Applying interpretable machine learning to classify tree and utility pole related crash injury types

In spite of enormous improvements in vehicle safety, roadway design, and operations, there is still an excessive amount of traffic crashes resulting in injuries and major productivity losses. Despite the many studies on factors of crash frequency and injury severity, there is still further research to be conducted. Tree and utility pole/other pole related (TUOP) crashes present approximately 12 to 15% of all roadway departure (RwD) fatal crashes in the U.S. The count of TUOP crashes comprise nearly 22% of all fatal crashes in Louisiana. From 2010 to 2016, there were 55,857 TUOP crashes reported in Louisiana. Individually examining each of these crash reports is not a realistic option to investigate crash factors. Therefore, this study employed text mining and interpretable machine learning (IML) techniques to analyze all TUOP crashes (with available crash narratives) that occurred in Louisiana from 2010 to 2016. This study has two major goals: 1) to develop a framework for applying machine learning models to classify injury levels from unstructured textual content, and 2) to apply an IML framework that provides probability measures of keywords and their association with the injury classification. The present study employed three machine learning algorithms in the classification of injury levels based on the crash narrative data. Of the used modeling techniques, the eXtreme gradient boosting (XGBoost) model shows better performance, with accuracy ranging from 0.70 to 24% for the training data and from 0.30% to 16% for the test data.     

Using machine leaning techniques for evaluation of motorcycle injury severity

There is a growing interest in the application of the machine learning techniques in predicting the motorcycle crash severity. This is partly due to a progress in autonomous vehicles technology, and machine learning technique, which as a main component of autonomous vehicle could be implemented for traffic safety enhancement. Wyoming's motorcycle crash fatalities constitute a concern since the count of riders being killed in motorcycle crashes in 2014 was 11% of the total road fatalities in the state. The first step of crash reduction could be achieved through identification of contributory factors to crashes. This could be accomplished by using a right model with high accuracy in predicting crashes. Thus, this study adopted random forest, support vector machine, multivariate adaptive regression splines and binary logistic regression techniques to predict the injury severity outcomes of motorcycle crashes. Even though researchers applied all the aforementioned techniques to model motorcycle injury severities, a comparative analysis to assess the predictive power of such modeling frameworks is limited. Hence, this study contributes to the road safety literature by comparing the performance of the discussed techniques. In this study, Wyoming's motorcycle crash injury severities are modeled as functions of the characteristics that give rise to crashes. Before conducting any analyses, feature reduction was used to identify a best number of predictors to be included in the model. Also to have an unbiased estimation of the performance of different machine learning techniques, 5-fold cross-validation was used for model performance evaluation. Two measure, Area under the curve (AUC), and confusion matrix were used to compare different models' performance. The machine learning results indicate that random forest model outperformed the other models with the least misclassification and higher AUC. It was also revealed that a dichotomous response variable, with fatality and incapacitation injury in one category, along with all other categories in another group would result in a lower misclassification rate than a polychotomous response variable. This might result from the nature of motorcycle crashes, lacking a protection compared with passenger cars, preventing machine learning technique to get trained properly. Moreover, the most important variables identified by the random forest model are those related to the operating speed, resentful other party, traffic volume, truck traffic volume, riding under the influence, horizontal curvature, wide roadway with more than two lanes and rider's age.     

Severity analysis of tree and utility pole crashes: Applying fast and frugal heuristics

A roadway departure (RwD) crash is defined as a crash that occurs after a vehicle crosses an edge line or a center line, or otherwise leaves the designated travel path. RwD crashes account for approximately 50% of all traffic fatalities in the U.S. Additionally, crashes related to roadside fixed objects such as trees, utility poles, or other poles (TUOP) make up 12–15% of all fatal RwD crashes in the U.S. Data spanning over seven years (2010–2016) shows that TUOP crashes account for approximately 22% of all fatal crashes in Louisiana, which is significantly higher than the national statistic. This study aims to determine the effect of crash, geometric, environmental, and vehicle characteristics on TUOP crashes by applying the fast and frugal tree (FFT) heuristics algorithm to Louisiana crash data. FFT identifies five major cues or variable threshold attributes that contribute significantly to predicting TUOP crashes. These cues include posted speed limit, primary contributing factor, highway type, weather, and locality type. The balanced accuracy is around 56% for both training and test data. The current model shows higher accuracies compared to machine learning models (e.g., support vector machine, CART). The present findings emphasize the importance of a comprehensive understanding of factors that influence TUOP crashes. The insights from this study can help data-driven decision making at both planning and operation levels.     

