首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 15 毫秒
1.
This analysis examines the ability of previous offenses to predict future high-risk offenses, and similarly, the ability of crashes to predict future high-risk crashes, using the complete driver history data (up to 9 years) for a set of young Michigan subjects. As expected, those with previous ticketed offenses or reported crashes are at greater risk for future offenses or crashes; with a previous-year serious offense doubling the odds of serious offenses during the subsequent year, and a previous-year at-fault crash increasing the odds of subsequent-year at-fault crashes by nearly 50%. There is modest evidence that serious offenses and at-fault crashes may better predict subsequent behavior in females and in more experienced drivers. This latter finding is also evidenced by the fact that records of these young drivers are less predictive of subsequent driving history than is true for records of all drivers in general found in other studies. This suggests that, in the early stages of driving, offenses and crashes are, at least in part, attributable to inexperience, and hence, characteristic of all beginning drivers.  相似文献   

2.
为减少因驾驶疲劳导致的交通安全事故,提出基于脑电(EEG)信号模糊熵(FE)的驾驶疲劳检测方法。开展在驾驶仿真模拟试验,采集28名被试模拟正常驾驶和疲劳驾驶的EEG信号;基于2种驾驶状态的EEG信号计算出FE值;运用随机森林(RF)、支持向量机(SVM)、决策树(DT)和K近邻(KNN)等4种分类器检测驾驶疲劳状态;利用多种性能指标及被试工作特征曲线(ROC)对驾驶疲劳检测结果进行分析比较。结果表明:基于疲劳驾驶状态下的EEG信号的FE值明显高于较正常驾驶状态下的值;4种分类器均可有效检测驾驶疲劳,其中K近邻的平均准确率达97.4%;基于EEG信号模糊熵的驾驶疲劳检测方法具有较好的鲁棒性和稳定性。  相似文献   

3.
为预防事故发生,保障飞行安全,提出一种基于多生理信号和支持向量机(SVM)的飞行警戒疲劳检测方法,识别飞行员飞行警戒中的疲劳状态。首先,研究疲劳评价与检测方法,并基于自主开发的飞行警戒测试系统与多导生物反馈仪和眼动仪搭建试验平台;然后,采集飞行警戒作业中的心电、眼动、呼吸等多生理信号和主观疲劳自评值;再次,通过配对样本的非参数检验,提取敏感生理指标,并以此作为特征向量,通过机器学习训练,构建基于多生理信号和SVM的疲劳检测模型;最后,依据受试者工作特征(ROC)曲线和模型准确率,对比分析各疲劳检测模型的效果。结果表明:在飞行警戒疲劳状态下,作业者的多项生理指标均有显著变化;心电、眼动和呼吸等多生理信号融合较单一信号的疲劳检测效果好,其ROC曲线下面积为0.802。基于高斯径向基核函数(RBF)构建的疲劳检测模型训练及预测准确率可达93%和87.50%。基于多生理信号和SVM方法可以实现对飞行警戒疲劳状态的检测。  相似文献   

4.
    
Objective: This study aimed to explore the relationship between crash types and different freeway segments and identify the factors contributing to crashes on different freeway segments. Unlike most of the previous studies on freeway segments, this study separately investigates basic freeway segments, single ramp influence segments, and multiple ramp influence segments.

Methods: Nonlinear canonical correlation analysis (NLCCA) and proportionality test were used to identify the relationship between crash types and different freeway segments. The data sets for the different freeway segments accumulated for this study consist of 9,867 crash samples with complete information on all 22 chosen variables. A multinomial logit model (MNL) was used to estimate the influence of crash factors on different freeway segments.

Results: The results show that weaving and diverge overlap influence segments (WD) are more likely to have injury or fatal crashes; diverge and diverge overlap influence segments (DD) are more likely to have property damage–only (PDO) crashes; merge and merge overlap influence segments (MM) are more likely to have sideswipe crashes; and WD have non-sideswipe crashes; WD and weaving overlap influence segments (MW) are more likely to have rear end crashes; and MM segments are less likely to have hit object crashes. The contributing factors are identified by MNL and the results show that different traffic variables, environmental variables, vehicle variables, driver variables, and geometric variables significantly affected the likelihood of crashes on different freeway segments.

