基于可解释性机器学习的城市O3驱动因素挖掘

受前体物排放和气象条件等因素共同驱动,大气臭氧(O₃)已成为影响城市夏季环境空气质量的主要污染物.目前物理化学机制驱动的演绎模型在进行O₃污染解析时需要的模型参数众多,运算时效性较差;数据驱动的归纳模型运算效率高,但存在可解释性差等问题.通过建立可解释性数据驱动的Correlation-ML-SHAP模型,Correlation模块挖掘O₃浓度关联影响因素,机器学习ML模块耦合可解释性SHAP模块计算各驱动因素对O₃浓度的影响贡献,实现对驱动因素的定量解析,并以晋城市2021年夏季O₃污染过程为例开展应用研究.结果表明,Correlation-ML-SHAP模型能够挖掘并利用强驱动因素模拟O₃浓度和量化影响贡献,其中ML模块采用XGBoost模型模拟准确度最佳. 2021年夏季晋城市O₃污染强驱动因素为：气温、日照强度、湿度和前体物排放水平,贡献权重为：32.1%、 21.3%、 16.5%和15.6%,其中气温、日照强度和前体物排放...     

中国碳排放及影响因素的市域尺度分析

评估区域碳排放及其与社会经济状况的关系对于制定碳减排措施至关重要.以中国339个地级及以上城市(不含新疆部分城市和港澳台地区)为研究对象,探究了非化石能源占比、土地开发度、常住人口城镇化率、第二产业占比、人均GDP和人均建设用地面积对人均CO₂排放量的影响.通过构建模拟人均CO₂排放量的贝叶斯信念网络,识别各因素对人均CO₂排放量的全局影响;采用多尺度地理加权回归模型,分析各因素对人均CO₂排放量的局部影响.结果表明：(1)2020年,中国地级及以上城市人均CO₂排放量呈现出由南向北递增,东部沿海向内陆递减的格局.(2)从全局来看,人均CO₂排放量对各因素的敏感性从高到低依次为：人均建设用地面积>人均GDP>常住人口城镇化率>土地开发度>第二产业占比>非化石能源占比.(3)从局部来看,各因素与人均CO₂排放量的空间关系方向与全局关系一致,关系强度上存在空间异质性.(4)清洁能源、脱碳技术、土地节约集约利用...     

Parents' views of teen driving risks, the role of parents, and how they plan to manage the risks

PROBLEM: There is limited information about how parents view teen driving risks and intend to handle these risks during the licensing process, and how they will respond to graduated licensing provisions. METHODS: Parents in Connecticut were interviewed when their teens got their learner's permit. The survey was undertaken when the state did not have a midnight restriction or a passenger restriction. RESULTS: Generally, parents were well aware of teen driving risks, thought parents should be thoroughly involved in the licensing process, and plan to be active participants themselves. DISCUSSION: Parents were concerned about the risk of driving after midnight and already restrict that behavior. However, parents do not seem to see or understand the risks of having even one teen passenger in the vehicle. IMPACT ON INDUSTRY: The views and existing practices of parents need to be taken into account in deciding on the provisions of graduated licensing legislation and how to best ensure acceptance and compliance.     

Driving anger among motor vehicle drivers in China: A cross-sectional survey

Objective: Driving anger is a common emotion while driving and has been associated with traffic crashes. This study aimed to investigate situations that increase driving anger among Chinese drivers.

Methods: A cross-sectional study was conducted among 3,101 drivers in southern China. The translated version of the 33-item Driving Anger Scale (DAS) was used to measure driving anger. Data were collected by face-to-face interviews between June 2016 and September 2016.

Results: Confirmatory factor analysis showed that the fit of the original 6-factor model (discourtesy, traffic obstacles, hostile gestures, slow driving, illegal driving, and police presence) was satisfactory, after removing 2 items and allowing 5 error pairs to covary. The model showed satisfactory fit: goodness of fit index (GFI) = 0.90, incremental fit index (IFI) = 0.90, root mean square error of approximation (RMSEA) = 0.06, 90% confidence interval (CI) = 0.061–0.064. Driving anger among Chinese drivers was lower than that in some Western countries. Compared to older and experienced drivers, younger and new drivers were more likely to report driving anger. There was no difference in total reported driving anger between males and females. Additionally, the higher the driver’s anger level was, the more likely he or she was to have had a traffic crash.

