Crash Mechanisms Research Articles

A read-efficient and write-optimized hash table for Intel Optane DC Persistent Memory

Emerging non-volatile memory technologies are driving the next generation of storage systems and durable data structures. Among them, many hash table proposals employ NVM as the storage layer for both fast access and efficient persistence. Most of them are based on the assumption that NVM has cacheline access granularity, poor write endurance, DRAM-comparable read latency and relatively higher write latency. However, a commercial non-volatile memory product, namely Intel Optane DC Persistent Memory (Optane), has some interesting features that are different from previous assumptions, such as 256-byte OptaneLine access granularity, higher read latency than DRAM and DRAM-comparable write latency, limited read/write bandwidth, and hardware-layer wear-leveling. Confronted with the new challenges brought by Optane, we propose Rewo-Hash, a novel read-efficient and write-optimized persistent hash table. Our incremental contributions over our previous work are summarized as follows. First, provide a more detailed technical description for cached table-inclined read mechanism and log-free atomic write mechanism. Second, we devise a consistent shadowing synchronization scheme to mask the data synchronization overhead. Third, we propose a non-blocking lightweight resizing scheme and elaborate the crash recovery mechanism. Fourth, we conduct a comprehensive analysis of the implications of Intel ceasing the production of Optane, and provide a forward-looking perspective on the future of non-volatile memory. The experimental results show that compared with state-of-the-art NVM-Optimized hash tables, Rewo-Hash gains remarkable performance improvement.

Effects of speed difference on injury severity of freeway rear-end crashes: Insights from correlated joint random parameters bivariate probit models and temporal instability

Rear-end crashes particularly on freeways are the most frequent type of collisions causing many injuries, damage and congestion. This paper investigates the impact of varying speed differences between following and leading vehicles on injury severity in two-vehicle rear-end crashes. It develops three groups of correlated joint random parameters bivariate probit models with heterogeneity in means. The rear-end crash data from 2019 to 2021 on Interstate freeways in Florida are utilized, and categorized into periods before, during, and after the COVID-19 pandemic. The study considers two potential injury severity outcomes: no injury and injury/fatality, for both drivers involved in these crashes. The findings indicate that a range of variables, including driver, vehicle, roadway, environmental, crash, and temporal attributes, significantly influence the injury severity outcomes for drivers in both following and leading vehicles. Demonstrating superior goodness-of-fit, the proposed approach sheds light on interactive unobserved heterogeneity, captured through heterogeneity in means and significant correlations among random parameters. The study observes critical influences on the injury severity outcomes of both drivers, with significant factors such as gender, age, vehicle type, weather conditions, lighting, and time of day. Furthermore, the results substantiate the heightened risk outcomes associated with greater speed differences and the period of the COVID-19 pandemic. These findings yield further insights into the risk mechanisms of two-vehicle rear-end crashes and offer guidance for the development of effective safety countermeasures.

Advances, challenges, and future research needs in machine learning-based crash prediction models: A systematic review

Accurately modelling crashes, and predicting crash occurrence and associated severities are a prerequisite for devising countermeasures and developing effective road safety management strategies. To this end, crash prediction modelling using machine learning has evolved over two decades. With the advent of big data that provides unprecedented opportunities to better understand the crash mechanism and its determinants, such efforts will likely be accelerated. To gear these efforts, understanding state-of-the-art machine learning-based crash prediction models becomes paramount to summarise the lessons learned from past efforts, which can assist in developing robust and accurate models. This review paper aims to address this gap by systematically reviewing the machine learning studies on crash modelling. Models are reviewed from three aspects of the application: (a) crash occurrence (or real-time crash) prediction, (b) crash frequency prediction, and (c) injury severity prediction. Further, model intricacies that impact model performance are identified and thoroughly reviewed. This comprehensive review highlights specific gaps and future research needs in three aforementioned model applications, such as improper selection of non-crash events for crash occurrence models, the inability of future forecasting of crash frequency models, and inconsistency in injury severity classes. Critical research needs relating to model development, evaluation, and application are also discussed. This review envisages methodological advancements in machine learning models for crash prediction modelling and leveraging big data to better link crashes with its determinants.