Conclusions: Investigation of crash types and factors contributing to crashes on different freeway segments is based on multiple ramp influence segments, which can promote a better understanding of the safety performance of various freeway segments.  相似文献   


5.
汽车-护栏系统耐撞性研究的有限元模型   总被引:11,自引:3,他引:8  
为了建立汽车及公路护栏组成的复杂系统的耐撞性分析模型,基于VPG与LS-DYNA软件平台,应用标准化建模方法,即通过设定建模原则,在充分利用VPG内置的标准模型数据库如悬挂、轮胎、假人、安全带等各种模型的基础上,采用分块建模法,分别建立汽车、护栏、座椅模型,定义好各自内部的接触;并利用VPG的\"export\"功能,生成各自的DYN文件;再利用生成的DYN文件,就可组合出汽车-护栏系统耐撞性研究的各种中间环节的有限元模型,最终实现\"汽车-护栏-乘员-座椅-安全带\"系统模型的一体化.仿真分析与试验结果的对比表明,笔者建立的模型具有足够的可信度,适合工程应用,并给出了一个应用示例.  相似文献   

6.
Introduction: We used road crashes between vehicles and two-wheelers from Yinzhou District Ningbo in 2011–2015 from the China In-depth Accident Study (CIDAS) as sample cases. The risk factors of different injury severity grades were analyzed. Method: The classification tree model was used to screen the possible interaction items, and the corresponding regression model was constructed according to the results of the tree model to explore the influencing factors of cyclist injury. Results: The road types, weather types, gender, age of the riders, and vehicle speed were significantly correlated with the dependent variables. The interaction effect of gender*road type, weather*age, weather*speed and speed*age were obtained through a tree model. Conclusions: The risk of male casualties at the crossroads was 3.31 times higher than that of female casualties at the straight roads. On sunny days, the risk of crash casualties in Ningbo was low, and the fatality risk when the speed reached 38 km/h was 10%. Under the interaction effect of weather and age, the fatality risk in cloudy/foggy and rainy days was almost coincident, and the serious risk in cloudy/foggy conditions was the highest. Practical applications: Through factor analysis, it is confirmed that there is interaction effect among the factors, and it can provide reference for relevant departments to formulate more targeted and effective governance strategies.  相似文献   

7.
为量化分析山区高速公路线形指标对交通事故发生及严重程度的影响,引入事故修正系数(CMF)概念,提出基于CMF的高速公路交通事故预测模型。验证事故数据服从零膨胀负二项(ZINB)分布,并标定10个不同线形组合路段的基本事故预测模型;在界定理想条件的基础上,借助优势比分析方法,建立10个不同线形组合相对于基本预测模型的CMF模型;通过弹性分析识别出对不同严重程度事故有显著影响的因素,并以此分析山区高速公路线形指标及线形组合的安全效应。研究结果表明:CMF能够定量反映不同线形组合的风险效应,且其值越高,事故率及事故严重程度可能更高;山区高速公路中,平曲线缓坡组合相对安全,平曲线陡坡组合、平曲线竖曲线组合均有较高的事故风险;平曲线与凹型竖曲线组合时的风险会略低于其与凸形竖曲线组合;控制纵坡度、减少平竖曲线的组合均有利于山区高速公路交通安全。  相似文献   

8.
为研究交通事故发生前后交通流特征对事故严重程度的影响,以JT高速公路作为研究对象,长期观测和采集交通流及事故数据.将交通事故发生时段的交通流主要衡量指标与事故信息进行数据匹配,形成交通事故与事故小时交通流匹配数据集,并分析流量、速度、大车比例等交通流表征指标与不同等级事故数的分布规律.通过分析发现:在某些流量、速度或大车比例区段,交通事故数及其严重程度处于较高的水平.在此基础上,利用主成分分析(PCA)技术对衡量交通流特征的初始指标进行降维处理,用交通流主成分指标综合反映交通流特征,并建立事故严重程度与交通流主成分指标的统计分析模型.结果表明:交通流主成分指标趋于零的区段的事故严重程度明显高于其他区段.  相似文献   

9.
    