Conclusion: Driving anger is a common emotion among Chinese drivers and has a strong correlation with aggressive driving behavior and traffic crashes.     

载重车辆超载检测与阻止装置研究

针对载重车辆严重的超载问题,对车辆超载的起因、危害、检测方法等进行了深入的分析,提出了一种基于光电式位移传感器的车辆超载检测与阻止装置,并对其进行了结构设计与原理分析。利用车辆载荷与车身高度之间的对应关系,在车辆静止的状态下,通过检测车架与车桥的距离,判断车辆的载荷情况。根据超载情况提供不同的超载报警提醒,甚至切断起动机电源线、喷油器供电线及点火信号线,使发动机无法起动或正常工作,从而从源头上阻止车辆超载现象的发生。     

Structural equation model analysis for the evaluation of overall driving performance: A driving simulator study focusing on driver distraction

Objective: The present research relies on 2 main objectives. The first is to investigate whether latent model analysis through a structural equation model can be implemented on driving simulator data in order to define an unobserved driving performance variable. Subsequently, the second objective is to investigate and quantify the effect of several risk factors including distraction sources, driver characteristics, and road and traffic environment on the overall driving performance and not in independent driving performance measures.

Methods: For the scope of the present research, 95 participants from all age groups were asked to drive under different types of distraction (conversation with passenger, cell phone use) in urban and rural road environments with low and high traffic volume in a driving simulator experiment. Then, in the framework of the statistical analysis, a correlation table is presented investigating any of a broad class of statistical relationships between driving simulator measures and a structural equation model is developed in which overall driving performance is estimated as a latent variable based on several individual driving simulator measures.

Results: Results confirm the suitability of the structural equation model and indicate that the selection of the specific performance measures that define overall performance should be guided by a rule of representativeness between the selected variables. Moreover, results indicate that conversation with the passenger was not found to have a statistically significant effect, indicating that drivers do not change their performance while conversing with a passenger compared to undistracted driving. On the other hand, results support the hypothesis that cell phone use has a negative effect on driving performance. Furthermore, regarding driver characteristics, age, gender, and experience all have a significant effect on driving performance, indicating that driver-related characteristics play the most crucial role in overall driving performance.

Conclusions: The findings of this study allow a new approach to the investigation of driving behavior in driving simulator experiments and in general. By the successful implementation of the structural equation model, driving behavior can be assessed in terms of overall performance and not through individual performance measures, which allows an important scientific step forward from piecemeal analyses to a sound combined analysis of the interrelationship between several risk factors and overall driving performance.     

基于情感思维的安全管理模式研究

为促进安全管理，提高效率与效果，对基于情感思维的安全管理进行研究，将情感思维融于安全管理，基于情感思维的定义、内涵及功能，具体分析安全管理中情感思维的功能及其功能综合作用，建立安全管理中情感思维功能作用理论模型；根据该理论模型分析情感思维驱动力及强化作用及其对安全目标实现的影响；建立基于情感思维的安全管理设计模式，最后提出优化安全管理的措施与方法，以促进安全管理的实施。研究表明:基于情感思维的安全管理研究，能较好地体现安全管理人本原理，发挥情感的能动作用，将理性融入其中与情感进行平衡，实现安全管理的优化。     

Are older drivers’ driving patterns during an on-road driving task representative of their real-world driving patterns?

Abstract

Objective: The current study investigated whether older drivers’ driving patterns during a customized on-road driving task were representative of their real-world driving patterns.

Methods: Two hundred and eight participants (male: 68.80%; mean age?=?81.52 years, SD?=?3.37 years, range?=?76.00–96.00 years) completed a customized on-road driving task that commenced from their home and was conducted in their own vehicle. Participants’ real-world driving patterns for the preceding 4-month period were also collected via an in-car recording device (ICRD) that was installed in each participant’s vehicle.

