Heteroscedastic Gaussian processes for uncertainty modeling in large-scale crowdsourced traffic data

Accurately modeling traffic speeds is a fundamental part of efficient intelligent transportation systems. Nowadays, with the widespread deployment of GPS-enabled devices, it has become possible to crowdsource the collection of speed information to road users (e.g. through mobile applications or dedicated in-vehicle devices). Despite its rather wide spatial coverage, crowdsourced speed data also brings very important challenges, such as the highly variable measurement noise in the data due to a variety of driving behaviors and sample sizes. When not properly accounted for, this noise can severely compromise any application that relies on accurate traffic data. In this article, we propose the use of heteroscedastic Gaussian processes (HGP) to model the time-varying uncertainty in large-scale crowdsourced traffic data. Furthermore, we develop a HGP conditioned on sample size and traffic regime (SSRC-HGP), which makes use of sample size information (probe vehicles per minute) as well as previous observed speeds, in order to more accurately model the uncertainty in observed speeds. Using 6 months of crowdsourced traffic data from Copenhagen, we empirically show that the proposed heteroscedastic models produce significantly better predictive distributions when compared to current state-of-the-art methods for both speed imputation and short-term forecasting tasks.     

Balancing energy consumption and risk of delay in high speed trains: A three-objective real-time eco-driving algorithm with fuzzy parameters

Eco-driving is an energy efficient traffic operation measure that may lead to important energy savings in high speed railway lines. When a delay arises in real time, it is necessary to recalculate an optimal driving that must be energy efficient and computationally efficient.In addition, it is important that the algorithm includes the existing uncertainty associated with the manual execution of the driving parameters and with the possible future traffic disturbances that could lead to new delays.This paper proposes a new algorithm to be executed in real time, which models the uncertainty in manual driving by means of fuzzy numbers. It is a multi-objective optimization algorithm that includes the classical objectives in literature, running time and energy consumption, and as well a newly defined objective, the risk of delay in arrival. The risk of delay in arrival measure is based on the evolution of the time margin of the train up to destination.The proposed approach is a dynamic algorithm designed to improve the computational time. The optimal Pareto front is continuously tracked during the train travel, and a new set of driving commands is selected and presented to the driver when a delay is detected.The algorithm evaluates the 3 objectives of each solution using a detailed simulator of high speed trains to ensure that solutions are realistic, accurate and applicable by the driver. The use of this algorithm provides energy savings and, in addition, it permits railway operators to balance energy consumption and risk of delays in arrival. This way, the energy performance of the system is improved without degrading the quality of the service.     

Ontologies for transportation research: A survey

Transportation research relies heavily on a variety of data. From sensors to surveys, data supports day-to-day operations as well as long-term planning and decision-making. The challenges that arise due to the volume and variety of data that are found in transportation research can be effectively addressed by ontologies. This opportunity has already been recognized – there are a number of existing transportation ontologies, however the relationship between them is unclear. The goal of this work is to provide an overview of the opportunities for ontologies in transportation research and operation, and to present a survey of existing transportation ontologies to serve two purposes: (1) to provide a resource for the transportation research community to aid in understanding (and potentially selecting between) existing transportation ontologies; and (2) to identify future work for the development of transportation ontologies, by identifying areas that may be lacking.     

三轴船舶电动摇摆模拟试验台研究

针对船舶摇摆模拟试验台系统在科学研究和船载仪器可靠性试验中的应用,设计了一种多功能三轴船舶电动摇摆试验台随动控制系统。首先对摇摆试验台进行控制建模,确定电流、速度、位置三闭环控制方案,然后采用常规PID算法设计三环控制器参数,对位置环用模糊自适应PID控制器进行优化设计。提出以变周期、变幅度和组合曲线给定的摇摆方法模拟风、浪、流干扰,对系统进行仿真研究。仿真试验结果表明,设计的系统具有响应迅速、模拟准确、可靠等特点,能够较好的模拟实际海况中船舶摇摆运动,为搭建实际试验平台奠定了基础。     

地铁列车逻辑控制电路安全服役技术应用研究

为克服传统地铁列车继电器控制电路高故障率和无记录功能等诸多缺陷,提出了基于新型二乘二取二技术的无触点逻辑控制方案.完成了系统架构设计包括热备冗余、网络通信、故障诊断、日志分析等功能.针对既有地铁列车进行了控制电路技术方案设计和施工改造,首先在分析原有控制回路原理的基础上,完成无触点逻辑控制单元替代继电器点位设计;然后综...     

