WO2018214675A1 - 一种量化分析城市建成环境对道路行程时间影响的方法 - Google Patents

一种量化分析城市建成环境对道路行程时间影响的方法 Download PDF

Info

Publication number
WO2018214675A1
WO2018214675A1 PCT/CN2018/083443 CN2018083443W WO2018214675A1 WO 2018214675 A1 WO2018214675 A1 WO 2018214675A1 CN 2018083443 W CN2018083443 W CN 2018083443W WO 2018214675 A1 WO2018214675 A1 WO 2018214675A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
intersection
variable
travel time
regression
Prior art date
Application number
PCT/CN2018/083443
Other languages
English (en)
French (fr)
Inventor
钟绍鹏
王仲
王全志
邹延权
程荣
李旭丰
Original Assignee
大连理工大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 大连理工大学 filed Critical 大连理工大学
Priority to US16/309,770 priority Critical patent/US20190266891A1/en
Publication of WO2018214675A1 publication Critical patent/WO2018214675A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/18Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/0104Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0112Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/0104Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125Traffic data processing
    • G08G1/0129Traffic data processing for creating historical data or processing based on historical data
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/0104Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/052Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed

Definitions

  • the invention belongs to the field of urban traffic planning and traffic big data research, and particularly relates to the application of urban taxi GPS data and spatial geographic information data to study the influence of urban built environment on road travel time.
  • Hofleitner A proposes a hybrid model framework to estimate the trunk travel time with a large number of floating vehicle GPS data in "Arterial travel time forecast with streaming data: A hybrid approach of flow modeling and machine learning"; Mucsi K in "An Adaptive Neuro- Fuzzy Inference System for estimating the number of vehicles for queue management at signalized intersections.
  • Three-layer neural network for predicting the travel time of the whole road segment using the sparse data collected by the floating vehicle Ma Chaofeng's estimation of the travel time of the road segment based on low-frequency sampling GPS data Based on the traffic flow theory, the influence of the intersection is considered, and the low-frequency GPS data is used to study the travel time of the road section to improve the estimation accuracy.
  • the technical problem to be solved by the present invention is that the research road is first divided into a plurality of small road sections, and the average speed and built environment attribute information of each small road section are extracted based on the taxi GPS data and the spatial geographic information data on the research road. Then, taking the average speed of each small section as the dependent variable, the built-up environment attribute of the road section is used as the key independent variable, and the virtual intersection of the nearest intersection type of the road section is used as the adjustment variable. The regression analysis is carried out considering the interaction between the key independent variable and the adjustment variable, and the regression result is obtained. The key independent variables that significantly affect the average speed of the road segment are selected. Finally, the extracted key independent variables are brought into the geographic weighted regression model (GWR) for quantitative analysis.
  • GWR geographic weighted regression model
  • a method for quantifying the impact of urban built environment on road travel time the steps are as follows:
  • segmentation is carried out every 20-30 m.
  • the GPS data of the collected taxis are filtered, corrected and matched, and the GPS data of the taxis containing the speed and passenger status on each road segment are obtained, which is recorded as table a, and then rented according to table a.
  • the GPS data of the vehicle is used to calculate the average speed and passenger ratio of all taxis in each section (the ratio of the taxi sample size in each passenger section to the taxi sample size in the full state).
  • the geographic information data of the road network firstly, the number of buildings, the number of banks, the number of hotels, the number of pharmacies, the number of parking lots, the number of supermarkets, the number of restaurants, the number of bus stations and the number of schools within 500 meters of the road section are statistically studied; The nearest school distance from each small section, the nearest intersection distance, and the nearest bus stop distance; finally, the speed limit of each small road section is counted.
  • the average speed of each section is taken as the dependent variable
  • the built-up environment attribute of the road section is used as the key independent variable
  • the virtual variable of the nearest intersection type of the section is used as the adjustment variable, considering the interaction between the key independent variable and the adjustment variable.
  • the specific model structure is as follows:
  • S in the model indicates the average speed of the road segment;
  • ⁇ o is the regression constant;
  • ⁇ 1 , ⁇ 2 ,..., ⁇ 14 indicates the number of buildings, the number of banks, the number of hotels, the number of pharmacies, the number of parking lots, the number of supermarkets, and catering The number of stores, the number of bus stops, the passenger-to-pass ratio, the number of schools, the nearest school distance, the nearest intersection distance, the nearest bus stop distance, and the speed limit, a total of 14 key independent variables, of which ⁇ 1 , ⁇ 2 ,..., ⁇ 14 Corresponding regression coefficients; D 1 , D 2 , ..., D n-1 respectively represent n-1 intersection type dummy variables, where ⁇ 1 , ⁇ 2 , ..., ⁇ n-1 are their corresponding regression coefficients ;
  • ⁇ kp is the interaction coefficient of the built environment attribute and the intersection type dummy variable;
  • is the random error term;
  • the key independent variables obtained in the global regression analysis that significantly affect the road travel time are brought into the spatial local model, namely the geographically weighted regression model (GWR model).
  • GWR model geographically weighted regression model
  • S i is the average speed of the i-th road segment; (u i , v i ) is the i-th road segment coordinate; ⁇ o (u i , v i ) is the i-th road segment regression constant; ⁇ ik is the ith The kth independent variable of the link, ⁇ k (u i , v i ) is its corresponding regression coefficient; m indicates that there are m key independent variables in the global regression are significant; ⁇ i is the random error term of the i-th road segment ;
  • the spatial local model considers the spatial heterogeneity of the influence of different geographical locations on the road travel time, and studies the spatial heterogeneity phenomenon and causes from a quantitative perspective, thus revealing the inherent influence law of urban built environment and road travel time.
  • the invention analyzes the influencing factors of the road travel time from the root cause, and the obtained result reflects a more general law, which is easy to be popularized and applied to other research areas; the result of the invention can be obtained by studying the influence law of the road sections in each area of the research line. Therefore, the traffic manager can help the clear location of the problem in the urban road network, and then the targeted design to improve the performance of the traffic system; the results of the present invention also help to improve the urban built environment and the traffic planners and managers The understanding of the relationship between transportation systems, in order to develop targeted urban planning and management strategies, in order to improve the efficiency of the road network through the improvement of the urban built environment, reduce traffic congestion and road travel time.