Boosting Ensemble Learning for Freeway Crash Classification under Varying Traffic Conditions: A Hyperparameter Optimization Approach

Freeway crashes represent a significant and persistent threat to road safety, resulting in both loss of life and extensive property damage. Effectively addressing this critical issue requires a comprehensive understanding of the factors contributing to these incidents and the ability to accurately predict crash severity under different traffic conditions. This study aims to improve the accuracy of crash classification by incorporating key traffic-related variables such as braking, weather conditions, and speed. To validate the effectiveness of proposed model, we utilize real-world crash data from Flint, Michigan. To achieve the objective, we employ an innovative Boosting Ensemble Learning approach, leveraging five advanced ensemble learning models: Gradient Boosting, Cat Boost, XGBoost, LightGBM, and SGD. Through the application of hyperparameter optimization techniques, we further enhance the performance of these models, improving their predictive capabilities. Our evaluation results demonstrated the effectiveness of our approach, with Gradient Boosting algorithms achieving an accuracy rate of up to 96% in crash classification. This research provides valuable insights into the potential of using Boosting Ensemble Learning as a tool for accurately and efficiently classifying freeway crashes across a spectrum of traffic conditions. Additionally, it sheds light on the nuanced variations in crash mechanisms observed when employing diverse ensemble learning models. The findings of this study underscore the significance of hyperparameter optimization as a critical factor in elevating the predictive precision of freeway crashes.

Real use of vehicle dynamic capacities: Motorcyclists versus motorists

The risk of serious crashes is much higher for motorcyclists than for motorists. While research into PTW safety is not as extensive as for other road users, there is a need for further understanding of fatal and injury crash patterns and causes, particularly in the critical pre-crash phase. Naturalistic Driving Studies (NDS) have been used to improve road safety and gain a better understanding of car crash mechanisms, but few studies have used this approach to examine PTW behavior. This paper aims to compare the actual use of PTW's dynamic capacities to that of passenger cars based on three Naturalistic Driving Studies conducted in France. A method designed to study the dynamic behavior of cars has been adapted to study the dynamic behavior of PTWs. This adaptation involves combining the longitudinal acceleration, not only with the lateral acceleration (which is adapted for cars), but also with the roll rate or the yaw rate. By doing so, it becomes possible to consider the specific behavior of PTWs in curves, and finally, to compare the dynamic demands experienced by cars and PTWs in all directions. It was found that there are significant differences in the distribution of accelerations, roll rate, yaw rate, and speeds between motorcycles and cars. Motorcycles were observed to endure higher levels of positive acceleration, experience more intense braking, and exhibit slightly higher levels of medium or high yaw rate values. The final analysis of speeds, with a 5 km/h interval, shows that motorcyclists travel at higher speeds than car drivers within a small fleet of equipped cars. However, when compared to a larger fleet of cars with speed data with a 10 km/h interval, car drivers were found to travel faster. Demand levels differ between fleets of cars and fleets of motorists, particularly where lateral demands are concerned. This can be attributed to various factors such as driving context, study duration, road type and weather conditions. Other NDS with more cars and PTWs should be analyzed with this method to complete the results.

Spatio-temporal dynamic change mechanism analysis of traffic conflict risk based on trajectory data

Analyzing risk dynamic change mechanism under spatio-temporal effects can provide a better understanding of traffic risk, which helps reinforce the safety improvement. Traditionally, spatio-temporal studies based on crash data were mostly conducted to explore crash risk evolution mechanism from a macroscopic perspective. Dynamic change mechanism of short-term risk within a small-scale area deserves exploration, which cannot be captured in macroscopic crash-based studies. It is practical to analyze traffic conflict risk as a surrogate safety measure, which can preferably overcome the limitations of crash-based studies. This study aims to explore the spatio-temporal dynamic change mechanism of conflict risk based on trajectory data. Both conflict frequency and severity are integrated and assessed by applying fuzzy logic theory to develop the whole risk indicator. Trajectories on U.S. Highway101 from NGSIM dataset are utilized and aggregated. A two-step framework is proposed to analyze the risk dynamic change mechanism. The spatial Markov model is firstly applied to explore the transition probability of risk level, and then the panel regression approach is employed to quantify the relationship between spatio-temporal risk and traffic characteristics. Modeling results show that (1) the dynamic change trend of safety states differs under different spatial lag conditions, and it can be well depicted by the spatial Markov model; (2) dynamic spatial panel data modeling method performs better than the model that only considers temporal or spatial dependency. The novel proposed framework promotes a systematic exploration of conflict risk from a mesoscopic perspective, which contributes to assess the real-time road safety more comprehensively.

