基于空间聚类的城市路网事故多发区域共性特征分析应用

为了针对性地识别与治理城市道路事故黑点,需要深入挖掘事故特征。文中采用国内某市内城市道路交通事故数据,分别提取年事故数、每公里事故数为指标,利用空间聚类算法对事故点进行聚类,经过数据可视化得到城市道路交通事故风险分布的聚类结果图并进行特征分析。结果表明,该方法可以有效关联事故多发位置鉴别与特征分析,能在路网层级准确识别事故多发区域,为城市道路交通安全管理提供决策指导。     

改进的聚类法在事故多发点成因分析中的应用

道路交通事故多发点的成因分析是道路交通安全管理工作的重要内容,在对交通事故影响因素系统整理的基础上,提出了优化改进的核密度聚类分析方法,即采取"优化窗宽的核密度聚类方法"进行道路交通事故多发点成因的分析。同时,实践性地将该方法应用于某城市的部分交通事故数据分析,产生了有关交通事故多发点各影响因素的聚类图层,进而将各图层进行叠置分析,最终得到两大主要的综合性影响因素。结果表明,提出的优化窗宽的核密度聚类分析技术可以有效地对道路事故多发点成因进行分析,为日益严峻的交通安全问题研究做出一定的探索。     

城市道路交通安全典型问题分析

城市道路交通安全是一个复杂的社会问题,涉及城市建设、交通运输、公安交通管理、医疗救援、保险等不同行业领域。本文以道路交通事故调查分析的视角,从城市道路交通事故的总体发展趋势、年龄分布特征、肇事者交通方式、职业分布特点等方面,剖析四类城市道路交通安全典型问题,旨在明确城市道路交通安全面临的主要风险及未来的挑战,为城市道路交通安全治理提供参考。     

基于聚类分析的高速公路事故黑点鉴别及成因分析研究

为了提高事故黑点鉴别的客观性、公正性及识别水平,提出基于灰色聚类评价的事故黑点鉴别方法,并结合聚类因子法识别事故黑点诱发因素。该方法是将聚类思想应用于事故黑点鉴别及成因分析的全过程,可实现对不同层次事故黑点的分级管理。经鉴别,可将评价路段单元分为正常路段、一般路段及事故黑点3类,从而将道路几何条件、交通条件、环境特性属性相似的事故黑点聚为一类进行事故成因分析。依托长余高速公路的交通事故数据进行实例分析,确定上下行事故黑点数,并对其进行成因分析,且将基于聚类分析得到的事故黑点及其成因与实际考察得到的事故黑点及其成因进行对比分析。结果表明:基于聚类分析得到的事故黑点与实际路段事故黑点基本吻合,采用基于聚类分析预测事故黑点是可靠的。     

高速公路安全事故时间关联聚类分析

随着高速公路迅猛发展,交通事故的数量、死伤人数也呈不断上升趋势,交通安全不容忽视。针对我国某高速公路2004－2010年的事故数据,利用聚类分析方法,就公路安全数据中影响安全的时间因素进行了量化聚类分析。针对月、星期、时段对高速公路安全事故指数进行聚类,并考虑路况线形因素的影响,挖掘交通事故时间分布规律,找到高发事故期,为今后的风险分析和预警模型提供科学依据。结果表明,交通事故在季节、星期和时段上分布规律显著,说明时间因素是影响交通安全的重要因素之一。     

基于外部环境因素影响的高速公路交通事故聚类分析

根据大广(大庆—广州)高速公路K2952+350—K3044+450段2007—2012年交通事故统计资料,考虑事故严重程度,对死亡事故和受伤事故赋予不同的权重系数θ换算成相同严重程度的不同事故次数,综合考虑人、车、路和环境对交通事故的影响,结合车况、路况及天气状况等外界影响因素,采用模糊聚类法和系统聚类法对机动车司机不同违章驾驶行为的关联性进行分析。结果显示,当截取水平λ∈[0.955 2,0.973 6]、聚类个数k=5时,两种聚类方法的聚类结果相同,12种常见违章驾驶行为聚为五类,类间距与各违章驾驶行为引发的直接经济损失之差成正比,符合实际数据统计情况。最后标定了各种违章驾驶行为在外界环境因素综合作用下引发交通事故的严重程度,为进一步规范交通安全管理提供理论依据。     