  • Figure 1 is a diagram showing the location of a road intersection.
  • Figure 2 is a spatial distribution diagram of regression coefficients for the number of bus stops.
  • Figure 3 is a spatial distribution map of the t value of the number of bus stops.
  • Figure 4 is a spatial distribution of regression coefficients for the nearest intersection distance.
  • Fig. 5 is a spatial distribution diagram of the value of t of the nearest intersection distance.
  • the research road was first divided into 397 sections in a 25-meter section. Then, according to the road sections and time periods to be studied, the collected taxi GPS data is filtered, corrected and matched, and the average speed and passenger ratio of all taxis on each road segment are calculated. Finally, according to the geographical information data of the road network, the number of buildings, the number of banks, the number of hotels, the number of pharmacies, the number of parking lots, the number of supermarkets, the number of food and beverage outlets, the number of bus stops and the number of schools, and the number of schools within 500 meters around the road section are statistically studied. Recent school distance, recent intersection distance, recent bus stop distance, and speed limit.
  • the research road contains a total of 17 intersections.
  • the names of the intersections are shown in Table 2.
  • the location of the intersections is shown in Figure 1.
  • intersection type variable cannot be quantified as variables such as the number of parking lots, the number of bus stops, and the passenger ratio. It is therefore necessary to specifically “quantify” its impact on road travel time by introducing “virtual variables”.
  • intersection type 4 is used as the reference item, and intersection type 1, type 2, and type 3 are set as dummy variables.
  • the specific intersection type classification method is shown in Table 3.
  • the virtual variable settings are shown in Table 4:
  • Type 1 The number of imported lanes does not exceed four lanes, and there is an independent left-turn lane
  • Type 2 The number of imported lanes does not exceed four lanes, and there is a left-turn lane but not independent
  • Type 3 The number of imported lanes does not exceed four lanes, and there is no left lane
  • Type 4 The number of imported lanes is greater than four lanes, with independent left-turn lanes
  • variable coefficient Standardization coefficient t value P value constant -83.099 - -4.101 0.000 Number of parking lots (a) 2.245 0.676 2.081 0.038 Number of bus stops (b) -1.881 -1.019 -4.218 0.000 Recent school distance (c) -0.033 -0.566 -2.521 0.012 Recent intersection distance (d) 0.033 0.329 3.303 0.001 Speed limit (e) 2.102 0.639 5.372 0.000 Passenger to passenger ratio (f) 32.484 0.378 4.836 0.000 Dummy
  • Model result At 0.648, the independent variables in the model can explain the 64.8% change in the average speed of the road segment.
  • intersection type 1 and intersection type 2 are significantly positively correlated with the average speed of the road segment, while intersection type 3 is excluded due to collinearity. It is indicated that the intersection type 2 has a left turn lane but is not independent, and the intersection type 3 has no left turn lane, and in fact, the effect of the intersection type 2 left turn lane is no different from the intersection type 3. When there is no left-turn lane in the intersection, the left-turning vehicle is disturbed by the preceding straight-through vehicle, resulting in the intersection type 2 being similar to the intersection type 3.
  • intersection type 4 As the comparison item, when the nearest intersection type is 1, the number of parking lots, the number of bus stops, the nearest school distance, the nearest intersection distance, the passenger ratio, and the speed limit will affect the average speed of the road segment. Significantly different; when the recent intersection type is 2, the number of bus stops and the speed limit will have a significant impact on the average speed of the road segment; when the recent intersection type is 3, the number of bus stops, the nearest intersection distance, and passengers The effect of comparing the average speed of the road segments will also be significantly different. It can be seen that, on the whole research route, when the types of the recent intersections of the road sections are different, the influence law of the urban built environment on the average speed of the road sections is also different, and there is spatial heterogeneity.
  • the average impact of urban built environment attributes on the entire regional road segment is estimated, ignoring the spatial heterogeneity of different regional road segments. Therefore, it is necessary to apply the spatial local model-GWR to explore the influencing factors of the average speed of different sections of the road and its spatial distribution characteristics.
  • the number of parking lots, the number of bus stops, the passenger ratio, the nearest school distance, the nearest intersection distance, and the speed limit are selected as independent variables.
  • the GWR model is calibrated using the GWR4.0 software package.
  • the output results can be obtained from the independent variable regression coefficients and t values of 397 small road segments.
  • Tables 6 and 7 list the minimum, 25%, median, mean, 75%, and maximum values of the regression coefficients and t values for the respective variables, respectively.
  • the independent coefficient and t value of different built environment attributes can be represented by a spatial distribution map.
  • the regression coefficient and t-value spatial distribution results of the number of bus stops and the distance of the nearest intersection are given.
  • Figures 2 and 3 respectively show the regression coefficient and the spatial distribution of t values of the number of bus stops;
  • Figure 4 and Figure 5 respectively show The regression coefficient of the nearest intersection distance and the spatial distribution map of the t value;
  • the number of bus stops is between the intersection 5 and the intersection 6, and the average speed of the section between the intersection 7 and the intersection 9 and between the intersection 16 and the intersection 17 is significantly positive.
  • the road travel time is sensitive to the number of bus stops, and the more bus stops, the shorter the road travel time.
  • bus lanes on the road of this study, and the taxi GPS data studied is in the bus lane (7:30-9:30). Therefore, although there are many bus stops on these road sections, bus bus stops will not have a negative impact on the speed of social vehicles due to the cooperation of bus lanes and harbor stops.
  • the more bus stops the greater the probability that passengers will take the bus. The probability of taking a taxi is relatively small, so the probability that the taxi needs to slow down to stop to carry passengers is smaller. Therefore, when the taxi data is used to collect the average speed of the entire road section, the average speed of the road section will be larger. .
  • the left-turn dedicated lane should be set as much as possible at the intersection, which can ensure the safety of the intersection and the efficiency of the left-turn lane, and reduce the travel time of the road.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Algebra (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种量化分析城市建成环境对道路行程时间影响的方法,首先根据道路上出租车GPS数据和地理信息数据提取出各小路段平均速度和建成环境属性信息;然后以各小路段平均速度作为因变量,建成环境属性作为关键自变量,最近交叉口类型虚拟变量作为调节变量,考虑关键自变量与调节变量的交互影响做回归分析,并从回归结果中选取出显著影响路段平均速度的关键自变量;最后将提取的关键自变量带入地理加权回归模型中进行量化分析。该方法为交通规划和管理部门调整城市建成环境属性,提高路网运行效率提供了决策依据。

