Objective: The main objective of this study is to identify the main factors associated with injury severity of vulnerable road users (VRUs) involved in accidents at highway railroad grade crossings (HRGCs) using data mining techniques.
Methods: This article applies an ordered probit model, association rules, and classification and regression tree (CART) algorithms to the U.S. Federal Railroad Administration's (FRA) HRGC accident database for the period 2007–2013 to identify VRU injury severity factors at HRGCs.
Results: The results show that train speed is a key factor influencing injury severity. Further analysis illustrated that the presence of illumination does not reduce the severity of accidents for high-speed trains. In addition, there is a greater propensity toward fatal accidents for elderly road users compared to younger individuals. Interestingly, at night, injury accidents involving female road users are more severe compared to those involving males.
Conclusions: The ordered probit model was the primary technique, and CART and association rules act as the supporter and identifier of interactions between variables. All 3 algorithms' results consistently show that the most influential accident factors are train speed, VRU age, and gender. The findings of this research could be applied for identifying high-risk hotspots and developing cost-effective countermeasures targeting VRUs at HRGCs. 相似文献
This study presents multiple approaches to the analysis of crash injury severity at three- and four-legged unsignalized intersections in the state of Florida from 2003 until 2006. An extensive data collection process was conducted for this study.
Method
The dataset used in the analysis included 2,043 unsignalized intersections in six counties in the state of Florida. For the scope of this study, there were three approaches explored. The first approach dealt with the five injury levels, and an ordered probit model was fitted. The second approach was an aggregated one, and dealt with only the severe versus non-severe crash levels, and a binary probit model was used. The third approach dealt with fitting a nested logit model. Results from the three fitted approaches were shown and discussed, and a comparison between the three approaches was shown.
Results
Several important factors affecting crash severity at unsignalized intersections were identified. These include the traffic volume on the major approach, and the number of through lanes on the minor approach (surrogate measure for traffic volume), and among the geometric factors, the upstream and downstream distance to the nearest signalized intersection, left and right shoulder width, number of left turn movements on the minor approach, and number of right and left turn lanes on the major approach. As for driver factors, young and very young at-fault drivers were associated with the least fatal probability compared to other age groups.
Impact on industry
The analysis identified some countermeasures to reduce injury severity at unsignalized intersections. The spatial covariates showed the importance of including safety awareness campaigns for speeding enforcement. Also, having a 90-degree intersection design is the most appropriate safety design for reducing severity. Moreover, the assurance of marking stop lines at unsignalized intersections is very essential. 相似文献
Climate change is expected to increase the frequency and severity of drought and wildfire. Aquatic and moisture‐sensitive species, such as amphibians, may be particularly vulnerable to these modified disturbance regimes because large wildfires often occur during extended droughts and thus may compound environmental threats. However, understanding of the effects of wildfires on amphibians in forests with long fire‐return intervals is limited. Numerous stand‐replacing wildfires have occurred since 1988 in Glacier National Park (Montana, U.S.A.), where we have conducted long‐term monitoring of amphibians. We measured responses of 3 amphibian species to fires of different sizes, severity, and age in a small geographic area with uniform management. We used data from wetlands associated with 6 wildfires that burned between 1988 and 2003 to evaluate whether burn extent and severity and interactions between wildfire and wetland isolation affected the distribution of breeding populations. We measured responses with models that accounted for imperfect detection to estimate occupancy during prefire (0–4 years) and different postfire recovery periods. For the long‐toed salamander (Ambystoma macrodactylum) and Columbia spotted frog (Rana luteiventris), occupancy was not affected for 6 years after wildfire. But 7–21 years after wildfire, occupancy for both species decreased ≥25% in areas where >50% of the forest within 500 m of wetlands burned. In contrast, occupancy of the boreal toad (Anaxyrus boreas) tripled in the 3 years after low‐elevation forests burned. This increase in occupancy was followed by a gradual decline. Our results show that accounting for magnitude of change and time lags is critical to understanding population dynamics of amphibians after large disturbances. Our results also inform understanding of the potential threat of increases in wildfire frequency or severity to amphibians in the region. Incrementos Rápidos y Declinaciones Desfasadas en la Ocupación de Anfibios Después de un Incendio 相似文献
