Fatal and serious road crashes involving young New Zealand drivers: a latent class clustering approach

A novel hazard avoidance model based on young drivers' characteristics: A driving simulator study

This paper aims to examine the key factors influencing young drivers' hazard avoidance in Iran. In this study, a hazard avoidance index is defined and calculated for investigating the effect of impulsiveness, behavioral, and psychological characteristics on driving hazard avoidance. A questionnaire and go-no-go and flanker computer tests as well as a driving simulator are used for collecting data from 173 Iranian drivers under the age of 30. For this purpose, different scenarios were used, such as pedestrian crossing, the presence of fixed obstacles, and animals crossing the road, whose various characteristics are also changed. Structural equation modeling and the partial least squares method are applied for investigating the relationship between different variables and the hazard avoidance index. The results show that the driver hazard avoidance index is mostly affected by variables such as inhibitory control, opposite directional response, attentional impulsiveness, motion impulsiveness, non-planning impulsiveness, disregarding the law, and lapses and error. The results could help policymakers to assess diving hazard avoidance and improve training programs related to traffic safety based on the variables that are more effective on inexperienced and novice drivers' hazard avoidance.

Investigating risk factors associated with injury severity in highway crashes: A hybrid approach integrating two-step cluster analysis and latent class ordered regression model with covariates

Highway crashes are responsible for a significant number of severe and fatal injuries drawing considerable attention from transportation authorities and safety researchers. This paper aims to investigate the unobserved heterogeneous effects of various risk factors, such as pre-crash circumstances, environmental and road conditions, vehicle-involved information, and driver attributes on injury severities. Our methodology uses a hybrid approach that combines two-step cluster analysis and latent class ordered regression model with covariates. The proposed approach extends traditional latent class model by elucidating potential relationships among predictors, covariates, and outcomes. A cross-sectional crash data covering a period of over five years (2011-2016) was obtained via the Dutch crash registration database for modeling injury severity outcomes. The results reveal substantial and statistically significant differences in injury severity between two latent classes. Moreover, we identify road lighting, time of crash, road surface conditions, weather, and season as covariates influencing class membership prediction. Factors such as high speed, alcohol involvement, frontal collision points, and older driver demographics increase the probability of serious injury and facility across all cases analyzed. Additionally, we observe notable heterogeneity effects between the two classes regarding temporal characteristics, the number and type of vehicles involved, as well as driver gender. Our findings provide specific and valuable insights into injury severity outcomes, which can inform the formulation of targeted safety countermeasures and regulatory strategies for traffic policies and relevant agencies.

Unveiling the relevance of traffic enforcement cameras on the severity of vehicle-pedestrian collisions in an urban environment with machine learning models

PURPOSE

One of the leading causes of violent fatalities around the world is road traffic collisions, and pedestrians are among the most vulnerable road users with respect to such incidents. Since walking is highly promoted in urban areas to alleviate motor-vehicle externalities, it is paramount to understand the causes associated with vehicle-pedestrian collisions and their severity to provide safe environments. Although traffic enforcement cameras can address vehicle-vehicle collisions, little is known about their effectiveness with respect to vehicle-pedestrian incidents.

METHODOLOGY

In this study, we trained a set of machine learning models to forecast if a vehicle-pedestrian collision will turn into an injury or fatality, and the most suitable model was used to investigate the contributing features associated with such events with emphasis on the impact of traffic enforcement cameras. In addition to traffic enforcement camera proximity, features associated with the collision, weather, vehicle, victim, and infrastructure are included in the model to reduce unobserved heterogeneity.

RESULTS

Results show that a Linear Discriminant Analysis model surpasses other machine learning models considering the evaluation metrics. Results reveal that the age and gender of the victim, the involvement of larger vehicles in the collision, and the quality of the illumination are the causes associated with pedestrian fatalities. On the other hand, involvement of motorcycles and collisions that occurred in densely populated locations are the causes associated with pedestrian injuries.

CONCLUSIONS

This investigation demonstrates how to articulate machine learning into a vehicle-pedestrian crash analysis to understand the direction and magnitude of covariates in the corresponding severity outcome. Furthermore, it highlights the remarkable effect that traffic enforcement cameras and other features have on vehicle-pedestrian crash severity. These results provide actionable guidance for educational campaigns, enhanced traffic engineering, and infrastructure improvements that could be implemented in the analyzed region to provide safer transportation.