Crash prediction model for two-lane rural highways in the Ashanti region of Ghana

Crash Prediction Models (CPMs) have been used elsewhere as a useful tool by road Engineers and Planners. There is however no study on the prediction of road traffic crashes on rural highways in Ghana. The main objective of the study was to develop a prediction model for road traffic crashes occurring on the rural sections of the highways in the Ashanti Region of Ghana. The model was developed for all injury crashes occurring on selected rural highways in the Region over the three (3) year period 2005–2007. Data was collected from 76 rural highway sections and each section varied between 0.8 km and 6.7 km. Data collected for each section comprised injury crash data, traffic flow and speed data, and roadway characteristics and road geometry data. The Generalised Linear Model (GLM) with Negative Binomial (NB) error structure was used to estimate the model parameters. Two types of models, the ‘core’ model which included key exposure variables only and the ‘full’ model which included a wider range of variables were developed. The results show that traffic flow, highway segment length, junction density, terrain type and presence of a village settlement within road segments were found to be statistically significant explanatory variables (p < 0.05) for crash involvement. Adding one junction to a 1 km section of road segment was found to increase injury crashes by 32.0% and sections which had a village settlement within them were found to increase injury crashes by 60.3% compared with segments with no settlements. The model explained 61.2% of the systematic variation in the data. Road and Traffic Engineers and Planners can apply the crash prediction model as a tool in safety improvement works and in the design of safer roads. It is recommended that to improve safety, highways should be designed to by-pass village settlements and that the number of junctions on a highway should be limited to carefully designed ones.     

Modeling two-way stop-controlled intersection crashes with zero-inflated models on Louisiana rural two-lane highways

Intersection safety continues to be a crucial issue throughout the United States. In 2016, 27% of the 37,461 traffic fatalities on U.S. roadways occurred at or near intersections. Nearly 70% of intersection-related fatalities occurred at unsignalized intersections. At such intersections, vehicles stopping or slowing to turn create speed differentials between vehicles traveling in the same direction. This is particularly problematic on two-lane highways. Research was performed to analyze safety performance for intersections on rural, two-lane roadways, with stop control on the minor roadway. Roadway, traffic, and crash data were collected from 4148 stop-controlled intersections of all 64 Parishes (counties) statewide in Louisiana, for the period of 2013 to 2017. Four count approaches, Poisson, Negative Binomial (NB), Zero-inflated Poisson (ZIP) and Zero-inflated Negative Binomial (ZINB) were used to model the number of intersection crashes for different severity levels. The results indicate that ZIP models provide a better fit than all other models. In addition to traffic volume, larger curve radii of major and minor roads and wider lane widths of major roads led to significantly smaller crash occurrences. However, higher speed limits of major roads led to significantly greater crash occurrences. Four-leg stop-controlled intersections have 35% greater total crashes, 49% greater fatal and injury crashes, and 25% greater property damage only (PDO) crashes, relative to three-leg intersections.     

零截尾负二项模型在交叉口事故预测中的应用

事故预测模型是广泛采用的交通安全定量分析方法，但往往要求具有完备的道路、交通和事故数据。然而，基础数据相对不健全是包括中国在内的发展中国家交通安全管理面临的主要问题之一，例如仅有发生事故路段或者交叉口的相关属性特征（即零截尾数据）。为此，为确保基础数据不全的情况下交叉口事故预测的准确性，提出了基于零截尾的广义负二项回归模型；采集了246个非信号控制交叉口的交通与事故数据，采用传统负二项模型和新提出的零截尾负二项模型对全数据和零截尾数据分别进行对比分析。结果表明：在针对截尾数据的分析中，零截尾负二项模型明显优于传统负二项模型，并且零截尾负二项模型的参数估计值与基于全数据的负二项基准模型的估计值非常接近；在所有模型中，交叉口的主路交通量和支路交通量与交叉口的安全性之间存在较大的正关联。此外，同等条件下，十字形交叉口的事故数量高于T形交叉口的事故数量；利用传统负二项分布模型分析截尾数据得到的事故预测模型与使用全数据的基准模型有显著差异，其结果不可靠；采用零截尾负二项分布模型的参数结果与基准模型基本一致，截尾模型的置信区间包含基准模型相应的参数估计值。当受条件所限无法获取全部数据时，可以考虑使用零截尾负二项模型进行安全分析。     