车速与交通事故综合研究

随着人们对交通安全问题日益关注,道路交通安全技术和相关研究也得以快速发展。分析车速对交通事故率及事故严重程度的影响,建立车速与交通事故率和事故严重程度2者之间的相关关系。研究发现,车速偏差越大,事故率越高;事故冲撞前后车速变化越大,事故越严重。由此可知,车速对交通安全有显著影响。     

城市道路交通事故多发位置鉴别

针对现有相关鉴别法的不足,以核密度估计和计数数据模型为理论基础,GIS为技术基础,建立基于点模式和面模式的空间聚类分析模型,提出了1种基于空间聚类分析技术的城市道路事故多发位置鉴别方法,充分挖掘空间数据,实现分析结果的可视化。研究表明,空间单元标准化 Z值>2.58,对应于α=0.01的显著性水平,表明该单元是1个极高值的空间聚类,为1级事故多发点;1.96< Z<2.58对应于α=0.05的显著性水平,表明该单元是1个高值的空间聚类,为2级事故多发点。      

基于温岭市康庄工程事故特征的交通安全对策

为了保证乡村康庄工程的交通安全,提高道路的通行效率,文章结合温岭市康庄工程的交通现状,根据2003～2007年康庄工程交通事故有关调查数据,对事故时间分布、事故时段分布、事故空间分布、事故死亡者年龄分布和事故车辆类型等一系列指标进行了统计,并在对各项指标进行分析研究的基础上,进一步提出有针对性的乡村康庄工程交通安全对策和建议。     

城市道路交通事故特点及解决对策

正2018年1月7日,中办国办印发《关于推进城市安全发展的意见》,部署加强城市安全治理工作。城市道路交通安全是城市安全的重要组成部分,推进道路交通安全管理对强化城市安全基础有重大现实意义。为此,公安部道路交通安全研究中心进行了专题研究,梳理归纳了城市道路交通安全发展的阶段性特征,并提出相关对策建议,以供参考。我国城市道路里程仅占全国道路总里程的7.5%,但城市道路交通事故却占全国道路交通事故的45.8%,城市道路交通事故伤亡人数占全国     

Quantification of surrogate safety measure to predict severity of road crashes at median openings

Traffic safety assessment is an integral part of transportation engineering. In a developing country like India, it is observed that in every four second, one person gets injured in road crashes. Moreover, at median openings which are usually uncontrolled in India, the severity of road crashes increase many fold. This is due to the fact that neither lane discipline nor priority rule is followed at the median openings. Conventionally, road crash data reports were used to study and analyze traffic safety. However, the drawback of this traditional method is that a lot of accidents need to be recorded for analysis and to draw any conclusions and take necessary corrective measures. In developing countries like India, available accident data are based on reports submitted by the police department of respective state governments. The accuracy of these accident data details is highly questionable. Therefore, in the recent times surrogate traffic safety measures are being used to analyze traffic safety. Various surrogate traffic measures like Deceleration Time (DT), Time to Collision (TTC), Post Encroachment Time (PET), etc. are being used to examine road safety. These values are based on the temporal and spatial proximity between road-users during possible conflict situation. Among all the traffic safety measures, PET is regarded as the most reliable and most commonly used indicator. Therefore, in this study, PET across different traffic volume levels at median opening area is calculated. A critical safe ratio has been introduced to better analyze the traffic safety at median opening based on minimum stopping sight distance (SSD) as per IRC: 66–1976 and speed to PET ratio. Finally clustering technique has been used to define various severity indices for probable road crashes at median opening area. For this study, data has been collected from different median openings located on six-lane divided urban roads.     

考虑空间相关性的行人宏观安全研究

为了探究行人事故的发生机理,分析影响行人交通安全的显著因素,收集上海市中心城区263个交通分析小区（TAZ）的行人事故、道路、人口及土地利用数据,并开展行人宏观安全研究。考虑到TAZ之间存在的空间相关性,建立考虑空间相关性的贝叶斯负二项条件自回归模型,在条件自回归模型中对比分析了5种不同的空间权重矩阵,包括0~1邻接矩阵、边界长度矩阵、分析单元中心距离倒数矩阵、事故空间中心距离倒数矩阵这4种既有矩阵,以及首次引入的宏观安全建模中的分析单元中心距离多阶矩阵。结果表明：分析单元中心距离多阶矩阵的模型拟合效果和事故预测准确度均显著优于既有的4种空间权重矩阵,证明了在宏观安全建模过程中考虑研究对象交通特征（居民步行平均出行距离等）的必要性;人口数量、主干道长度、次干道长度、路网密度等因素均与行人事故呈现显著正相关,平均交叉口间距、三路交叉口比例等因素与行人事故呈显著负相关;相较于高等、低等土地利用强度,中等土地利用强度对行人事故的影响最大。     