Description

一种量化分析城市建成环境对道路行程时间影响的方法 技术领域
本发明属于城市交通规划及交通大数据研究领域,特别涉及应用城市出租车GPS数据和空间地理信息数据来研究城市建成环境对道路行程时间的影响。
背景技术
近年来,伴随着人们出行时间观念的加强以及交通路网运行效率的恶化,道路行程时间的研究已经成为智能交通系统研究的热点。现有关于道路行程时间的研究多是基于交通流理论或数据驱动方法进行道路行程时间估计和预测。如Hofleitner A在《Arterial travel time forecast with streaming data:A hybrid approach of flow modeling and machine learning》中用大量浮动车GPS数据提出一种混合模型框架来估计干线出行时间;Mucsi K在《An Adaptive Neuro-Fuzzy Inference System for estimating the number of vehicles for queue management at signalized intersections》中利用浮动车采集的稀疏数据预测整个路段行程时间的三层神经网络;马超锋在《基于低频采样GPS数据的路段行程时间估计》中基于交通流理论重点考虑交叉口的影响,并用低频GPS数据对路段行程时间进行深入研究以提高估计精度。
然而,这些方法往往无法分析影响道路行程时间的主要因素,且受限于所研究区域自身建成环境属性和数据,研究成果很难被直接应用到其他区域。以往的研究已经证实城市建成环境与出行者出行行为之间存在密切关系,城市建成环境会影响出行者的出行目的地、出行方式、出行频率、出行路线等出行行为,并最终影响道路网络行程时间。因此,有必要从城市建成环境的角度入手,深入研究影响道路行程时间的主要因素。此外,由于空间异质性的存在,城市建成环境对不同区域道路行程时间的影响规律也不尽相同。本发明在此基础上,应用城市出租车GPS数据和空间地理数据,提出一种量化分析城市建成环境对道路行程时间影响的方法。
发明内容
本发明要解决的技术问题是:先将研究道路分成多个小路段,并基于研究道路上的出租车GPS数据和空间地理信息数据提取出各小路段的平均速度和建成环境属性信息。然后以各小路段的平均速度作为因变量,路段建成环境属性作为关键自变量,路段最近交叉口类型虚拟变量作为调节变量,考虑关键自变量与调节变量的交互影响做回归分析,并从回归结果中选取出显著影响路段平均速度的关键自变量。最后将提取的关键自变量带入地理加权回归模型(GWR)中,进行量化分析。
本发明的技术方案:
一种量化分析城市建成环境对道路行程时间影响的方法,步骤如下:
1.基础数据
对选取的研究道路(8公里以上),按每20—30米进行分段。
(1)路段平均速度和载客比数据提取
根据所要研究的路段和时段,对收集到的出租车GPS数据进行筛选、校正和匹配,得到各个路段上含有速度和载客状态的出租车GPS数据,记为表a,然后根据表a中出租车GPS数据,分别计算每个路段所有出租车的平均速度和载客比(各路段载客状态下出租车样本量与全状态下出租车样本量之比)。
(2)路段建成环境属性信息提取
根据路网地理信息数据,首先统计研究路段周边500米范围内的大厦数量、银行数量、宾馆酒店数量、药店数量、停车场数量、超市数量、餐饮店数量、公交站点数量以及学校数量;然后统计距离各小路段最近的学校距离、最近的交叉口距离以及最近的公交站点距离;最后统计各小路段的限速大小。
(3)道路交叉口类型分类
对研究道路上所有交叉口按进口车道数、是否有左转车道、左转车道是否独立分成n(n>=2)类。然后将最后一种交叉口类型(即类型n)作为参照项,其余n-1种交叉口类型设为“虚拟变量”,具体设置如表1所示:
表1 交叉口类型虚拟变量的设置
交叉口类型 D 1 D 2 D n-1
类型1 1 0 0
类型2 0 1 0
类型n-1 0 0 1
2.含交叉项的全局回归分析
在全局回归分析中,以各路段平均速度作为因变量,路段建成环境属性作为关键自变量,路段最近交叉口类型虚拟变量作为调节变量,考虑关键自变量与调节变量的交互影响。具体模型结构如下:
Figure PCTCN2018083443-appb-000001
其中:模型中S表示路段平均速度大小;β o为回归常数;χ 1,χ 2,…,χ 14分别表示大厦数量、银行数量、宾馆酒店数量、药店数量、停车场数量、超市数量、餐饮店数量、公交站点数量、载客比、学校数量、最近学校距离、最近交叉口距离、最近公交站点距离、限速大小,共14个关键自变量,其中β 1,β 2,…,β 14为其对应的回归系数;D 1,D 2,…,D n-1分别表示n-1个交叉口类型虚拟变量,其中η 1,η 2,…,η n-1为其对应的回归系数;λ kp为建成环境属性与交叉口类型虚拟变量的交互影响系数;ε为随机误差项;
通过全局回归分析,可以得到显著影响道路行程时间的关键自变量,并且可以证明了空间异质性的存在,因此需要使用空间局部模型做进一步的量化分析。
3.空间局部模型分析
将全局回归分析中得到的显著影响道路行程时间的关键自变量,带入空间局部模型中,即地理加权回归模型(GWR模型)。具体模型结构如下:
Figure PCTCN2018083443-appb-000002
其中:S i为第i个路段的平均速度;(u i,v i)为第i个路段坐标;β o(u i,v i)为第i个路段回归常数;χ ik为第i个路段第k个自变量,β k(u i,v i)为其对应的回归系数;m表示在全局回归中有m个关键自变量是显著的;ε i为第i个路段的随机误差项;
