The National Highway Traffic Safety Administration’s (NHTSA) guideline on state motor vehicle inspection programs recommends that states should maintain a vehicle safety inspection program to reduce the crash outcomes from the number of vehicles with existing or potential conditions. Some states have started to terminate the vehicle safety inspection program because of insufficient effectiveness measures, budget constraints, and modern safer automobiles. Despite the consensus that these periodic inspection programs improve vehicle condition and improve safety, research remains inconclusive about the effect of safety inspection programs on crash outcomes. There is little recent research on the relationship between vehicle safety inspection programs and whether these programs reduce crash rates or crash severities. According to the 2011–2016 Fatality Analysis Reporting System (FARS) data, nearly 2.6% of fatal crashes happened as a result of the vehicle’s pre-existing manufacturing defects. NHTSA’s vehicle complaint database incorporates more than 1.4 million complaint reports. These reports contain extended information on vehicle-related disruptions. Around 5% of these reports involve some level of injury or fatalities. This study used these two databases to determine the effectiveness of vehicle inspection regulation programs in different states of the U.S. A statistical significance test was performed to determine the effectiveness of the vehicle safety inspection programs based on the states with and without safety inspection in place. This study concludes that there is a need for vehicle safety inspections to be continued for the reduction of vehicle complaints.

No abstract

No abstract

Distraction occurs when a driver’s attention is diverted from driving to a secondary task. The number of distraction-affected crashes has been increasing in recent years. Accurately predicting distraction-affected crashes is critical for roadway agencies to reduce distracted driving behaviors and distraction-affected crashes. Recently, more and more emerging phone-use data and machine learning techniques are available to safety researchers, and can potentially improve the prediction of distraction-affected crashes. Therefore, this study first examines if phone-use events provide essential information for distraction-affected crashes. The authors apply the machine learning technique (i.e., XGBoost) under two scenarios, with and without phone-use events, and compare their performances with two conventional statistical models: logistic regression model and mixed-effects logistic regression model. The comparison demonstrates the superiority of XGBoost over logistic regression with a high-dimensional unbalanced dataset. Further, this study implements SHAP (SHapley Additive exPlanation) to interpret the results and analyze the importance of individual features related to distraction-affected crashes and tests its ability to improve prediction accuracy. The trained XGBoost model achieves a sensitivity of 91.59%, a specificity of 85.92%, and 88.72% accuracy. The XGBoost and SHAP results suggest that: (1) phone-use information is an important factor associated with the occurrences of distraction-affected crashes; (2) distraction-affected crashes are more likely to occur on roadway segments with higher exposure (i.e., length and traffic volume), unevenness of traffic flow condition, or with medium truck volume.