非常态下城市道路交通检测器布局优化方法

为了使城市道路上布设的交通检测器能够实时、准确地提供路网动态交通流信息,并最大程度地节约经济成本,通过仿真对交通异常事件下城市道路交通流量和车辆延误进行了估计,并利用模糊聚类分析法、回归分析法和车辆延误估计模型,研究了路网在非常态下的检测器空间位置以及空间密度的布局优化方法;通过一个算例,对提出的检测器布局优化方法进行了验证分析,并得出了算例中检测器布局的优化方案。结果表明:所提出的检测器布局优化方法是可行的。     

道路因素对典型较严重道路交通事故严重性的影响分析

基于道路交通事故数据探究事故影响因素对于认识事故的影响因素、提高交通安全水平具有重要意义。利用近年来国内典型较严重道路交通事故数据,应用泊松模型和负二项模型,以区分事故形态的方式建立追尾事故、侧碰事故及撞行人事故的事故死亡率的道路影响因素分析模型。这些模型以三类事故中涉及人员的死亡数为因变量,以一系列道路因素为自变量,将事故涉及人数作为偏移变量。模型的具体形式以过离散系数及赤池信息量准则(AIC)为依据进行选择。结果显示,追尾事故的死亡率与道路等级、路侧防护设施显著相关;侧碰事故则与天气、路表情况、路口路段位置、坡度以及道路结构有关;撞行人事故与路表情况、道路等级、车道数、平曲线半径有关。本文拓展了事故严重性研究的深度,其研究成果对于更好地利用重特大事故的深入调查数据有现实意义,也可为事故分析及道路设计等提供借鉴。      

Factors affecting severity of motorcycle accidents on Thailand's arterial roads: Multiple correspondence analysis and ordered logistics regression approaches

Thailand was classified as a middle-income country and ranked second highest in terms of road traffic fatality rate in the world in 2015. By 2018, this ranking went up to ninth in world which may be because of various earnest safety policies implementation, supporting road safety research and establishing a road safety directing center. However, crash fatality rate has considerably remained high until recent year, indicating a clear need for further related research. Considering severity of the crashes, the majority of fatal crashes involved the motorcycle road user. Therefore, motorcycle crashes are important issues and should be considered to mitigate fatality due to immoderate proportion of motorcycle road user and motorcyclist fatality. This study aims to identify factors that influence the severity of motorcycle accidents on Thailand's arterial roads by employing ordered logistic regression and multiple correspondence analysis. The results demonstrated that although both analyses were relatively different, they provided similar results. Age, road lanes, and helmet wearing were significant factors that influenced the severity of motorcycle accidents. The results could serve as reference for planning strategies or organizing campaigns to reduce and prevent death owing to road traffic accidents, which may enhance the overall image of road traffic safety in Thailand.     

Extremely serious crashes on urban roadway networks: Patterns and trends

Extremely serious traffic crashes, defined as having a death toll of two and greater than two, have become a serious safety concern on urban roadways in Louisiana. This study examined the different contributing factors of these crashes to determine significant trends and patterns. We collected traffic crash data from Louisiana during the period of 2013 to 2017 and found that a total of 72 extremely serious crashes (around 2% of all traffic fatalities) occurred on Louisiana urban roadway networks. As crash data contain an enormous list of contributing factors, there was an issue of ‘more features than data points’ in solving the research problem. Most of these variables are categorial in nature. We selected a dimension reduction tool called Taxicab Correspondence Analysis (TCA) to investigate the complex interaction between multiple factors under a two-dimensional map. Findings of the study reveal several key clusters of attributes that show patterns of association between different crash attributes. The conclusions of this study are exploratory, and the results can help in better visualizing the association between key attributes of crashes. The findings have potentials in designing suitable countermeasures to reduce extremely serious crashes.     

What affects pedestrian crossing difficulty at urban intersections in a developing country?