空间局部模型考虑不同地理位置建成环境对道路行程时间影响的空间异质性,从定量角度研究这种空间异质性现象和成因,从而揭示城市建成环境与道路行程时间的内在影响规律。
本发明的有益效果:
本发明从根源上分析了道路行程时间的影响因素,因此得到的结果反映的是更普遍的规律,易于推广和应用到其他研究区域;本发明的结果可以得到研究线路各区域路段的影响规律,因此可以帮助交通管理者明确了城市路网中问题存在地点,进而有针对性的设计方案来改善交通系统的性能;本发明的结果还有助于提升交通规划者和管理者对城市建成环境与交通系统关系的认识,从而制定有针对性的城市规划和管理策略,以期通过城市建成环境的改善进而从根源上提高路网通行效率,减少交通拥堵和道路行程时间时间。
附图说明
图1是研究道路交叉口位置图。
图2是公交站点数量的回归系数空间分布图。
图3是公交站点数量的t值空间分布图。
图4是最近交叉口距离的回归系数空间分布图。
图5是最近交叉口距离的t值的空间分布图。
具体实施方式
以下结合实例详细叙述本发明的具体实施方式,并模拟发明的实施效果。
1.基础数据
选取深圳市南山区工业八路与后海大道交叉口到侨城东路与白石路交叉口之间的路段作为案例研究对象。使用2014年6月9日到2014年6月13日7::30到9:30之间该路段上所有的出租车实际数据。
先将该研究道路按25米一段,分成397段。然后根据所要研究的路段和时段,对收集到的出租车GPS数据进行筛选、校正和匹配,并计算每个路段上所有出租车平均速度和载客比。最后根据路网地理信息数据,统计研究路段周边500米范围内大厦数量、银行数量、宾馆酒店数量、药店数量、停车场数量、超市数量、餐饮店数量、公交站点数量以及学校数量,各小路段最近学校距离、最近交叉口距离、最近公交站点距离以及限速大小。
由于要考虑交叉口类型与建成环境的交互影响,需要对研究道路交叉口类型进行处理。该研究道路一共包含17个交叉口,交叉口名称见表2所示,交叉口位置图如图1所示。
表2 交叉口名称
交叉口编号 交叉口名称 交叉口编号 交叉口名称
交叉口1 工业八路与后海大道交叉口 交叉口10 沙河东路与白石路交叉口
交叉口2 东滨路与后海大道交叉口 交叉口11 石洲中路、深湾一路与白石路交叉口
交叉口3 登良路与后海大道交叉口 交叉口12 红树街、深湾二路与白石路交叉口
交叉口4 创业路与后海大道交叉口 交叉口13 深湾三路与白石路交叉口
交叉口5 海德一道与后海大道交叉口 交叉口14 深湾四路与白石路交叉口
交叉口6 学府路与后海大道交叉口 交叉口15 深湾五路与白石路交叉口
交叉口7 岗园路与白石路交叉口 交叉口16 云天路、海园一路与白石路交叉口
交叉口8 科苑南路与白石路交叉口 交叉口17 侨城东路与白石路交叉口
交叉口9 科技南路与白石路交叉口
对研究道路上所有交叉口按进口车道数、是否有左转车道、左转车道是否独立分成4类。由于交叉口类型变量无法像停车场数量、公交站点数量、载客比等变量可以定量去度量。因此需要通过引入“虚拟变量”来具体“量化”其 对道路行程时间的影响。为了避免“虚拟变量陷阱”(多重共线性问题),本案例将交叉口类型4作为参照项,交叉口类型1、类型2和类型3设为虚拟变量,具体交叉口类型分类方法见表3所示,虚拟变量设置见表4所示:
表3 交叉口类型分类方法
交叉口类型 特点
类型1 进口车道数不超过四车道,有独立左转车道;
类型2 进口车道数不超过四车道,有左转车道但不是独立的;
类型3 进口车道数不超过四车道,无左转车道;
类型4 进口车道数大于四车道,有独立左转车道;
表4 虚拟变量设置
交叉口类型 D 1 D 2 D 3
类型1 1 0 0
类型2 0 1 0
类型3 0 0 1
2.含交叉项的全局回归分析结果
将基础数据带入本发明技术方案中提出的全局模型中,用SPSS进行多元线性回归,其结果见表5所示。当各个变量t值的绝对值大于1.96时,说明该变量是显著的,则被选择列入表5中。
表5 多元线性回归模型结果
变量 系数 标准化系数 t值 P值
常量 -83.099 -4.101 0.000
停车场数量(a) 2.245 0.676 2.081 0.038
公交站点数量(b) -1.881 -1.019 -4.218 0.000
最近学校距离(c) -0.033 -0.566 -2.521 0.012
最近交叉口距离(d) 0.033 0.329 3.303 0.001
限速大小(e) 2.102 0.639 5.372 0.000
载客比(f) 32.484 0.378 4.836 0.000
Dummy
交叉口类型1(D1) 205.796 6.172 3.336 0.001
交叉口类型2(D2) 240.479 5.108 3.637 0.000
交互项
a×D1 -5.465 -1.424 -3.745 0.000
b×D1 2.403 1.571 4.397 0.000
b×D2 2.910 0.652 2.726 0.007
b×D3 2.604 0.525 39-.027 0.003
c×D1 0.034 0.489 2.318 0.021
d×D1 0.045 0.390 3.522 0.000
d×D3 0.044 0.223 2.579 0.010
e×D1 -3.823 -6.528 -3.691 0.000
e×D2 -5.445 -6.052 -4.007 0.000
f×D1 -27.627 -0.504 -3.446 0.001
f×D3 -24.866 -0.355 -2.509 0.013
F值 13.805
R 2 0.699
分析:模型估计结果的F值为13.805,给定显著水平α=0.05,有F>F 0.05(58,338),则表明拒绝原假设,至少有一个自变量的系数显著不等于0,模型的线性关系在95%的置信水平下显著成立。模型结果中
