Floating Car Data Based Nonparametric Regression Model for Short-Term Travel Speed Prediction

A K-nearest neighbor （K-NN） based nonparametric regression model was proposed to predict travel speed for Beijing expressway. By using the historical traffic data collected from the detectors in Beijing expressways, a specically designed database was developed via the processes including data filtering, wavelet analysis and clustering. The relativity based weighted Euclidean distance was used as the distance metric to identify the K groups of nearest data series. Then, a K-NN nonparametric regression model was built to predict the average travel speeds up to 6 min into the future. Several randomly selected travel speed data series, collected from the floating car data （FCD） system, were used to validate the model. The results indicate that using the FCD, the model can predict average travel speeds with an accuracy of above 90%, and hence is feasible and effective.

Freight Vehicle Routing Optimization for Sporadic Orders Using Floating Car Data

The increasing popularity of e-commerce brings large volumes of sporadic orders from different customers,which have to be handled by freight trucks and distribution centers. To improve the level of service and reduce the total shipping cost as well as traffic congestions in urban area, flexible methods and optimal vehicle routing strategies should be adopted to improve the efficiency of distribution effort. An optimization solution for vehicle routing and scheduling problem with time window for sporadic orders (VRPTW- S) was provided based on time-dependent travel time extracted from floating car data (FCD) with ArcGIS platform. A VRPTW-S model derived from the traditional vehicle routing problem was proposed, in which uncertainty of customer orders and travel time were considered. Based on this model, an advanced vehicle routing algorithm was designed to solve the problem. A case study of Shenzhen, Guangdong province, China, was conducted to demonstrate the vehicle operation flow,in which process of FCD and efficiency of delivery systems under different situations were discussed. The final results demonstrated a good performance of application of time-dependent travel time information using FCD in solving vehicle routing problems.

A Comprehensive Taxi Assessment Index Using Floating Car Data

With the expansion of urban area and development of taxi system,problems arise,such as low operation efficiency,high taxi idling rate,and long passenger waiting-time. Although various studies have been conducted,only limited overview of the factors towards urban taxi system has been provided. Consequently,a comprehensive evaluation of taxi system is essential for the urban planner to analyze the current situation and take effective measures. This paper,by using Floating Car Data( FCD),proposes a Comprehensive Taxi Assessment Index( CTAI) to quantify the quality of existing urban taxi system with the assistance of Geographic Information System( GIS) technology. The proposed index system extracts and classifies key factors,reflecting the taxi system from the perspectives of operation efficiency,customer and taxi-driver satisfaction. The system contributes to improving the organization and operation of urban taxi system. Based on the data obtained from the city of Shenzhen,Guangdong Province,China,for both weekday and weekends( Dec.,2011),the proposed CTAI was illustrated by using the Principal Component Analysis( PCA) with ArcGIS 10. 0 platform. The results indicate that the system provides a good multi-dimensional view to delve into the existing urban taxi operation, thus to point out the most sensitive indices towards the entire system,which consequently provides guidelines for future improvement and management of urban taxi system.

City Routing Velocity Estimation Model under theEnvironment of Lack of Floating Car Data

After introducing the principle of float car data (FCD), this paper gives the primary flow of pre-handing and map- matching of the FCD. After analyzing the percentage of coverage of FCD on the road network, large quantity of heritage database of routing status is used to estimate the routing velocity when lack of FCD on parts road segments. Multi liner regression model is then put forwarded by considering the spatial correlativity among the road network, and some model parameters are deduced when time series is classified in day and week. Besides, error of velocity probability and error of status probability are achieved based on the result from field testing while the feasibility and reliability of the velocity estimation model is obtained as well. Finally, as a case study in Shanghai center area, the whole routing velocity in the road network is estimated and published in real time.

The Relationship between Road Characteristics and Speed Collected from Floating Car Data

Speed is of great importance to the safety level of a road. Speed choice is strongly influenced by the road environment and the drivers＇ assessment of safe speed level at a specific location. This paper presents an analysis of the relationships between speed and road characteristics and speed and driver characteristics. The analysis is based on big data on speed and driver characteristics combined with data on road characteristics on 49 secondary rural two-lane roads in Denmark. Data is modelled using multivariate linear regression. The results show a primarily influence from road and shoulder width, the extent of road markings and the section lengths on speed. Secondly, they also show the presence of woodland and intersections influencing speed as gender, age of vehicle and time of day do.