Results: During the 4-month period prior to completing the on-road driving task, participants’ median real-world driving trip distance was 2.66?km (interquartile range [IQR]?=?1.14–5.79?km) and their median on-road driving task trip distance was 4.41?km (IQR?=?2.83–6.35?km). Most participants’ on-road driving task trip distances were classified as representative of their real-world driving trip distances (95.2%, n?=?198).

Conclusions: These findings suggest that most older drivers were able to devise a driving route that was representative of their real-world driving trip distance. Future research will examine whether additional aspects of the on-road driving task (e.g., average speed, proportion of trips in different speed zones) are representative of participants’ real-world driving patterns.     

Estimating resource utilization demands in implementing statewide screening,brief intervention,and referral to treatment for alcohol-impaired drivers

Objectives: The Alcohol Use Disorders Identification Test (AUDIT) is used to assess the level of alcohol use/misuse and to inform the intensity of intervention delivered within screening, brief intervention, and referral to treatment (SBIRT) programs. Policy initiatives are recommending delivery of SBIRT within health care settings to reduce alcohol misuse and prevent alcohol-impaired driving. Recent reports are considering extending delivery of SBIRT to criminal justice settings. One consideration in implementing SBIRT delivery is the question of resource utilization; the amount of effort required in delivering the 4 different intensities of intervention in SBIRT: Alcohol education, simple advice, brief counseling and continued monitoring, and brief counseling and referral to specialist (from least to most intense in terms of delivery time, the skill level of the provider, and personnel resources).

Methods: In order to inform expectations about intervention intensity, this article describes the AUDIT scores from 982 adults recently arrested for alcohol-impaired driving. The distribution of scores is extrapolated to state rates for individuals arrested for alcohol-impaired driving by intervention level.

Results: Though alcohol education was the most common intervention category, about one quarter of the sample scored in a range corresponding with the more intensive interventions using the brief counseling, continued monitoring for ongoing alcohol use, and/or referral to specialist for diagnostic evaluation and treatment.

Conclusions: This article provides local distribution of AUDIT scores and state estimates for the number of individuals scoring in each level of risk (AUDIT risk zone) and corresponding intervention type. Routine criminal justice practice is well positioned to deliver alcohol screening, education, simple advice, and continued alcohol monitoring, making delivery of SBIRT feasible for the majority of alcohol-impaired drivers. Challenges to implementing the full range of SBIRT services include resource demands of brief counseling, identifying the appropriate providers within a criminal justice context, and availability of community providers for referral to diagnostic and specialty care. Solutions may vary by state due to differences in population density and incidence rates of alcohol-impaired driving.     

Identification of aggressive driving from naturalistic data in car-following situations

Introduction: Aggressive driving has been associated as one of the causes for crashes, sometimes with very serious consequences. The objective of this study is to investigate the possibility of identifying aggressive driving in car-following situations on motorways by simple jerk metrics derived from naturalistic data. Method: We investigate two jerk metrics, one for large positive jerk and the other for large negative jerk, when drivers are operating the gas and brake pedal, respectively. Results: The results obtained from naturalistic data from five countries in Europe show that the drivers from different countries have a significantly different number of large positive and large negative jerks. Male drivers operate the vehicle with significantly larger number of negative jerks compared to female drivers. The validation of the jerk metrics in identifying aggressive driving is performed by tailgating (following a leading vehicle in a close proximity) and by a violator/non-violator categorization derived from self-reported questionnaires. Our study shows that the identification of aggressive driving could be reinforced by the number of large negative jerks, given that the drivers are tailgating, or by the number of large positive jerks, given that the drivers are categorized as violators. Practical applications: The possibility of understanding, classifying, and quantifying aggressive driving behavior and driving styles with higher risk for accidents can be used for the development of driver support and coaching programs that promote driver safety and are enabled by the vast collection of driving data from modern in-vehicle monitoring and smartphone technology.