Abstract

Objective: The clinical evaluation of motor vehicle collision (MVC) victims is challenging and commonly relies on computed tomography (CT) to detect internal injuries. CT scans are financially expensive and each scan exposes the patient to additional ionizing radiation with an associated, albeit low, risk of cancer. Injury risk prediction based on regression modeling has been to be shown to be successful in estimating Injury Severity Scores (ISSs). The objective of this study was to (1) create risk models for internal injuries of occupants involved in MVCs based on CT body regions (head, neck, chest, abdomen/pelvis, cervical spine, thoracic spine, and lumbar spine) and (2) evaluate the performance of these risk prediction models to predict internal injury.

Methods: All Abbreviated Injury Scale (AIS) 2008 injury codes were classified based on which CT body region would be necessary to scan in order to make the diagnosis. Cases were identified from the NASS-CDS. The NASS-CDS data set was queried for cases of adult occupants who sought medical care and for which key crash characteristics were all present. Forward stepwise logistic regression was performed on data from 2010–2014 to create models predicting risk of internal injury for each CT body region. Injury risk for each region was grouped into 5 levels: very low (<2%), low (2–5%), medium (5–10%), high (10–20%), and very high (20%). The models were then tested using weighted data from 2015 in order to determine whether injury rates fell within the predicted risk level.

Results: The inclusion and exclusion criteria identified 5,477 cases in the NASS-CDS database. Cases from 2010–2014 were used for risk modeling (n?=?4,826). Seven internal injury risk models were created based on the CT body regions using data from 2010–2014. These models were tested against data from 2015 (n?=?651). In all CT body regions, the majority of occupants fell in the very low or low predicted injury rate groups, except for the head. On average, 57% of patients were classified as very low risk and 15% as low risk for each body region. In most cases the actual rate of injury was within the predicted injury risk range. The 95% confidence interval overlapped with predicting injury risk range in all cases.

Conclusion: This study successfully demonstrated the ability for internal injury risk models to accurately identify occupants at low risk for internal injury in individual body regions. This represents a step towards incorporating telemetry data into a clinical tool to guide physicians in the use of CT for the evaluation of MVC victims.  相似文献   

10.
为最大程度降低事故损伤度,以碰撞无法避免时的极限工况下车车正碰为研究对象,分析预测车辆碰撞事故损伤度的评价指标,采用正向推理方法建立车车全重叠及斜向碰撞前后速度变化ΔV预测模型,分析不同因素对碰撞前后速度变化ΔV的影响,将其影响关系与事故损伤度标准值关联,进而预测事故损伤度,并以实例验证事故损伤度预测方法。结果表明:当2车碰前相对速度与碰前夹角一定时,事故损伤度与2车质量比成反比关系;当2车质量比与碰前夹角一定时,事故损伤度与碰前相对速度成正比关系;在2车间碰撞无法避免的极限工况下,全重叠碰撞事故损伤度大于斜碰;司机应通过控制本车以较低车速、较小碰前夹角与对方车辆发生碰撞。  相似文献   

11.
采用粉尘浓度统计值建立GM(1,1)模型,进而对粉尘浓度进行预测,说明这种方法的有效性和实用性.  相似文献   

12.
    
Objective: Injury risk curves estimate motor vehicle crash (MVC) occupant injury risk from vehicle, crash, and/or occupant factors. Many vehicles are equipped with event data recorders (EDRs) that collect data including the crash speed and restraint status during a MVC. This study's goal was to use regulation-required data elements for EDRs to compute occupant injury risk for (1) specific injuries and (2) specific body regions in frontal MVCs from weighted NASS-CDS data.

Methods: Logistic regression analysis of NASS-CDS single-impact frontal MVCs involving front seat occupants with frontal airbag deployment was used to produce 23 risk curves for specific injuries and 17 risk curves for Abbreviated Injury Scale (AIS) 2+ to 5+ body region injuries. Risk curves were produced for the following body regions: head and thorax (AIS 2+, 3+, 4+, 5+), face (AIS 2+), abdomen, spine, upper extremity, and lower extremity (AIS 2+, 3+). Injury risk with 95% confidence intervals was estimated for 15–105 km/h longitudinal delta-Vs and belt status was adjusted for as a covariate.