考虑载客状态的改进孤立森林浮动车异常数据检测算法

为提高浮动车数据中异常数据检测能力及不同载客状态下的模型检测分析能力,提出基于S-DTA-IIForest(Summation&Difference Third Order Average&Improvement-Isolation Forest)的浮动车数据异常检测算法。构建由相邻两项求和(S)、三阶求和平均差分(DTA)的二维度空间SDTA特征向量;提出差额累计更新和动态区分辨识的改进孤立森林IIForest算法,通过设置停止阈值参数,避免当出现新样本异常值分数大于停止阈值时,仅更新样本不更新孤立森林模型的问题,设计每个二叉树区分辨识度参数,区分辨识度位于停止区间时停止二叉树生长,提高算法收敛性能,以ROC(Receiver Operating Characteristic)曲线下面积AUC(Area Under ROC Cure)、F1-score为指标对模型精度进行对比分析,并以重庆市中心城区学府大道开展实例验证。结果表明:本文S-DTA-IIForest组合算法AUC、F1-score分别为86.63%、0.89,AUC较传统孤立森林IForest(Isolation Forest)提高32.4%,运行效率提高1.29%,具有收敛速度更快、精度更高的优势,载客条件下模型AUC、F1-score较未载客分别提高7.7%、10.8%,组合算法对载客数据有更高的检测精度,且未载客状态数据异常率较载客状态增加71.4%,未载客数据异常率更高。

一种基于FCD的城市道路车流速度估计算法

针对在城市路网中大面积采集交通信息所存在的问题,提出了一种基于浮动车辆数据(floating car data,FCD)的城市道路车流速度估计算法,并通过FCD系统进行交通速度信息的采集.速度估计采用了一种改进的弧段Dijkstra路径寻优算法,在图的弧段-弧段存储结构中考虑了城市路网限制性道路交通信息的表达,并将路网的一些先验信息引入弧段关系结构中,提高了搜索效率和准确性.实验结果论证了所提出方法的有效性和可靠性.

KD-50-I-E平台的FCD并行计算与交通动态诱导

Intelligent traffic system(ITS) is a development trend for urban modern traffic.Active guidance control for urban traffic can relieve increasing traffic congestion pressure effectively.FCD(floating car data) based dynamic guidance for urban traffic is one of the directions of traffic control research.To meet the real-time demand for massive FCD processing,an FCD parallel computing based dynamic traffic guidance approach is presented and implemented.The FCD properties are analyzed in detail.An FCD parallel computing based dynamic traffic guidance system is developed on KD-50-I-E platform.Experimental results demonstrate the effectiveness and feasibility of the proposed approach.

基于FCD和DAB交通信息采集与服务系统研究

城市交通问题日趋严重,交通信息化服务成为了智能交通领域又一热点。基于浮动车(floating car data FCD)和DAB(digital audio broadcasting)的交通信息采集与服务系统,对交通信息数据源、数据处理及信息解码分发至终端等方面进行了研究,阐述了系统总体结构、关键技术、核心算法。该系统通过采集处理、多源数据信息融合、信息发布和信息终端软件开发,采用TPEG(transportprotocol experts group)信息编码技术,编码成二进制码流文件,并传输给DAB数字服务器进行信息分发,进而将交通信息实时传输到移动终端,为出行者提供可靠的、科学的交通信息服务。

FCD大数据并行处理的动态任务调度算法

浮动车数据(floating car data, FCD)技术是大规模城市路网交通流实时采集的有效方法.城市交通的动态诱导和控制需要对海量FCD进行快速处理.鉴于此,提出了FCD并行计算的动态任务调度方法.针对FCD数据包计算时间的不确定性和动态性,根据计算节点的处理能力进行数据包的动态分割,在处理过程中,采用动态任务分配策略以实现计算节点的同步.该方法在龙芯国产大数据一体机平台上进行了实现,并采用现场FCD数据进行了实验验证,结果表明,该方法较轮询和Min-Min调度算法,显著地提高了并行处理的性能.