Figure PCTCN2018083443-appb-000003
为0.648,说明模型中的自变量能够解释路段平均速度64.8%的变化。
从表5中可以看到,交叉口类型1和交叉口类型2与路段平均速度均呈显著正相关,而交叉口类型3由于共线性而被排除。说明交叉口类型2有左转车道但不是独立的,交叉口类型3无左转车道,而事实上交叉口类型2左转车道的效果与交叉口类型3没有差异。当交叉口没有左转专用车道时,左转车受前面直行车辆的干扰,导致交叉口类型2与交叉口类型3相差不多。此外,根据表5中的结果还可以看到,停车场数量、最近交叉口距离、限速大小以及载客比与路段平均速度呈显著正相关,而公交站点数量和最近学校距离与路段平均速度呈显著负相关。
以交叉口类型4作为对比项,当最近交叉口类型为1时,停车场数量、公交站点数量、最近学校距离、最近交叉口距离、载客比以及限速大小对路段平均速度产生的影响会显著不同;当最近交叉口类型为2时,公交站点数量和限速大小对路段平均速度产生的影响会显著不同;当最近交叉口类型为3时,公交站点数量、最近交叉口距离以及载客比对路段平均速度产生的影响也会显著不同。由此可见,在整个研究线路上,当路段最近交叉口类型不同时,城市建成环境对路段平均速度的影响规律也不相同,存在空间异质性特点。在全局回归模型中,估计的是城市建成环境属性对整个区域路段的平均影响,忽略了不同区域路段的空间异质性。因此有必要应用空间局部模型—GWR来探索不同区域路段平均速度的影响因素以及其空间分布特征。
3.空间局部模型分析结果
在全局回归结果中选取停车场数量、公交站点数量、载客比、最近学校距离、最近交叉口距离以及限速大小作为自变量。GWR模型标定采用GWR4.0软件包。输出结果可以得到397个小路段各自对应的自变量回归系数和t值。表6和表7分别列出各自变量回归系数和t值的最小值、25%分位数、中位数、平均值、75%分位数以及最大值。
表6 GWR模型自变量系数估计结果
变量 最小 25%分位 中位数 平均值 75%分位数 最大值
常量 -121.072 -13.914 16.439 -0.006 31.870 75.133
停车场数量 -4.928 -2.700 -1.540 -1.581 -0.450 1.747
公交站点数量 -0.347 -0.042 0.394 0.332 0.647 1.093
载客比 -1.111 4.816 10.288 9.521 15.067 19.033
最近学校距离 -0.023 -0.012 0.005 0.007 0.030 0.038
最近交叉口距离 0.039 0.049 0.068 0.063 0.072 0.087
限速大小 -0.861 -0.259 -0.050 0.300 0.686 2.329
表7 GWR模型自变量t值估计结果
变量 最小 25%分位 中位数 平均值 75%分位数 最大值
常量 -4.021 -0.496 0.475 0.164 1.397 2.913
停车场数量 -3.579 -2.867 -1.737 -1.691 -1.079 1.683
公交站点数量 -0.939 -0.191 1.458 1.176 2.186 3.177
载客比 -0.191 0.811 1.534 1.466 2.384 2.757
最近学校距离 -2.689 -1.468 0.989 0.287 1.987 2.783
最近交叉口距离 2.963 5.041 7.762 7.083 8.457 11.614
限速大小 -1.374 -0.647 -0.098 0.518 1.358 4.623
从表6和表7中可以看到,同一解释变量对不同路段平均速度的影响并不相同。在某些路段上解释变量对其平均速度的影响为正相关,而在其他路段上却是负相关。同时,在某些路段上这种相关性是显著的,而在其他路段上却是非显著的。根据空间局部模型结果,可以将不同建成环境属性的自变量系数和t值用空间分布图表示。本案例中给出公交站点数量和最近交叉口距离的回归系数和t值空间分布结果,图2和图3分别表示公交站点数量的回归系数与t值空间分布图;图4和图5分别表示最近交叉口距离的回归系数与t值空间分布图;
从图2和图3中可以看到公交站点数量在交叉口5与交叉口6之间,交叉口7与交叉口9之间以及交叉口16与交叉口17之间对路段平均速度呈显著正相关。说明在这个三个区域路段,道路行程时间对公交站点数量比较敏感,且公交站点数量越多,道路行程时间越短。本研究道路上有公交专用道,且研究的出租车GPS数据正好处于公交专用道使用时间(7:30—9:30)。因此,在这些路段上虽然公交站点多,但是由于公交专用道和港湾停靠站配合,公交车辆停靠不会对社会车辆速度产生负面影响;其次,公交站点越多,出行者乘坐公交的概率越大,而乘坐出租车的概率就相对越小,则出租车需要减速至停车来载客的概率就越小,因此当用出租车数据来采集整个路段的平均速度时,路段平均速度就会越大。
从图4和图5中可以看到最近交叉口距离在整个研究线路上对路段平均速度均是呈显著正相关,但不同区域系数大小不同。这说明,最近交叉口距离对路段平均速度具有显著的影响,与最近交叉口距离越近,路段平均速度就越小,道路行程时间就越长。对比每个路段其最近交叉口类型发现,当路段最近交叉口类型为1和4时,其回归参数相对较大,而当其最近交叉口类型为2和3时,其回归参数相对较小。交叉口类型1和类型4都有独立的左转车道。这说明是否有左转专用道会对路段平均速度的大小产生影响。在其他因素相同条件下,当最近交叉口有独立左转专用道的路段其平均速度更快。因此,在城市主干道上,如果条件允许,在交叉口应该尽量设置左转专用车道,这样既可以保证了交叉口安全以及左转车道通行效率,还能减少道路行程时间的大小。