Association of reduced visibility with crash outcomes

Most of the information necessary for driving a vehicle is regarded as visual information. In spite of its importance, visibility conditions at the time of a crash are often not documented at a high level of detail. Past studies have not examined the quantified values of visibility and its association with crashes. The current study merged data collected from the National Oceanic and Atmospheric Administration (NOAA) with 2010–2012 Florida crash data. From the thousands of logged weather events compiled by the NOAA, the researchers isolated periods of normal visibility and comparable periods of reduced visibility in a matched-pairs study. The NOAA data provided real visibility score based on the spatiotemporal data of the crashes. Additionally, the crash data, obtained from Roadway Information Database (RID), contains several geometric and traffic variables that allow for effects of factors and visibility. The study aims to associate crash occurrence under different levels of visibility with factors included in the crash database by developing ordinal logistic regression. The intent is to observe how different visibility conditions contribute to a crash occurrence. The findings indicate that the likelihood of a crash increase during periods of low visibility, despite the tendency for less traffic and for lower speeds to prevail during these times. The findings of this study will add valuable knowledge to the realm of the impact of visibility in the way of using and designing appropriate countermeasures.     

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.     

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.     

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。     

Crash risk factors associated with injury severity of teen drivers

This paper focuses on identifying crash risk factors associated with injury severity of teen drivers. Crash data obtained from the Highway Safety and Information System (HSIS) for the entire state of North Carolina, for years 2011 to 2013, was used for analysis and modeling. Among all the crashes during the study period, a total of 62,990 crashes involving teen drivers (15 to 19?years) were analyzed. A partial proportionality odds model was developed to identify factors contributing to injury severity of teen drivers. The results obtained indicate that teen drivers driving sports utility vehicles and pickup trucks are more likely to be severely injured when compared to teen drivers driving passenger cars. Teen drivers are more likely to be severely injured on weekdays, particularly during peak hours. The chances of teen drivers getting involved in severe injury crashes on Tuesdays and Fridays is higher when compared to Sundays. Age, gender, road configuration, terrain, adverse weather condition, and access control are observed to have a significant effect on teen driver's injury severity.     

Modelling traffic safety at uncontrolled median openings: A case study in India

Assessment of traffic safety is an essential study in transportation engineering. In a developing country like India, around 150,000 people die in road crashes every year. Furthermore, at uncontrolled median openings, the severity of road crashes is higher due to the presence of impatient U-turning road users who don't obey the rule of priority. Traditionally, road crash data have been used since long to analyze traffic safety. However, in developing countries, the main drawback of this conventional method is limited availability of accident data as very few accidents get reported. Moreover, the accuracy of these reported data is questionable. Therefore, now-a-days, various surrogate traffic safety measures like Post Encroachment Time (PET), and Time to Collision (TTC) are being used to examine the safety of road users. Among them, PET is regarded as the most consistent, and most widely used safety indicator. Therefore, in the present study, PET across different traffic volume levels has been determined. Videography data has been collected from selected median openings located on six-lane divided urban roads. PET values for different traffic volumes, and different category of vehicles have been analysed in detail. Further, the distribution of PET values across the full width of road has also been studied. Concept of critical speed is introduced which is compared with conflicting speed to assess unsafe conflicts and determine a critical PET. Finally, regression models have also been proposed with good levels of accuracy to determine the PET values for various category of vehicles travelling at different conflicting speeds.     

Modeling lane-change-related crashes with lane-specific real-time traffic and weather data

This study investigates the relationship between lane-change-related crashes and lane-specific, real-time traffic factors. It is anticipated that the real-time traffic data for the two lanes—the vehicle's lane (subject lane) and the lane to which that a vehicle intends to change (target lane)—are more closely related to lane-change-related crashes, as opposed to congregated traffic data for all lanes. Lane-change-related crash data were obtained from a 62-mile long freeway in Southeast Wisconsin in 2012 and 2013. One-minute traffic data from the 5- to 10-minute interval prior to the crashes were extracted from an immediately upstream detector station and two immediately downstream stations from the crash location. Weather information was collected from a major historical weather database. A matched case-control logistic regression was used for analysis. Results show that the following factors significantly affect the probability of a lane-change-related crash: average flow into the target lane at the first downstream station, the flow ratio at the second downstream station, and snow conditions. Additionally, the average speed in the target lane at the first downstream station contributes to the occurrence of lane-change crashes during snowy conditions. According to the model, the probability of a lane-change-related crash under real-time traffic conditions can aid in flagging potential crash-prone conditions. The identified contributing factors can help traffic operators select traffic control and management countermeasures to proactively mitigate lane-change-related crashes.     