Results: Overall, belted occupants had lower estimated risks compared to unbelted occupants and the risk of injury increased as longitudinal delta-V increased. Belt status was a significant predictor for 13 specific injuries and all body region injuries with the exception of AIS 2+ and 3+ spine injuries. Specific injuries and body region injuries that occurred more frequently in NASS-CDS also tended to carry higher risks when evaluated at a 56 km/h longitudinal delta-V. In the belted population, injury risks that ranked in the top 33% included 4 upper extremity fractures (ulna, radius, clavicle, carpus/metacarpus), 2 lower extremity fractures (fibula, metatarsal/tarsal), and a knee sprain (2.4–4.6% risk). Unbelted injury risks ranked in the top 33% included 4 lower extremity fractures (femur, fibula, metatarsal/tarsal, patella), 2 head injuries with less than one hour or unspecified prior unconsciousness, and a lung contusion (4.6–9.9% risk). The 6 body region curves with the highest risks were for AIS 2+ lower extremity, upper extremity, thorax, and head injury and AIS 3+ lower extremity and thorax injury (15.9–43.8% risk).

Conclusions: These injury risk curves can be implemented into advanced automatic crash notification (AACN) algorithms that utilize vehicle EDR measurements to predict occupant injury immediately following a MVC. Through integration with AACN, these injury risk curves can provide emergency medical services (EMS) and other patient care providers with information on suspected occupant injuries to improve injury detection and patient triage.  相似文献   

13.
采用CFD技术,基于RNG k-ε紊流模型和磨损模型,研究了不同叶型除尘风机的流场和磨损率,证实了后倾型叶片比直叶片能优化流场,改善磨损,使风机使用寿命延长5倍.计算了一定粒度分布的粒子对后倾叶片中的磨损率.结果表明,颗粒粒径和数量浓度的大小是决定磨损程度的重要因素.因此去除大粒径粉尘、降低小粒径粉尘的数量浓度,是减轻叶片磨损的重要途径之一,更是除尘设备的工作方向.  相似文献   

14.
为研究煤矿瓦斯爆炸事故的伤亡规律,以2000-2014年发生的230起重大及以上瓦斯爆炸事故为样本,运用统计学和F-N曲线法对事故特征进行了研究。首先,对事故起数和伤亡情况的时间特征进行了统计;其次,对事故起数和伤亡数量的地域性特征进行了研究;最后,基于F-N曲线法,对事故的死亡人数和受伤人数进行了规律分析。研究结果表明:15年间的瓦斯爆炸事故起数总体上呈逐年下降的趋势,但在2005年出现了峰值,死亡人数与事故起数的变化趋势接近,受伤人数变化趋势不太明显;重特大瓦斯爆炸事故主要发生在中部和西南地区,且尤以山西省最为显著,其事故起数和伤亡人数都是最多的;大多数事故造成了10~30人的死亡,其累计概率曲线在对数坐标中的梯度是-1.642,受伤人数最频繁的区间是1~10人,其累计概率曲线在对数坐标中的梯度是-0.652。  相似文献   

15.
为提高双车道公路小半径曲线路段(SCCR)的交通安全监测水平,利用量表测试与驾驶模拟试验,实现驾驶人弯道焦虑水平的量化评测,定量刻画驾驶人弯道焦虑水平与行车安全特征量之间的关系;通过统计分析焦虑驾驶行为,运用Spearman分析法,筛选影响焦虑水平的关键行车安全特征量;综合道路线形条件、驾驶人个体特征和驾驶操作行为特性等行车安全特征因子,采用径向基神经网络(RBFNN)建立多因素驾驶人焦虑水平预测模型。结果表明:弯道焦虑水平与驾龄、年龄呈显著负相关,与车速、侧向偏移量、转角变异系数以及曲线半径之间存在着较为显著的负相关性(显著性概率p值<0.01);通过验证,基于RBFNN的驾驶人焦虑水平预测模型判别精度可达73.7%;转角变异系数、年龄、驾龄是影响驾驶人焦虑水平的重要因素,其重要度依次为100%、93.3%、90.7%。研究结果可为双车道公路SCCR驾驶焦虑水平监测、交通安全维护等方面提供理论支撑。  相似文献   

