Daily activity pattern recognition by using support vector machines with multiple classes

The focus of this paper is to learn the daily activity engagement patterns of travelers using Support Vector Machines (SVMs), a modeling approach that is widely used in Artificial intelligence and Machine Learning. It is postulated that an individual’s choice of activities depends not only on socio-demographic characteristics but also on previous activities of individual on the same day. In the paper, Markov Chain models are used to study the sequential choice of activities. The dependencies among activity type, activity sequence and socio-demographic data are captured by employing hidden Markov models. In order to learn model parameters, we use sequential multinomial logit models (MNL) and multiclass Support Vector Machines (K-SVM) with two different dependency structures. In the first dependency structure, it is assumed that type of activity at time ‘t’ depends on the last previous activity and socio-demographic data, whereas in the second structure we assume that activity selection at time ‘t’ depends on all of the individual’s previous activity types on the same day and socio-demographic characteristics. The models are applied to data drawn from a set of California households and a comparison of the accuracy of estimation of activity types and their sequence in the agenda, indicates the superiority of K-SVM models over MNL. Additionally, we show that accuracy in estimating activity patterns increases using different sets of explanatory variables or tuning parameters of the kernel function in K-SVM.     

A survey on planning semi-flexible transit systems: Methodological issues and a unifying framework

When demand for transportation is low or sparse, traditional transit cannot provide efficient and good-quality service, due to its fixed structure. New transportation alternatives are therefore increasingly proposed, combining on-demand service adjustment capabilities to the regular route and schedule characteristics of traditional transit. Such so-called semi-flexible systems require careful planning, but no formalization of the corresponding decisions problems, nor any comprehensive methodology has been proposed yet. This paper aims at contributing to fill this gap by presenting a comprehensive literature review, and a general and unifying modeling framework for representing and planning semi-flexible systems. The latter takes the form of the Demand Adaptive Systems, which generalizes the semi-flexible systems described in the literature, and also offers a number of advanced features, the scheduling mechanism, in particular. The paper then provides a classification of planning decisions, which is used to structure a comprehensive and comparative literature review of the field of semi-flexible systems, including methodological contributions as well as a number of particularly significant practical experiences.     

Is the provision of park-and-ride facilities at light rail stations an effective approach to reducing vehicle kilometers traveled in a US context?

Park-and-Ride (PNR) facilities are a commonly used means of making a transit system more widely available. However, given that a PNR passenger must drive for part of the trip, this approach to transit provision has an ambiguous influence on vehicle kilometers traveled (VKT). The impact of PNR on VKT is highly dependent of how PNR users would choose to travel if the PNR facilities were not available. Given that this issue has received little attention in a US context, we use the light rail system in Charlotte, North Carolina as a case study to examine the potential impact of PNR removal on VKT. Using a travel survey of PNR passengers, we estimate the VKT currently generated while driving to and from the rail stations and then estimate how VKT would change under various PNR removal scenarios that assume different behavioral responses. We find that, under the most realistic scenarios, PNR removal would lead the average PNR passenger to increase her driving by 8–15 VKT per round trip.     

Virtual durability test rigs for automotive engineering

In recent years so-called ‘virtual test rigs’ have become more and more important in the development process of cars and trucks. Originally, the idea was to substitute expensive durability tests with computer simulation. Meanwhile, the focus has changed towards a more cooperative usage of numerical and laboratory rig simulation. For many safety critical issues laboratory tests remain indispensable. In early development stages, when no physical prototypes are available yet, numerical simulation is used to analyse and optimise the design. In this paper, we show how to build numerical simulation models of complex servo-hydraulic test systems and their test specimen using multi-body simulation for the mechanics in combination with simulation models for the hydraulics and controls. We illustrate this at two industrial application examples: a spindle-coupled passenger car suspension rig and a tyre-coupled full vehicle rig. We show how the simulation models are used to design and optimise better test rigs and to support the test rig operation by preparing the physical tests with new specimen, i.e. by performing numerical simulations including numerical drive file iteration before the physical tests start.     

基于分形插值方法的城市轨道交通车站客流拟合与仿真

城市轨道交通车站客流量的变化具有复杂的非线性特点,通过对某些车站一天的客流量时间序列的分析,发现其客流量的变化具有自相似性,并且满足某种拟周期性。本文采用迭代函数系统模型描述城市轨道交通车站客流量的变化特征,用计算机自动求解该迭代函数系统的相关参数,在此基础上采用分形插值的方法模拟产生动态的客流。通过与实际客流调查数据的对比分析可以看出,该方法模拟产生的客流不仅与实际客流较好地吻合,而且能更好地描述客流的非线性特征。     

An assessment of the performance of the European long intermodal freight trains (LIFTS)

Intermodal rail/road freight transport has always been considered as a competitive alternative to its road freight counterpart in the European medium- to long-distance corridors (markets). Such consideration has been based on the increasing competitiveness of some innovative rail services and the existing and prospective performance of both modes in terms of the full social – internal or operational and external – costs. The most recent innovation of rail technologies and related services launched by some European railway companies, still at the conceptual level, is the Long Intermodal Freight Train (LIFT). This is supposed to be a block train operating in long-distance corridors (markets) with a substantial and regular freight demand.This paper develops analytical models for assessing the performance of the LIFTs, the already-operating Conventional Intermodal Freight Trains (CIFTs), and their road counterpart as well. The performance consists of the full – internal (private) and external – costs of the door-to-door delivery of loading units – containers, swap-bodies, and semi-trailers. The internal costs embrace the operational costs of the transport (rail and road) and intermodal terminal operators. The external costs include the costs of the impacts of door-to-door delivery of loading units on society and the environment. These negative externalities include noise, air pollution, traffic accidents, and congestion.The models are applied to a simplified version of intermodal and road transport system using inputs from the European freight transport sector. The aims are to compare the full costs of particular modalities in order to investigate the potential of the LIFTs as compared with the CIFTs in improving the internal efficiency of the rail freight sector and its competitiveness with respect to its road counterpart. In addition, the paper attempts to assess some effects on the potential modal shift of EU (European Union) transport policies on internalizing transport externalities.     

辊压成型设备在客车蒙皮制造中的应用

介绍几种不同结构的辊压成型设备及其在客车蒙皮制造中的应用，以满足客车不同部位蒙皮成型的要求。     

客车底盘纵梁数控冲孔生产线

简要介绍客车底盘纵梁数控冲孔生产线的发展历史与现状；着重介绍SPU12—32-4型汽车U型纵梁三面数控冲孔生产线和SPTB120—10型纵梁数控平板冲孔生产线的特点。     

基于定量分析的城市轨道交通与土地利用一体规划研究

随着城市化进程的加快,大都市交通拥堵现象日益严重,规划建设城市轨道交通已经成为许多城市解决交通拥堵、促进经济发展的迫切需求。城市轨道交通建设与城市土地利用是互馈关系,文章介绍3种定量研究方法,在定量分析的基础上,探讨了轨道交通车站、线路和线网的定量一体规划,最后提出轨道交通与土地利用定量一体规划以点、线、面分级考虑的一些建议。