基于FCD的城市路网常发性拥堵路段识别方法研究

常发性拥堵严重影响了城市路网运行效率,准确识别常发性拥堵是交通部门解决交通拥堵问题的重要任务。研究选取浮动车数据作为基础,确定了数据分析的时间粒度,从常发性拥堵的时空特性角度出发,建立拥堵阈值、时段拥堵时长比和常发频度3级判别指标,并运用GIS技术,结合指标体系设计了常发性拥堵时空分布的筛选平台。以北京为例,针对早高峰常发性拥堵路段进行识别。通过对识别结果的分析和相关数据对比,成果可反映常发拥堵的特征,以及北京近年来的缓堵工作效果。

Intersection delay estimation from floating car data via principal curves： a case study on Beijing＇s road network

It is a pressing task to estimate the real-time travel time on road networks reliably in big cities, even though floating car data has been widely used to reflect the real traffic. Currently floating car data are mainly used to estimate the real-time traffic conditions on road segments, and has done little for turn delay estimation. However, turn delays on road intersections contribute significantly to the overall travel time on road networks in modem cities. In this paper, we present a technical framework to calculate the turn delays on road networks with float car data. First, the original floating car data collected with GPS equipped taxies was cleaned and matched to a street map with a distributed system based on Hadoop and MongoDB. Secondly, the refined trajectory data set was distributed among 96 time intervals （from 0：00 to 23： 59）. All of the intersections where the trajectories passed were connected with the trajectory segments, and constituted an experiment sample, while the intersections on arterial streets were specially selected to form another experiment sample. Thirdly, a principal curve-based algorithm was presented to estimate the turn delays at the given intersections. The algorithm argued is not only statistically fitted the real traffic conditions, but also is insensitive to data sparseness and missing data problems, which currently are almost inevitable with the widely used floating car data collecting technology. We adopted the floating car data collected from March to June in Beijing city in 2011, which contains more than 2.6 million trajectories generated from about 20000 GPS-equipped taxicabs and accounts for about 600 GB in data volume. The result shows the principal curve based algorithm we presented takes precedence over traditional methods, such as mean and median based approaches, and holds a higher estimation accuracy （about 10%-15% higher in RMSE）, as well as reflecting the changing trend of traffic congestion. With the estimation result for the travel delay at intersections, we analyzed the spatio-temporal distribution of turn delays in three time scenarios （0： 00-0： 15, 8： 15-8：30 and 12： 00-12： 15）. It indicates that during one＇s single trip in Beijing, average 60% of the travel time on the road networks is wasted on the intersections, and this situation is even worse in daytime. Although the 400 main intersections take only 2.7% of all the intersections, they occupy about 18% travel time.

A novel method for road network mining from floating car data

Vehicles have been increasingly equipped with GPS receivers to record their trajectories,which we call floating car data.Compared with other data sources,these data are characterized by low cost,wide coverage,and rapid updating.The data have become an important source for road network extraction.In this paper,we propose a novel approach for mining road networks from floating car data.First,a Gaussian model is used to transform the data into bitmap,and the Otsu algorithm is utilized to detect road intersections.Then,a clothoid-based method is used to resample the GPS points to improve the clustering accuracy,and the data are clustered based on a distance-direction algorithm.Last,road centerlines are extracted with a weighted least squares algorithm.We report on experiments that were conducted on floating car data from Wuhan,China.To conclude,existing methods are compared with our method to prove that the proposed method is practical and effective.

Analyzing Behavior Differences of Occupied and Non-Occupied Taxi Drivers Using Floating Car Data

As the travel purpose of non-occupied taxies is to find new passengers rather than to arrive at the destination, large differences exist in the route choice behavior between the occupied and non-occupied taxies.With the assistance of geographic information system(GIS) and taxi-based floating car data(FCD), this paper investigates the behavior differences between occupied and non-occupied taxi drivers with the same origin and destination. Descriptive statistical indexes from the FCD in Shenzhen, China are explored to identify the route choice characteristics of occupied and non-occupied taxies. Then, a conditional logit model is proposed to model the quantitative relationship between drivers' route choice and the related significant variables. Attributes of the variables related to non-occupied taxies' observed routes are compared with the case of occupied ones. The results indicate that, compared with their counterparts, non-occupied taxi drivers generally pay more attention to choosing arterial roads and avoiding congested segments. Additionally, they are also found less sensitive to fewer traffic lights and shorter travel time. Findings from this research can assist to improve urban road network planning and traffic management.