16.
针对带式输送机托辊数量众多且分布较散,而现有故障诊断方法准确率低、易受环境影响、监测成本高等问题,提出一种基于声信号的诊断方法。首先,通过伯恩斯全向麦克风采集带式输送机30组托辊工作状态下的声信号;然后,利用统计法分析采集的声信号的时域(TD)特征,实现故障特征初步挖掘;最后,分析声信号的频域(FD)以及时频域(TFD)中所包含的特征,以提高对故障特征的表达能力。结果表明:托辊声音的TD特征能够检测锈蚀故障,FD特征能够检测出严重故障,TFD域特征能够检测出各种典型的轴承损伤,在工业带式输送机托辊故障监测方面具有应用前景。  相似文献   

17.
为提高行李托运差异化安检系统安全性,基于安检设备的依赖关系,提出行李托运安检设备联合响应研究;根据旅客风险属性对其托运行李实施差异化安检,利用二维正态分布建立安检设备的响应分布函数,进行安检设备响应值的数据融合;将系统错误率作为评价指标对比设备联合响应与设备独立响应,分析设备之间的相关系数、报警阈值对系统安全性的影响,并借助ROC曲线得到最优设备报警阈值。研究结果表明:在行李托运差异化安检系统中,设备联合响应优于设备独立响应。研究结果可为民航旅客行李托运安检提供设备支持。  相似文献   

18.
改进GM(1,1)模型在城市环境噪声预测中的应用   总被引:1,自引:2,他引:1  
本文从传统GM(1,1)预测模型构造原理出发分析其存在的不足,指出模型适用于具有较强指数规律的序列,只能描述单调变化过程,而且预测数据序列中出现连续两个相等值时将使得a等于0,会使预测数据发散致使预测失效.文中通过采用平均斜率的概念计算a(k)序列,并利用MATLAB编程实现数据处理.广州市环境噪声污染数据的计算表明,新方法有满意的拟合和预测效果,从而为提高建模精度提供了新的途径.  相似文献   

19.
汽车碰撞兼容性由于能更好地反映真实交通事故,已发展成为被动安全研究领域中最具安全技术潜力的新技术.针对侧面冲击载荷作用下车对车的碰撞兼容性问题,从理论分析和仿真分析角度出发,研究了主要影响因素:两车质量比、汽车前端刚度特性、汽车几何特征对两车碰撞兼容性的影响.结果表明:质量比是影响两车兼容性好坏的关键因素,通过降低汽车前端变形吸能刚度和主吸能位置、提高两车碰撞接触面积等可以提高被撞击车的耐撞性和降低撞击车的攻击性,从而降低所有涉案人员损伤,提高车对车侧面碰撞兼容性.  相似文献   

20.
活性粉末混凝土(RPC)的断裂力学性能   总被引:1,自引:1,他引:0  
在试验及观察的基础上,对活性粉末混凝土的断裂过程进行定性分析,给出活性粉末混凝土的裂纹发展原理及钢纤维的增韧机理,并分析其不同于普通混凝土的两个基本断裂特征.介绍了利用缺口梁三点弯曲试验确定混凝土拉伸软化本构方程的方法.基于Hillerborg模型,提出活性粉末混凝土的拉伸软化模型,根据三点弯曲断裂试验结果,确定出活性粉末混凝土的双线性拉伸软化曲线中的具体参数.据该软化曲线公式,计算出的活性粉末混凝土断裂能同试验得出的值相比,误差仅为0.9%.笔者得出的双线性软化曲线能较精确地反映活性粉末混凝土材料的断裂特性,可为今后进行RPC裂缝的分析和预测提供定量计算的依据,对于研究活性粉末混凝土的断裂能、尺寸效应等问题也很具意义.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号