In developing countries, road traffic crashes involving pedestrians have become a foremost concern. At present, road safety assessment plans and selection of interventions are primarily restricted to traditional approaches that depend on the investigations of historical crash data. However, in developing countries such as India, the availability, consistency, and accuracy of crash data are major concerns. In contrast, proactive approaches such as studying road users' risk perception have emerged as a substitute method of examining potential risk factors. An individual's risk perception offers vital information on probable crash risk, which may be beneficial in detecting high-risk locations and major causes of crashes. Since the pedestrian fatality risk is not uniform across the urban road network level, it may be expected that pedestrians' perceived risk measured in terms of “crossing difficulty” would also vary across the sites. In this perspective, the present paper establishes a mathematical association between the pedestrians' perceived “crossing difficulty” and actual crashes. The model outcome confirms that pedestrians' perceived crossing difficulty is a good surrogate of fatal pedestrian crashes at the intersection level in Kolkata City, India. Subsequently, to examine the impact of traffic exposures, road infrastructure, land use, spatial factors, and pedestrian-level attributes on pedestrians' “crossing difficulty”; a set of Ordered Logit models are developed. The model outcomes show that high vehicle and pedestrian volume, vehicular speed, absence of designated bus stop, the presence of inaccessible pedestrian crosswalk, on-street parking, lack of signalized control (for both vehicle and pedestrian), inadequate sight distance, land use pattern, slum population, pedestrian-vehicular post encroachment time, waiting time before crossing, road width, and absence of police enforcement at an intersection significantly and positively increase pedestrian's crossing difficulty at urban intersections. To end, the model findings are advantageously utilized to develop a set of countermeasures across 3E's of road safety.     

基于多任务迁移学习的交通警情信息自动处理方法

从交通警情数据中自动获取信息对于快速处理交通事故和提高交通管理水平具有重要的意义。为此，提出了一种基于多任务迁移学习的交通警情信息自动处理方法，该方法上游采用文本预训练模型作为共享参数层，下游建立多任务并行学习方法，实现对交通警情中的关键信息、类型和语义自动处理。选取江苏省苏州市2年内共120 191条原始交通警情作为试验数据，通过自动处理方法构建了一套标准的交通警情信息数据库。试验结果表明：所建立的关键信息抽取方法可以更精准地提取警情数据中的时间、地址和车牌信息；交通警情分类模型性能优于现有的深度学习模型，分类准确率达93%；基于局部特征增强的警情语义分析方法重点识别了警情中事故的严重程度和救援需求，识别准确率达87%。研究结论显示交通警情自动化处理方法具有良好的可移植性和实用性。     

Evaluation of risk factors for road accidents under mixed traffic: Case study on Indian highways

This paper presents an evaluation of risk factors for highway crashes under mixed traffic conditions. The basis of selecting study sites was abutting land use, roadway, and traffic characteristics. Accordingly, the study selected thirteen segments on the existing highway network in the state of West Bengal of India, covering a wide spectrum of such road attributes. A systematic investigation based on site-specific accident data to capture the highway sections' safety features revealed that the crash rate has steadily increased for years with traffic regardless of roadway category and conditions. A number of risk factors that affect road accidents were identified; they are mid-block access, pavement and shoulder conditions, vehicle involvement, time of day, and road configuration, i.e., two and multi-lane. The empirical observation indicates that the crash rate is relatively lower on multi-lane highways; however, the severity of any crash on such a road is relatively high. Notably, the crash frequencies on such roads are less during daylight hours due to the lane-based unidirectional traffic movement. This is quite the opposite during nighttime when drivers exhibit an inability to meet traffic contingencies, thereby increasing crash risk. The majority of crashes on two-lane highways are, on the other hand, due to unsafe driving manoeuvers. The study also observed that frequent mid-block accesses and poor shoulder conditions reduce scopes to rectify driving errors and increase crash risk as a consequence. The paper subsequently suggests proactive approaches to identify safety deficits at the time of planning and designing.     

我国弱势交通参与者交通安全现状及问题分析

对我国交通中的弱势交通参与者进行界定,总结了目前我国城市交通中存在的一些有关弱势交通参与者交通安全方面的问题,详细分析了过去15年我国弱势交通参与者道路交通事故的现状与特征,研究了导致弱势交通参与者交通死亡的主要原因,并提出改善其交通安全状况的对策建议。