Analysis of traffic injury severity: an application of non-parametric classification tree techniques

Statistical regression models, such as logit or ordered probit/logit models, have been widely employed to analyze injury severity of traffic accidents. However, most regression models have their own model assumptions and pre-defined underlying relationships between dependent and independent variables. If these assumptions are violated, the model could lead to erroneous estimations of injury likelihood. The classification and regression tree (CART), one of the most widely applied data mining techniques, has been commonly employed in business administration, industry, and engineering. CART does not require any pre-defined underlying relationship between target (dependent) variable and predictors (independent variables) and has been shown to be a powerful tool, particularly for dealing with prediction and classification problems. This study uses the 2001 accident data for Taipei, Taiwan. A CART model was developed to establish the relationship between injury severity and driver/vehicle characteristics, highway/environmental variables and accident variables. The results indicate that the most important variable associated with crash severity is the vehicle type. Pedestrians, motorcycle and bicycle riders are identified to have higher risks of being injured than other types of vehicle drivers in traffic accidents.     

Identifying crash contributory factors at urban roundabouts and using association rules to explore their relationships to different crash types

The use of roundabouts improves intersection safety by eliminating or altering conflict types, reducing crash severity, and causing drivers to reduce speeds. However, roundabout performances can degrade if precautions are not taken during either the design or the operation phase. Therefore, additional information on the safety of the roundabouts is extremely helpful for planners and designers in identifying existing deficiencies and in refining the design criteria currently being used. The aim of the paper was to investigate the crash contributory factors in 15 urban roundabouts located in Italy and to study the interdependences between these factors.The crash data refer to the period 2003–2008. The identification of the crash contributory factors was based on site inspections and rigorous analyses performed by a team of specialists with a relevant road safety engineering background. Each roundabout was inspected once every year from 2004 to 2009, both in daytime and in nighttime. Overall, 62 different contributory factors and 2156 total contributory factors were identified. In 51 crashes, a single contributory factor was found, whereas in the other 223 crashes, a combination of contributory factors was identified. Given the large amount of data, the interdependences between the contributory factors and between the contributory factors and the different crash types were explored by an association discovery. Association discovery is the identification of sets of items (i.e., crash contributory factors and crash types in our study) that occur together in a given event (i.e., a crash in our study). The rules were filtered by support, confidence, and lift. As a result, 112 association rules were discovered.Overall, numerous contributory factors related to the road and environment deficiencies but not related to the road user or to the vehicle were identified. The most important factors related to geometric design were the radius of deflection and the deviation angle. In existing roundabouts, the improvement of these factors might be quite expensive, but the crucial role of a moderate radius of deflection and a large deviation angle in the design of new roundabouts was stressed. Many of the contributory factors were related to markings and signs, and these factors could be easily removed with low-cost safety measures. Furthermore, because of the association between the markings, signs, and geometric design contributory factors, the study results suggest that the improvement in markings and signs might also have a significant effect in the sites where geometric design deficiencies were identified as contributory factors.     

Industrial and occupational ergonomics in the petrochemical process industry: a regression trees approach

This work is an attempt to apply classification tree methods to data regarding accidents in a medium-sized refinery, so as to identify the important relationships between the variables, which can be considered as decision-making rules when adopting any measures for improvement. The results obtained using the CART (Classification And Regression Trees) method proved to be the most precise and, in general, they are encouraging concerning the use of tree diagrams as preliminary explorative techniques for the assessment of the ergonomic, management and operational parameters which influence high accident risk situations. The Occupational Injury analysis carried out in this paper was planned as a dynamic process and can be repeated systematically. The CART technique, which considers a very wide set of objective and predictive variables, shows new cause-effect correlations in occupational safety which had never been previously described, highlighting possible injury risk groups and supporting decision-making in these areas. The use of classification trees must not, however, be seen as an attempt to supplant other techniques, but as a complementary method which can be integrated into traditional types of analysis.     

Analysis of injury severity of drivers involved in single- and two-vehicle crashes on highways in Ontario

This study analyzes driver's injury severity in single- and two-vehicle crashes and compares the effects of explanatory variables among various types of crashes. The study identified factors affecting injury severity and their effects on severity levels using 5-year crash records for provincial highways in Ontario, Canada. Considering heteroscedasticity in the effects of explanatory variables on injury severity, the heteroscedastic ordered logit (HOL) models were developed for single- and two-vehicle crashes separately. The results of the models show that there exists heteroscedasticity for young drivers (≤30), safety equipment and ejection in the single-vehicle crash model, and female drivers, safety equipment and head-on collision in the two-vehicle crash models. The results also show that young car drivers have opposite effects between single-car and car–car crashes, and sideswipe crashes have opposite effects between car–car and truck–truck crashes. The study demonstrates that separate HOL models for single-vehicle and different types of two-vehicle crashes can identify differential effects of factors on driver's injury severity.