船舶推进轴系设计的模糊综合评估

采用模糊综合评估方法对推进轴系设计进行综合评估。重点介绍推进轴系综合评估的结构模型的建立,应用层次分析法（AHP）计算各评估指标的权重,并简单介绍主要指标因素隶属度函数的研究。对某船两套推进轴系设计方案进行了具体的计算评估。结果表明,本方法可较好地评估船舶推进轴系设计。     

设备拥有量模型的研究

通过对设备完好率、设备出勤台数和设备拥有量三者之间的关系进行深入的分析,找出三者之间的单值对应关系,采用线性回归、最优化理论、曲面拟合等数学方法并结合计算机软件建立设备拥有量的计算模型,并对此模型进行更深入的分析,建立其分段模型,从而保证了模型的计算精度,为企业的设备投资提供科学的准确的定量分析依据。     

Investigating micro-simulation error in activity-based travel demand forecasting: a case study of the FEATHERS framework

Activity-based models of travel demand have received considerable attention in transportation planning and forecasting in recent years. However, in most cases they use a micro-simulation approach, thereby inevitably including a stochastic error that is caused by the statistical distributions of random components. As a consequence, running a transport micro-simulation model several times with the same input will generate different outputs, which baffles practitioners in applying such a model and in interpreting the results. A common approach is therefore to run the model multiple times and to use the average value of the results. The question then becomes: what is the minimum number of model runs required to reach a stable result? In this paper, systematic experiments are carried out using Forecasting Evolutionary Activity-Travel of Households and their Environmental RepercussionS (FEATHERS), an activity-based micro-simulation modelling framework currently implemented for the Flanders region of Belgium. Six levels of geographic detail are taken into account. Three travel indices – average daily activities per person, average daily trips per person and average daily distance travelled per person, as well as their corresponding segmentations – are calculated by running the model 100 times. The results show that the more disaggregated the level, the larger the number of model runs is needed to ensure confidence. Furthermore, based on the time-dependent origin-destination table derived from the model output, traffic assignment is performed by loading it onto the Flemish road network, and the total vehicle kilometres travelled in the whole Flanders are subsequently computed. The stable results at the Flanders level provides model users with confidence that application of FEATHERS at an aggregated level requires only limited model runs.     

基于单片机和Fuzzy技术的液压在线故障监测系统的设计

介绍了基于单片机和Fuzzy技术的液压在线故障监测诊断系统的设计,给出了系统组成和软件设计。该系统以高性能单片机为核心,采用Fuzzy逻辑分析技术实现了液压系统故障诊断的基本结构和知识库的方法,建立了液压系统故障Fuzzy分析的逻辑结构,实验表明,该系统提高了液压系统故障推理的正确性和推理速度。     

Development of railway station choice models to improve the representation of station catchments in rail demand models

ABSTRACT

This paper describes the development of railway station choice models suitable for defining probabilistic station catchments. These catchments can then be incorporated into the aggregate demand models typically used to forecast demand for new rail stations. Revealed preference passenger survey data obtained from the Welsh and Scottish Governments was used for model calibration. Techniques were developed to identify trip origins and destinations from incomplete address information and to automatically validate reported trips. A bespoke trip planner was used to derive mode-specific station access variables and train leg measures. The results from a number of multinomial logit and random parameter (mixed) logit models are presented and their predictive performance assessed. The models were found to have substantially superior predictive accuracy compared to the base model (which assumes the nearest station has a probability of one), indicating that their incorporation into passenger demand forecasting methods has the potential to significantly improve model predictive performance.