Odds of work zone crash occurrence and getting involved in advance warning,transition, and activity areas by injury severity

Work zone area types include advance warning area, transition area, and activity area. The geometric conditions, traffic control aspects, traffic operations, and driver's maneuverability differ within each work zone area type. Therefore, the odds of getting involved in a crash and factors associated with injury severity vary by work zone area type. The focus of this research is to examine the odds of getting involved in a crash in work zone advance warning, transition, and activity areas by injury severity. Five years (2010–2014) of crash data for the state of North Carolina was obtained from the Highway Safety Information Systems (HSIS) and used in this research. Three partial proportional odds models and one proportional odds model were developed using Statistical Analysis Software (SAS) in this research. The results indicate that the odds of getting involved in a work zone crash in the transition area when compared to the advance warning area is higher during cloudy weather condition, on wet roads and interstates, and on roads equipped with double yellow / no passing zone, with rigid post barrier, grass, and flexible post barrier median. Further, the odds of getting involved in a work zone crash in the activity area when compared to the advance warning area is higher during cloudy weather condition, on interstate and US routes, and on roads with stop and go signal, double yellow / no passing zone and flexible post barrier median. Overall, the findings indicate that the odds and factors associated with crash occurrence depend on the work zone area type. The odds of getting involved in a severe or moderate injury crash is higher on curved roads in all the three work zone area types compared to straight roads. It is higher 1) in the advance warning area on roads with semi-flexible post barrier medians, 2) in the transition area on US routes, and 3) in the activity area on dark lighted roads, US routes, and State routes. Overall, the odds of getting involved in a severe or moderate injury crash and associated factors vary by work zone area type. The findings from this research assist the practitioners to take precautionary measures and reduce the odds of getting involved in a crash by implementing work zone area-specific safety countermeasures.     

Run-off-road and recovery – state estimation and vehicle control strategies

Despite many advances in vehicle safety technology, traffic fatalities remain a devastating burden on society. With over two-thirds of all fatal single-vehicle crashes occurring off the roadway, run-off-road (ROR) crashes have become the focus of much roadway safety research. Current countermeasures, including roadway infrastructure modifications and some on-board vehicle safety systems, remain limited in their approach as they do not directly address the critical factor of driver behaviour. It has been shown that ROR crashes are often the result of poor driver performance leading up to the crash. In this study, the performance of two control algorithms, sliding control and linear quadratic control, was investigated for use in an autonomous ROR vehicle recovery system. The two controllers were simulated amongst a variety of ROR conditions where typical driver performance was inadequate to safely operate the vehicle. The sliding controller recovered the fastest within the nominal conditions but exhibited large variability in performance amongst the more extreme ROR scenarios. Despite some small sacrifices in lateral error and yaw rate, the linear quadratic controller demonstrated a higher level of consistency and stability amongst the various conditions examined. Overall, the linear quadratic controller recovered the vehicle 25% faster than the sliding controller while using 70% less steering, which combined with its robust performance, indicates its high potential as an autonomous ROR countermeasure.     

基于GIS分析的深圳市道路交通事故空间分布特征研究

掌握城市道路交通事故空间分布特征是城市道路交通安全管理的重要基础。基于深圳市2014~2016年的道路交通事故数据,首先应用地理编码方法对原始事故记录进行空间定位,形成事故的空间分布。其次针对考虑/不考虑路网密度的2种情况,应用密度分析方法对道路交通事故多发的区域和事故严重程度较高的区域进行鉴别,比较2种情况下区域分布的差异并分析造成这种差异的可能原因。最后利用异常点分析和热点分析2种空间聚类分析模型对事故严重程度较高的区域进行进一步鉴别,并对密度分析和聚类分析2种方法得到的结果进行了比较。密度分析结果表明：就事故频度而言,深圳市中心城区单位面积上的交通事故频度较高,而郊区单位长度道路上的交通事故分布更为密集;就事故严重程度而言,郊区的交通事故平均严重程度高于市中心区域。造成上述差异的原因可能与郊区道路限速较高等因素有关。聚类分析结果与密度分析结果相近,在郊区形成了高严重程度的事故聚类,而在中心城区形成了低严重程度的事故聚类,说明郊区的交通事故严重程度总体高于市中心区域。从2种方法的比较来看,密度分析简单易行,有助于交通管理部门对城市交通事故空间分布特征直观快速的了解;聚类分析可精确到事故点,为精细化的交通安全管理工作提供支撑。研究结果表明基于密度分析和聚类分析的研究方法对于确定道路交通事故空间分布特征有良好的作用。     