Claims (1)

  1. 一种量化分析城市建成环境对道路行程时间影响的方法,其特征在于,步骤如下:
    一、基础数据
    对选取的研究道路按每20~30米进行分段,形成多个路段;所述的研究道路为8公里以上;
    (1)路段平均速度和载客比数据提取
    根据所要研究的路段和时段,对收集到的出租车GPS数据进行筛选、校正和匹配,得到各个路段上含有速度和载客状态的出租车GPS数据,记为表a,然后根据表a中出租车GPS数据,分别计算每个路段所有出租车的平均速度和载客比,即各路段载客状态下出租车样本量与全状态下出租车样本量之比;
    (2)路段建成环境属性信息提取
    根据路网地理信息数据,首先统计研究道路周边500米范围内的大厦数量、银行数量、宾馆酒店数量、药店数量、停车场数量、超市数量、餐饮店数量、公交站点数量以及学校数量;然后统计距离各路段最近学校距离、最近交叉口距离以及最近公交站点距离;最后统计各路段的限速大小;
    (3)道路交叉口类型分类
    对研究道路上所有交叉口按进口车道数、是否有左转车道、左转车道是否独立分成n类,n>=2;然后将最后一种交叉口类型n作为参照项,其余n-1种交叉口类型设为“虚拟变量”,具体设置如表1所示:
    表1交叉口类型虚拟变量的设置
    交叉口类型 D 1 D 2 D n-1 类型1 1 0 0 类型2 0 1 0 类型n-1 0 0 1
    二、含交叉项的全局回归分析
    在全局回归分析中,以各路段平均速度作为因变量,路段建成环境属性作为关键自变量,路段最近交叉口类型虚拟变量作为调节变量,考虑关键自变量与调节变量的交互影响,具体模型结构如下:
    Figure PCTCN2018083443-appb-100001
    其中:模型中S表示路段平均速度大小;β o为回归常数;χ 1,χ 2,…,χ 14分别表示大厦数量、银行数量、宾馆酒店数量、药店数量、停车场数量、超市数量、餐饮店数量、公交站点数量、载客比、学校数量、最近学校距离、最近交叉口距离、最近公交站点距离和限速大小,共14个关键自变量,其中β 1,β 2,…,β 14为其对应的回归系数;D 1,D 2,…,D n-1分别表示n-1个交叉口类型虚拟变量,其中η 1,η 2,…,η n-1为其对应的回归系数;λ kp为建成环境属性与交叉口类型虚拟变量的交互影响系数;ε为随机误差项;
    通过全局回归分析,得到显著影响道路行程时间的关键自变量,并且证明了空间异质性的存在,因此需要使用空间局部模型做进一步的量化分析;
    三、空间局部模型分析
    将全局回归分析中得到的显著影响道路行程时间的关键自变量,带入空间局部模型中,即地理加权回归模型,具体模型结构如下:
    Figure PCTCN2018083443-appb-100002
    其中:S i为第i个路段的平均速度;(u i,v i)为第i个路段坐标;β o(u i,v i)为第i个路段回归常数;χ ik为第i个路段第k个自变量,β k(u i,v i)为其对应的回归系数;m表示在全局回归中有m个关键自变量是显著的;ε i为第i个路段的随机误差项;
    空间局部模型考虑不同地理位置建成环境对道路行程时间影响的空间异质性,从定量角度研究这种空间异质性现象和成因,从而揭示城市建成环境与道路行程时间的内在影响规律。
PCT/CN2018/083443 2017-05-24 2018-04-18 一种量化分析城市建成环境对道路行程时间影响的方法 WO2018214675A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/309,770 US20190266891A1 (en) 2017-05-24 2018-04-18 A method to quantitatively analyze the effects of urban built environment on road travel time

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710371007.8A CN107016851B (zh) 2017-05-24 2017-05-24 一种量化分析城市建成环境对道路行程时间影响的方法
CN201710371007.8 2017-05-24

Publications (1)

Publication Number Publication Date
WO2018214675A1 true WO2018214675A1 (zh) 2018-11-29

Family

ID=59450786

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/083443 WO2018214675A1 (zh) 2017-05-24 2018-04-18 一种量化分析城市建成环境对道路行程时间影响的方法

Country Status (3)

