In 2016 alone, around 4000 people died in crashes involving trucks in the USA, with 21% of these fatalities involving only single-unit trucks. Much research has identified the underlying factors for truck crashes. However, few studies detected the factors unique to single and multiple crashes, and none have examined these underlying factors to severe truck crashes in conjunction with violation data. The current research assessed all of these factors using two approaches to improve truck safety. The first approach used ordinal logistic regression to investigate the contributory factors that increased the odds of severe single-truck and multiple-vehicle crashes, with involvement of at least one truck. The literature has indicated that past violations can be used to predict future violations and crashes. Therefore, the second approach used risky violations, related to truck crashes, to identify the contributory factors to the risky violations and truck crashes. Driver actions of failure to keep proper lane following too close and driving too fast for conditions accounted for about 40% of all the truck crashes. Therefore, the same violations as the aforementioned driver actions were included in the analysis. Based on ordinal logistic regression, the analysis for the first approach indicated that being under non-normal conditions at the time of crash, driving on dry-road condition and having a distraction in the cabin are some of the factors that increase the odds of severe single-truck crashes. On the other hand, speed compliance, alcohol involvement, and posted speed limits are some of the variables that impacted the severity of multiple-vehicle, truck-involved crashes. With the second approach, the violations related to risky driver actions, which were underlying causes of severe truck crashes, were identified and analysis was run to identify the groups at increased risk of truck-involved crashes. The results of violations indicated that being nonresident, driving off-peak hours, and driving on weekends could increase the risk of truck-involved crashes. This paper offers an insight into the capability of using violation data, in addition to crash data, in identification of possible countermeasures to reduce crash frequency.

Motor vehicle crashes (MVCs) have a huge cost to society in terms of death, injury and property damage. The cost of fatal MVCs alone is estimated at US $44 billion per year. Among many confounding factors, traffic citations as an element that may reduce MVC frequency are not well understood, and most research carried out to date has evaluated the effects of the total number of citations on the number of MVCs. However, certain types of citations may be more likely to reduce the number of MVCs, whereas other types are not very effective. This research was set out to examine the impact of different types of traffic citations on MVCs on two hazardous main US highways in Wyoming US-30 and US-26. A negative binomial modeling technique was implemented by exploiting 4 years of crash and citations data to identify the causal impacts of traffic citations on crash frequency by incorporating traffic and geometric features. The modeling results showed that higher numbers of speeding and seat belt citations reduce the number of crashes significantly. These findings are the results of law enforcement efforts along the highways. Traffic count and the number of horizontal curves were found to significantly increase the number of MVCs.

The pandemic has posed an intense threat to the mental health of younger adults. Despite significant efforts in studying various aspects of COVID-19, there is a dearth of evidence on how negative emotions are associated with behaviors. A comparison across associated factors to different negative emotions by means of a unified model is especially missing from the literature. This study was conducted by using the results of a survey conducted across 2,534 students enrolled in 7 states in the US. Various feelings such as sad, irritable, stress and guilt were analyzed in a unified model by means of seemingly unrelated regression (SUR). Questions were asked related to rationally limiting the spread of virus, and questions related to behaviors that seem to be extreme. Irrational behaviors, such as limiting exercise at home due to COVID-19 could be due to experiencing negative emotions, which distort the meaning of events for the students. That behavior, for instance, was found to be positively associated with various negative feelings. In addition, the results highlighted significant differences across emotions in terms of demographic characteristics such as gender and age, and various precautionary actions that students take, such as limiting outdoor activities or limiting social gathering. For instance, it was highlighted while avoiding a large group of people, in spite of its importance in curbing the spread of virus, is negatively associated with various negative emotions, taking a possible nonconsequential precaution of completely limiting all people outside the immediate family result in a higher level of negative emotions. Also, it was found that having a higher body mass index (BMI), self-rated worse health conditions, and limiting outdoor activities have detrimental effects on the mental health of students.

Machine learning (ML) techniques play a crucial role in today's modern world. Over the last years, road traffic safety is one of the applications where ML‐methods have been successfully employed to prevent road users from being killed or seriously injured. A reliable data‐driven predictive model is essential for this purpose. This could be achieved by successfully applying an intelligent transportation system to identify a driver at a higher risk of crashes. This study investigates the capabilities of different deep learning techniques to predict motorcycle crash severity. This study is based on 2,430 motorcycle crashes in a mountainous area in the United States over a 10‐year period. Different deep networks (DNNs), including deep belief network, standard recurrent neural network (RNN), multilayer neural network, and single‐layer neural network, were considered and compared in terms of prediction accuracy of motorcycle crash severity. Before conducting any analysis, feature reduction was performed to identify the optimal number of variables to include in the models by minimizing the error rate. Different metrics including the area under the curve and confusion matrix were used to compare the different models. Although the analyses were conducted on a relatively small dataset, the results indicate that almost all the DNN models better perform in predicting the severity of motorcycle crashes, compared with the single layer neural network. Finally, the RNN outperforms the other three neural network models. A comprehensive discussion has been made about the methodological approach implemented in this study.