高速公路穿越村镇路段安全性分析及处置措施

依托京昆高速石家庄至冀晋界段建设工程,采用运行速度分析方法,提出了高速公路穿村镇路段的安全性评价方法,分别就路基段和桥梁段进行了分析,为公路的安全性评估提供了一种方法,并提供了相应的处置措施供设计、管理单位参考.     

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.     

Road characteristics and environment factors associated with motorcycle fatal crashes in Malaysia

This study aims to determine risk factors contributing to traffic crashes in 9,176 fatal cases involving motorcycle in Malaysia between 2010 and 2012. For this purpose, both multinomial and mixed models of motorcycle fatal crash outcome based on the number of vehicle involved are estimated. The corresponding model predicts the probability of three fatal crash outcomes: motorcycle single-vehicle fatal crash, motorcycle fatal crash involving another vehicle and motorcycle fatal crash involving two or more vehicles. Several road characteristic and environmental factors are considered including type of road in the hierarchy, location, road geometry, posted speed limit, road marking type, lighting, time of day and weather conditions during the fatal crash. The estimation results suggest that curve road sections, no road marking, smooth, rut and corrugation of road surface and wee hours, i.e. between 00.00 am to 6 am, increase the probability of motorcycle single-vehicle fatal crashes. As for the motorcycle fatal crashes involving multiple vehicles, factors such as expressway, primary and secondary roads, speed limit more than 70 km/h, roads with non-permissible marking, i.e. double lane line and daylight condition are found to cause an increase the probability of their occurrence. The estimation results also suggest that time of day (between 7 pm to 12 pm) has an increasing impact on the probability of motorcycle single-vehicle fatal crashes and motorcycle fatal crashes involving two or more vehicles. Whilst the multinomial logit model was found as more parsimonious, the mixed logit model is likely to capture the unobserved heterogeneity in fatal motorcycle crashes based on the number of vehicles involved due to the underreporting data with two random effect parameters including 70 km/h speed limit and double lane line road marking.     

Normal and risky driving patterns identification in clear and rainy weather on freeway segments using vehicle kinematics trajectories and time series cluster analysis

Enhancing traffic safety on freeways is the main goal for all transportation agencies. However, to achieve this goal, many analysis protocols of network screening models need to be improved through considering human factors while analyzing traffic data. This paper introduces one on the new analysis protocol of identifying and discriminating between normal and risky driving in clear and rainy weather. The introduced analysis protocol will consider the effect of human factors on updating the networking screening process of identifying hotspots of crash risk. This paper employs the Second Strategic Highway Research Program (SHRP2) Naturalistic Driving Study (NDS) data to investigate the behavior of normal and risky driving under both rainy and clear weather conditions. Near-crash events on freeways, which were used as Surrogate Measure of Safety (SMoS) for crash risk, were identified based on the changes in vehicle kinematics, including speed, longitudinal and lateral acceleration and deceleration rates, and yaw rates. Through a trajectory-level data analysis, there were significant differences in driving patterns between rainy and clear weather conditions; factors that affected crash risk mainly included driver reaction and response time, their evasive maneuvers such as changes in acceleration rates and yaw rates, and lane-changing maneuvers. A cluster analysis method was employed to classify driving patterns into two clusters: normal and risky driving condition patterns, respectively. Statistical results showed that risky driving patterns started on average one second earlier in rainy weather conditions than in clear weather conditions. Furthermore, risky driving patterns extended in average three seconds in rainy weather conditions, while it was two seconds in clear weather conditions. The identification of these patterns is considered as a primary step towards an automated development that would distinguish between different driving patterns in a Connected Vehicle CV environment using Basic Safety Messages (BSM) and to enhance the network screening analysis for increased crash risk hotspots.