Country Link
US (1) US20190266891A1 (zh)
CN (1) CN107016851B (zh)
WO (1) WO2018214675A1 (zh)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109783893A (zh) * 2018-12-27 2019-05-21 同济大学 一种考虑路段上下游线形设计参数的连续建模方法
CN110929783A (zh) * 2019-11-21 2020-03-27 同济大学 基于共享对象的租还数据的用地属性分类方法
CN110991262A (zh) * 2019-11-12 2020-04-10 同济大学 生态服务价值预测的多带宽地理加权回归元胞自动机方法
CN111489008A (zh) * 2019-08-24 2020-08-04 天津职业技术师范大学(中国职业培训指导教师进修中心) 一种交通事故影响因素空间效应分析方法及其应用
CN112070259A (zh) * 2019-06-10 2020-12-11 中国航天系统工程有限公司 一种预测城市空载出租车数量的方法
CN113393104A (zh) * 2021-06-03 2021-09-14 东南大学 一种轨道交通运行状态对周边公共自行车影响的评价方法
CN114117700A (zh) * 2021-11-29 2022-03-01 吉林大学 基于复杂网络理论的城市公共交通网络优化研究方法
CN114239929A (zh) * 2021-11-30 2022-03-25 东南大学 一种基于随机森林的出租车交通需求特征预测方法
CN114331058A (zh) * 2021-12-15 2022-04-12 东南大学 建成环境对交通运行状况影响的评估方法
CN114723275A (zh) * 2022-04-01 2022-07-08 东南大学 一种面向综合交通系统的客运生成总量分析方法
CN115048617A (zh) * 2022-03-28 2022-09-13 山西大学 一种基于信息论的空间因子空间分层异质性强弱的评价方法
CN118585603A (zh) * 2024-08-05 2024-09-03 广东工业大学 道路环境数据处理装置、方法、电子装置及存储介质

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107016851B (zh) * 2017-05-24 2019-06-28 大连理工大学 一种量化分析城市建成环境对道路行程时间影响的方法
CN107622325A (zh) * 2017-09-12 2018-01-23 大连理工大学 基于建成环境和微博数据的交通事故时空分布量化方法
CN107657377B (zh) * 2017-09-26 2021-02-19 大连理工大学 一种基于断点回归的公交专用道政策评价方法
CN107798418A (zh) * 2017-09-28 2018-03-13 东南大学 一种基于交通分析小区的交通事故频次预测方法
US11004333B2 (en) * 2018-11-29 2021-05-11 International Business Machines Corporation Detecting influential factors for traffic congestion
CN110070720B (zh) * 2019-05-15 2020-11-03 武汉科技大学 提高交叉口占道施工区通行能力模型拟合度的计算方法
CN110751366A (zh) * 2019-09-12 2020-02-04 西南交通大学 一种干线铁路与城市轨道交通运能匹配度计算方法
CN111241227B (zh) * 2020-01-14 2023-06-06 江苏省城市规划设计研究院有限公司 一种基于道路网络特征的街景数据获取方法
CN111932873B (zh) * 2020-07-21 2022-10-04 重庆交通大学 一种山地城市热点区域实时交通预警管控方法及系统
CN112185116B (zh) * 2020-09-29 2021-11-23 重庆文理学院 一种城市道路交通网络抗灾韧性能力评估方法
CN112380489B (zh) * 2020-11-03 2024-04-16 武汉光庭信息技术股份有限公司 数据处理时间计算方法、数据处理平台评价方法及系统
CN114254250B (zh) * 2021-12-14 2024-07-05 北京航空航天大学 一种考虑时空非平稳性的网约车出行需求预测方法
CN114548811B (zh) * 2022-03-01 2023-07-04 中国民用航空总局第二研究所 一种机场可达性的检测方法、装置、电子设备及存储介质
CN114912742A (zh) * 2022-03-25 2022-08-16 江苏联宏智慧能源股份有限公司 一种基于轨道交通车站能耗模型的能耗指标计算方法
CN115273467B (zh) * 2022-07-15 2023-07-04 南京莱斯信息技术股份有限公司 一种基于多区域检测数据的车流相互影响事件识别方法
CN115240424A (zh) * 2022-07-26 2022-10-25 石河子大学 基于数据驱动的多视图流量预测方法及系统
CN117218836B (zh) * 2023-09-13 2024-02-27 荆州市城市规划设计研究院 一种基于智慧城市的城市规划项目综合管理信息平台

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120276847A1 (en) * 2011-04-29 2012-11-01 Navteq North America, Llc Obtaining vehicle traffic information using mobile Bluetooth detectors
CN105006147A (zh) * 2015-06-19 2015-10-28 武汉大学 一种基于道路时空关联关系的路段行程时间推断方法
CN106384509A (zh) * 2016-10-08 2017-02-08 大连理工大学 考虑出租车运营状态下的城市道路行程时间分布估算方法
CN107016851A (zh) * 2017-05-24 2017-08-04 大连理工大学 一种量化分析城市建成环境对道路行程时间影响的方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102737510B (zh) * 2012-07-03 2014-05-21 浙江大学 一种基于移动智能终端的实时交通路况采集方法
US9739626B2 (en) * 2014-03-31 2017-08-22 Amadeus S.A.S. Journey planning method and system
US9558664B1 (en) * 2015-08-13 2017-01-31 Here Global B.V. Method and apparatus for providing parking availability detection based on vehicle trajectory information
CN106781474B (zh) * 2016-12-21 2019-03-12 东南大学 一种基于交通视频判断交通事故发生地自愈能力的方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120276847A1 (en) * 2011-04-29 2012-11-01 Navteq North America, Llc Obtaining vehicle traffic information using mobile Bluetooth detectors
CN105006147A (zh) * 2015-06-19 2015-10-28 武汉大学 一种基于道路时空关联关系的路段行程时间推断方法
CN106384509A (zh) * 2016-10-08 2017-02-08 大连理工大学 考虑出租车运营状态下的城市道路行程时间分布估算方法
CN107016851A (zh) * 2017-05-24 2017-08-04 大连理工大学 一种量化分析城市建成环境对道路行程时间影响的方法