Evaluating spatial accessibility to healthcare services from the lens of emergency hospital visits based on floating car data

Public medical facilities that are closely related to the health of residents have been recognised as one of the most crucial elements in sustainable urban planning.For the sake of social equality of medical services(especially for emergency medical conditions),the spatial distributions of medical resources need to be accurately measured and continuously optimized.This study presents an effective method to examine night emergency hospital visit and analyse its spatiotemporal characteristics using float car data(FCD).By extracting the hospital service areas,the two-step floating catchment area(2SFCA)methodology was improved to calculate hospital accessibility.Then,the balance between hospital accessibility and population density was analysed.In addition,we investigated the relationship between individual hospital choice preferences and hospital level and analysed several factors that affect individual choices.These results help us understand the special requirements and need of emergency hospital travel in cities and identify areas where medical resources are scarce.They can be used as guidance for urban hospital planning and construction.And the approach of hospital access behaviour investigation and the improved 2SFCA method can also provide insights for other activity-based travel behaviour research.

“新冠”疫情对私家车出行特征的影响

受新冠肺炎疫情的影响,北京市私家车辆在2020年的出行特征,包括出行频率,出行时间以及出行地点均表现出了不同于往年的变化.使用安装在志愿者车辆上的车载盒子收集车辆行驶的浮动车数据,通过对比2020年6月与2019年6月同期的私家车辆出行特征,在不同功能的出行区域内、以出行终点为研究对象,对私家车辆的出行特征进行分析.经过对数据的筛选和处理,进而从出行目的及出行意愿角度对“新冠”疫情影响私家车辆出行特征的改变进行总结.

基于网格划分的城市交通常发拥堵识别方法

为解决常发性拥堵识别中合流点较多、存在环路导致识别困难、路段值缺失使拥堵难以溯源等问题,提出了基于网格模型的城市交通网络常发性拥堵识别方法,基于空间自相关理论,确定以3 km为识别拥堵扩散的显著范围;定义常发性拥堵路段识别规则,计算常发性拥堵路段在拥堵扩散范围内与邻近路段的时间相关系数,得到强相关路段对应的时序偏移量,最终以北京市朝阳区为例,识别常发性拥堵瓶颈37个,并以健翔桥为例证明方法的准确性.研究表明,本文提出的常发性拥堵路段和拥堵瓶颈识别方法,简化了复杂的路网拓扑关系,为拥堵传播机理的准确分析奠定了基础,结果能为制定疏堵方案提供理论依据和数据支撑.

基于浮动车数据的行程速度估计算法及优化

依托重点实验室构建的浮动车采集处理实验系统,从行程速度的交通工程学定义出发,利用实时上传的浮动车数据,构建了以浮动车的驻留时间和路段长度为基础的行程速度估计算法．通过对比现场跟车实验测得的行程速度与算法计算结果,验证了该算法的行程速度结果精度达到90％以上,从而为交通信息服务系统提供了简单、准确的区间速度计算方法．最后,对算法进行了优化,有效地提高了算法效率,为满足大规模应用奠定了基础．

出租车经验知识建模与路径规划算法

以出租车采集的浮动车数据,研究出租车司机道路选择的经验和规律,建立出租车司机道路寻径的经验知识模型,将城市交通道路网按该知识模型分成不同等级的经验路网;在此基础上提出基于经验知识的交通道路寻径算法,并以武汉市交通路网和浮动车为实验数据,将本文提出的道路寻径算法与传统的最短路径规划算法进行比较,实验结果表明在起止点相同的情况下,本文选择的路径较好地保持了道路等级的一致性和连贯性,明显减少通行时间,更符合自主出行的认知。

基于向量识别的启发式路径推测算法

浮动车数据主要是由车辆的轨迹点数据组成,是一种重要的原始数据,可以广泛地用于各种交通应用,如交通管理和控制、路况计算等.但是原始的车辆GPS数据存在定位误差,必须经过路径推测的修正处理才可以应用.传统的路径推测算法主要采用两种方法:渐增式和全局式.两种方法各有优缺点,渐增式方法计算速度快但准确性差,全局式方法准确性好但计算速度慢.通过综合考虑两种传统算法,文中提出了一种基于向量识别的启发式路径推测算法,该算法采用了启发式图搜索方式,导入几何运算的约束条件,根据车辆轨迹点所形成的向量与路网模型比较来进行启发式搜索,并选择车辆所有可能行驶的候选路径.根据全局择优的方式从整体进行比较,确定车辆最有可能的行驶路径.实验结果表明,这种算法能够在复杂路网下,比较准确地推测距离间隔较大的车辆轨迹点,并且能够实时高效地处理大规模数据.