The relationship between a large number of mine and mine worker characteristics and injury severity was examined using multiple regression techniques. The study was based on data extracted from the New South Wales (N.S.W.) Joint Coal Board's computer based accident/incident reporting system describing 21,372 non-fatal, lost-time injurious incidents that occurred in the N.S.W. underground coal mining industry during the 4 year period from 1 July 1986 to 30 June 1990. The number of days lost as a result of an injurious incident was the best available proxy measure of injury severity. Over the study period, the number of days lost per 100,000 tonnes of raw coal production declined by 73%. Over the same period, injurious incidents involving more than 20 days off work, which constituted only 16% of all injurious incidents in underground mines, resulted in 75% of the total days lost for the whole N.S.W. underground coal mining industry. Factors that had practical importance and that were significantly associated with injury severity included mine worker's age, part of the body injured, type of accident, agency of accident, and mine worker activity. Factors not important or not significant in their relationship with injury severity were: time into shift, previous hours worked, mine location of incident, occupation, work experience, frequency of task, shift, and mining region. This study suggests that factors related to the susceptibility of a mine worker's body tissue to damage or repair, and factors related to the concentration of energy on the mine worker by vehicle and environmental characteristics are important determinants of injury severity. 相似文献
Road accident severity may be influenced by a number of factors. This article investigates the relationship between weather and road accidents in England and Wales. The weather information recorded on Police Accident Report Forms was taken as the prevailing weather at the time of the accident. At the local authority level, accident severity for the various adverse weather categories of rain, fog, and high winds is compared with the nonhazardous condition of fine weather. Severity ratios are then calculated. Findings establish that accident severity decreases significantly in rain compared with fine weather, while severity in fog shows geographical variation. Evidence for accident severity in high winds remains inconclusive. 相似文献
PROBLEM: This study evaluated injured construction workers' perceptions of workplace safety climate, psychological job demands, decision latitude, and coworker support, and the relationship of these variables to the injury severity sustained by the workers. METHODS: Injury severity was assessed using the Health Assessment Questionnaire (HAQ), which evaluates functional limitations. Worker perceptions of workplace variables were determined by two instruments: (a) the Safety Climate Measure for Construction Sites and (b) the Job Content Questionnaire (JCQ). RESULTS: The overall model explained 23% of the variance in injury severity, with unique contributions provided by union status, the Safety Climate Score, and Psychological Job Demands. A positive significant correlation was found between injury severity and the Safety Climate Scores (r = .183, P = .003), and between the Safety Climate Scores and union status (r = .225, P < .001). DISCUSSION: There were statistically significant differences between union and nonunion workers' responses regarding perceived safety climate on 5 of the 10 safety climate items. Union workers were more likely than nonunion workers to: (a) perceive their supervisors as caring about their safety; (b) be made aware of dangerous work practices; (c) have received safety instructions when hired; (d) have regular job safety meetings; and (e) perceive that taking risks was not a part of their job. However, with regard to the 49-item JCQ, which includes Coworker Support, the responses between union and nonunion workers were very similar, indicating an overall high degree of job satisfaction. However, workers who experienced their workplace as more safe also perceived the level of management (r = -.55, P < .001) and coworker (r = -.31, P < .001) support as being higher. IMPACT ON INDUSTRY: The findings of this study underscore the critical need for construction managers to alert workers to dangerous work practices and conditions more frequently, and express concern and praise workers for safe work in a manner that is culturally acceptable in this industry. Workplace interventions that decrease the incidence and severity of injuries, but that are flexible enough to meet a variety of potentially competing imperatives, such as production deadlines and client demands, need to be identified. 相似文献