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109783893A (zh) * 2018-12-27 2019-05-21 同济大学 一种考虑路段上下游线形设计参数的连续建模方法
CN109783893B (zh) * 2018-12-27 2023-06-06 同济大学 一种考虑路段上下游线形设计参数的连续建模方法
CN112070259A (zh) * 2019-06-10 2020-12-11 中国航天系统工程有限公司 一种预测城市空载出租车数量的方法
CN112070259B (zh) * 2019-06-10 2023-12-22 中国航天系统工程有限公司 一种预测城市空载出租车数量的方法
CN111489008A (zh) * 2019-08-24 2020-08-04 天津职业技术师范大学(中国职业培训指导教师进修中心) 一种交通事故影响因素空间效应分析方法及其应用
CN111489008B (zh) * 2019-08-24 2023-09-19 天津职业技术师范大学(中国职业培训指导教师进修中心) 一种交通事故影响因素空间效应分析方法及其应用
CN110991262A (zh) * 2019-11-12 2020-04-10 同济大学 生态服务价值预测的多带宽地理加权回归元胞自动机方法
CN110991262B (zh) * 2019-11-12 2023-05-02 同济大学 生态服务价值预测的多带宽地理加权回归元胞自动机方法
CN110929783B (zh) * 2019-11-21 2023-04-07 同济大学 基于共享对象的租还数据的用地属性分类方法
CN110929783A (zh) * 2019-11-21 2020-03-27 同济大学 基于共享对象的租还数据的用地属性分类方法
CN113393104A (zh) * 2021-06-03 2021-09-14 东南大学 一种轨道交通运行状态对周边公共自行车影响的评价方法
CN113393104B (zh) * 2021-06-03 2024-05-14 东南大学 一种轨道交通运行状态对周边公共自行车影响的评价方法
CN114117700A (zh) * 2021-11-29 2022-03-01 吉林大学 基于复杂网络理论的城市公共交通网络优化研究方法
CN114239929A (zh) * 2021-11-30 2022-03-25 东南大学 一种基于随机森林的出租车交通需求特征预测方法
CN114331058B (zh) * 2021-12-15 2023-04-21 东南大学 建成环境对交通运行状况影响的评估方法
CN114331058A (zh) * 2021-12-15 2022-04-12 东南大学 建成环境对交通运行状况影响的评估方法
CN115048617A (zh) * 2022-03-28 2022-09-13 山西大学 一种基于信息论的空间因子空间分层异质性强弱的评价方法
CN115048617B (zh) * 2022-03-28 2024-04-12 山西大学 一种基于信息论的空间因子空间分层异质性强弱的评价方法
CN114723275A (zh) * 2022-04-01 2022-07-08 东南大学 一种面向综合交通系统的客运生成总量分析方法
CN118585603A (zh) * 2024-08-05 2024-09-03 广东工业大学 道路环境数据处理装置、方法、电子装置及存储介质

Also Published As

Publication number Publication date
CN107016851B (zh) 2019-06-28
US20190266891A1 (en) 2019-08-29
CN107016851A (zh) 2017-08-04

Similar Documents

Publication Publication Date Title
WO2018214675A1 (zh) 一种量化分析城市建成环境对道路行程时间影响的方法
Tu et al. Spatial variations in urban public ridership derived from GPS trajectories and smart card data
McIntosh et al. The role of urban form and transit in city car dependence: Analysis of 26 global cities from 1960 to 2000
Fu et al. Empirical analysis of large-scale multimodal traffic with multi-sensor data
CN105493109B (zh) 使用多个数据源的空气质量推断
CN114897444B (zh) 一种城市分区域内服务设施需求识别方法及系统
Kong et al. RMGen: A tri-layer vehicular trajectory data generation model exploring urban region division and mobility pattern
Zahabi et al. Spatio-temporal analysis of car distance, greenhouse gases and the effect of built environment: A latent class regression analysis
CN109102114B (zh) 一种基于数据融合的公交出行下车站点估计方法
Pan et al. Exploring spatial variation of the bus stop influence zone with multi-source data: A case study in Zhenjiang, China
Mendiola et al. The relationship between urban development and the environmental impact mobility: A local case study
CN110555544A (zh) 一种基于gps导航数据的交通需求估计方法
CN104464280B (zh) 车辆行进开销的预测方法及系统
Alomari et al. Regional evaluation of bus rapid transit with and without transit signal priority
Zhong et al. Exploring the spatially heterogeneous effects of urban built environment on road travel time variability
Mao et al. Customer attractiveness evaluation and classification of urban commercial centers by crowd intelligence
Andrew et al. Operational evaluation of the bus rapid transit system: Case study of Dar es Salaam city
Jiang et al. Pedestrian volume prediction with high spatiotemporal granularity in urban areas by the enhanced learning model
Ma et al. An interpretable analytic framework of the relationship between carsharing station development patterns and built environment for sustainable urban transportation
Lian et al. Advances in estimating pedestrian measures through artificial intelligence: From data sources, computer vision, video analytics to the prediction of crash frequency
Lin et al. Data-driven spatial-temporal analysis of highway traffic volume considering weather and festival impacts
CN112559909B (zh) 一种基于gcn嵌入空间聚类模型的商业区发现方法
Faroqi et al. GIS-based ride-sharing and DRT in Tehran city
CN109447352B (zh) 一种公交出行od矩阵反推的组合方法
CN109544005A (zh) 基于大数据框架的比较区域内公交客流和出租客流差异的系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18805601

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18805601

Country of ref document: EP

Kind code of ref document: A1