The Analysis of Spatial Patterns and Significant Factors Associated with Young-Driver-Involved Crashes in Florida

Over the last three decades, traffic crashes have been one of the leading causes of fatalities and economic losses in the U.S.; compared with other age groups, this is especially concerning for the youth population (those aged between 16 and 24), mostly due to their inexperience, greater inattentiveness, and riskier behavior while driving. This research intends to investigate this issue around selected Florida university campuses. We employed three methods: (1) a comparative assessment for three selected counties using both planar Euclidean Distance and Roadway Network Distance-based Kernel Density Estimation methods to determine high-risk crash locations, (2) a crash density ratio difference approach to compare the maxima-normalized crash densities for the youth population and those victims that are 25 and up, and (3) a logistic regression approach to identify the statistically significant factors contributing to young-driver-involved crashes. The developed GIS maps illustrate the difference in spatial patterns of young-driver crash densities compared to those for other age groups. The statistical findings also reveal that intersections around university areas appear to be significantly problematic for youth populations, regardless of the differences in the general perspective of the characteristics of the selected counties. Moreover, the speed limit countermeasures around universities could not effectively prevent young-driver crash occurrences. Hence, the results of this study can provide valuable insights to transportation agencies in terms of pinpointing the high-risk locations around universities, assessing the effectiveness of existing safety countermeasures, and developing more reliable plans with a focus on the youth population.

Exploring the severity of bicycle-vehicle crashes using latent class clustering approach in India

INTRODUCTION

Bicyclists are vulnerable users in the shared asset like roadways. However, people still prefer to use bicycles for environmental, societal, and health benefits. In India, the bicycle plays a role in supporting the mobility to more people at lower cost and are often associated with the urban poor. Bicyclists represents one of the road user categories with highest risk of injuries and fatalities. According to the report by the Ministry of Road Transport and Highways (Accidents, 2017) in India, there is a sharp increase in the number of fatal victims for bicyclists in 2017 over 2016. The number of cyclists killed jumped from 2,585 in 2016 to 3,559 in 2017, a 37.7% increase.

METHOD

Few studies have only investigated the crash risk perceived by the bicyclists while interacting with other road users. The present paper investigates the injury severity of bicyclists in bicycle-vehicle crashes that occurred in the state of Tamilnadu, India during the nine year period (2009-2017). The analyses demonstrate that dividing bicycle-vehicle collision data into five clusters helps in reducing the systematic heterogeneity present in the data and identify the hidden relationship between the injury severity levels of bicyclists and cyclists demographics, vehicle, environmental, temporal cause for the crashes.

RESULTS

Latent Class Clustering (LCC) approach was used in the present study as a preliminary tool for the segmentation of 9,978 crashes. Later, logistic regression analysis was used to identify the factors that influence bicycle crash severity for the whole dataset as well as for the clusters that were obtained from the LCC model. Results of this study show that combined use of both techniques reveals further information that wouldn't be obtained without prior segmentation of the data. Few variables such as season, weather conditions, and light conditions were significant for certain clusters that were hidden in the whole dataset. This study can help domain experts or traffic safety researchers to segment traffic crashes and develop targeted countermeasures to mitigate injury severity.

Finding causation in occupational fatalities: A latent class analysis

BACKGROUND

The method "Learning by mistakes" was developed in Italy to conduct occupational injury investigations and to collect information on the genesis of injuries. The aim is to analyze data classified with this method in order to identify patterns among the factors contributing to injury dynamics.

METHODS

Data regarding 673 factors, corresponding to 354 occupational fatalities that occurred in the Piedmont region (north-west of Italy) during 2005-2014 were considered. Latent Class Analysis (LCA) was applied to find patterns among these factors.

RESULTS

The eight-class model was selected. Most of the factors fell in the class "Fall from height or vehicle rollover due to incorrect practice" (40.56%) while the remaining factors where heterogeneously distributed in the other classes.

CONCLUSIONS

All the classes found allow for a logical interpretation. Systematic use of LCA could aid in uncovering new, unexpected patterns of factors not otherwise detectable by analysis of the single fatal accident.

Definition of run-off-road crash clusters-For safety benefit estimation and driver assistance development

Single-vehicle run-off-road crashes are a major traffic safety concern, as they are associated with a high proportion of fatal outcomes. In addressing run-off-road crashes, the development and evaluation of advanced driver assistance systems requires test scenarios that are representative of the variability found in real-world crashes. We apply hierarchical agglomerative cluster analysis to define similarities in a set of crash data variables, these clusters can then be used as the basis in test scenario development. Out of 13 clusters, nine test scenarios are derived, corresponding to crashes characterised by: drivers drifting off the road in daytime and night-time, high speed departures, high-angle departures on narrow roads, highways, snowy roads, loss-of-control on wet roadways, sharp curves, and high speeds on roads with severe road surface conditions. In addition, each cluster was analysed with respect to crash variables related to the crash cause and reason for the unintended lane departure. The study shows that cluster analysis of representative data provides a statistically based method to identify relevant properties for run-off-road test scenarios. This was done to support development of vehicle-based run-off-road countermeasures and driver behaviour models used in virtual testing. Future studies should use driver behaviour from naturalistic driving data to further define how test-scenarios and behavioural causation mechanisms should be included.