysis are collected from Serbian Railways and include expert opinions about the influence of infrastructure along different routes on train arrival delays.     

Transport resilience and vulnerability: The role of connectivity

This paper aims to adopt a critical stance on the relevance and interpretation of the recently emerging concepts of resilience and vulnerability in transportation studies. It makes a clear distinction between engineering and ecological interpretations of these concepts and offers a systematic typology of various studies in this field. A core element in the study is the linkage between the aforementioned concepts and connectivity/accessibility in transport networks. The methodological findings in the study are put in perspective by addressing also such concepts as robustness, reliability and friability of transport systems.     

Analysis of air traffic control operational impact on aircraft vertical profiles supported by machine learning

The Air Traffic Management system is under a paradigm shift led by NextGen and SESAR. The new trajectory-based Concept of Operations is supported by performance-based trajectory predictors as major enablers. Currently, the performance of ground-based trajectory predictors is affected by diverse factors such as weather, lack of integration of operational information or aircraft performance uncertainty.Trajectory predictors could be enhanced by learning from historical data. Nowadays, data from the Air Traffic Management system may be exploited to understand to what extent Air Traffic Control actions impact on the vertical profile of flight trajectories.This paper analyses the impact of diverse operational factors on the vertical profile of flight trajectories. Firstly, Multilevel Linear Models are adopted to conduct a prior identification of these factors. Then, the information is exploited by trajectory predictors, where two types are used: point-mass trajectory predictors enhanced by learning the thrust law depending on those factors; and trajectory predictors based on Artificial Neural Networks.Air Traffic Control vertical operational procedures do not constitute a main factor impacting on the vertical profile of flight trajectories, once the top of descent is established. Additionally, airspace flows and the flight level at the trajectory top of descent are relevant features to be considered when learning from historical data, enhancing the overall performance of the trajectory predictors for the descent phase.     

Integrated planning of static and dynamic charging infrastructure for electric vehicles

This paper investigates the optimal deployment of static and dynamic charging infrastructure considering the interdependency between transportation and power networks. Static infrastructure means plug-in charging stations, while the dynamic counterpart refers to electrified roads or charging lanes enabled by charging-while-driving technology. A network equilibrium model is first developed to capture the interactions among battery electric vehicles’ (BEVs) route choices, charging plans, and the prices of electricity. A mixed-integer bi-level program is then formulated to determine the deployment plan of charging infrastructure to minimize the total social cost of the coupled networks. Numerical examples are provided to demonstrate travel and charging plans of BEV drivers and the competitiveness of static and dynamic charging infrastructure. The numerical results on three networks suggest that (1) for individual BEV drivers, the choice between using charging lanes and charging stations is more sensitive to parameters including value of travel time, service fee markup, and battery size, but less sensitive to the charging rates and travel demand; (2) deploying more charging lanes is favorable for transportation networks with sparser topology while more charging stations can be more preferable for those denser networks.     

一类大规模运输网络多阶段随机规划配流模型

利用随机规划理论，分析大规模运输网络的基本特性及优化，是近几年交通运输领域发展起来的一种新的研究方向，已广泛地应用于交通运输管理的各个部门。本文在分析了一类大规模运输网络在市场经济模式下的基本特性的基础上，提出了一类适用范围更广、更复杂的多阶段和广义多阶段随机规划配流模型。     

A Novel Evolutionary Feedforward Neural Network with Artificial Immunology

A hybrid algorithm to design the multi-layer feedforward neural network was proposed. Evolutionary programming is used to design the network that makes the training process tending to global optima. Artificial im-munology combined with simulated annealing algorithm is used to specify the initial weight vectors, therefore im-proves the probabiligy of training algorithm to converge to global optima. The applications of the neural network in the modulation-style recognition of analog modulated rader signals demonstrate the good performance of the network.     

主动磁轴承的神经网络辨识研究

简述了主动磁轴承的工作原理及数学模型,在传统系统辨识的基础上提出了基于BP神经网络的非线性辨识方案.通过闭环控制使转子稳定悬浮,并在控制器的输出信号中加入随机噪声,以使系统被充分激励.按照10 kHz的采样频率对磁轴承的I/O数据进行采样,以用于磁轴承特性的辨识.对某单自由度磁轴承的仿真表明,神经网络模型能够以很高的精度逼近磁轴承的输入输出数据,且对不同的输入信号有较好的泛化能力,验证了所提方案的有效性.     

电子商务综合发运跟踪系统的研究

基于中国电子商务和物流业的发展现状，提出了采用3层开发模型实现综合发运跟踪服务的设计方案，详细讨论了数据库表设计、应用系统间信息的表示和处理、基于2层隧道协议（Layer 2 Tunneling Protocol,L2TP)的拨号虚拟专用网（Virtual Private Network,VPN)技术的网络结构设计和查询反馈关键技术的实现问题。     

具有反应扩散的神经网络的稳定性分析

通过构造适当的平均Luapunov函数，利用M矩阵理论，研究了一类具有反应扩散的Hopfield神经网络的全局稳定性．在放松神经网络的激活函数的有界性、单调递增性和可微性的条件下，得到了神经网络的全局渐近稳定的条件．这些条件适合于神经网络的关联矩阵为对称或非对称矩阵、激活函数为非单调的情况．     

��ͨ�������縴���Լ������������о�

按照网络拓扑结构特征划分，我们经常接触到的实际网络有完全规划网络（Completely Regular Networks）、安全随机网络（Completely Random Networks）、小世界网络（Small-world Networks）和无标度网络(Scale-free Networks)．系统地对无标度网络的形成、特性和代表性研究成果进行简要总结，重点探讨交通运输网络的复杂性和相关问题，研究了城市公交网络的无标度特性及度分布指数，并以北京市公交网络为例完成了实证分析．进一步从理论上给出了怎样找到公交网络中的枢纽站点这一难题的研究思路、整体框架及求解算法，这是交通运输网络复杂性及其相关问题研究的关键．还分别从理论与应用两个层面给出了下一步研究工作的总体思路，为交通管理部门进行交通运输网络规划、设计、建设和管理提供了科学的研究手段和理论支持．