Modeling of Freeway Real-Time Traffic Crash Risk Based on Dynamic Traffic Flow Considering Temporal Effect Difference

With the development of traffic detection facilities technology, it is currently possible to obtain high-resolution traffic flow data. Due to the particular driving characteristics of vehicles on freeways, once traffic crashes occur, they are generally with serious consequences, and hence traffic safety issues on freeways have always been popular topics. In order to better realize the change from static analysis after the crash to dynamic analysis before the crash toward freeway safety, as well as explore the relationship between dynamic traffic flow characteristics and real-time traffic crash risk under different temporal conditions, this research constructed a real-time traffic crash risk prediction model considering the temporal effect difference. First, traffic crash information and the matched big data of high-resolution traffic flow located on the section of milepost 100–130 of Interstate 5 (I-5) in Washington State, were extracted. In terms of temporal dimension, the research object was divided into weekdays and weekends, and the traffic state was divided into unsaturated and saturated. The random forest (RF) algorithm was introduced to identify the traffic flow variables of crash precursors, and support vector machine (SVM) was applied to build the traffic crash risk prediction model under the condition of temporal difference. A confusion matrix, receiver operating characteristic (ROC) curve, and area under curve (AUC) values were used to evaluate the accuracy of the model performance. Furthermore, the prediction performance of the proposed model was tested via constructing the risk model without consideration of temporal effect and traffic state difference. Finally, the rationality of variable screening was verified by inputting the data set without variable screening into the constructed model. The results showed that the occurrence mechanism of dynamic traffic crashes under different temporal effect conditions varies; the AUC values of the constructed prediction model were all between 0.7 and 0.9, indicating that the recommended model has good prediction accuracy. In conclusion, the real-time freeway traffic crash risk prediction model considering the temporal effect difference has certain advantages compared with the conventional model, and its performance is better than the prediction model without screening of important traffic flow variables. This approach can provide theoretical guidance for dynamic traffic safety management toward freeway under temporal difference conditions.

Temporal instability and differences in injury severity between restrained and unrestrained drivers in speeding-related crashes

Upon detecting a crash impact, the vehicle restraint system locks the driver in place. However, external factors such as speeding, crash mechanisms, roadway attributes, vehicle type, and the surrounding environment typically contribute to the driver being jostled within the vehicle. As a result, it is crucial to model unrestrained and restrained drivers separately to reveal the true impact of the restraint system and other factors on driver injury severities. This paper aims to explore the differences in factors affecting injury severity for seatbelt-restrained and unrestrained drivers involved in speeding-related crashes while accounting for temporal instability in the investigation. Utilizing crash data from Thailand between 2012 and 2017, mixed logit models with heterogeneity in means and variances were employed to account for multi-layered unobserved heterogeneity. For restrained drivers, the risk of fatal or severe crashes was positively associated with factors such as male drivers, alcohol influence, flush/barrier median roadways, sloped roadways, vans, running off the roadway without roadside guardrails, and nighttime on unlit or lit roads. For unrestrained drivers, the likelihood of fatal or severe injuries increased in crashes involving older drivers, alcohol influence, raised or depressed median roadways, four-lane roadways, passenger cars, running off the roadway without roadside guardrails, and crashes occurring in rainy conditions. The out-of-sample prediction simulation results are particularly significant, as they show the maximum safety benefits achievable solely by using a vehicle's seatbelt system. Likelihood ratio test and predictive comparison findings highlight the considerable combined impact of temporal instability and the non-transferability of restrained and unrestrained driver injury severities across the periods studied. This finding also demonstrates a potential reduction in severe and fatal injury rates by simply replicating restrained driver conditions. The findings should be of value to policymakers, decision-makers, and highway engineers when developing potential countermeasures to improve driver safety and reduce the frequency of severe and fatal speeding-related single-vehicle crashes.

Application of Realistic Artificial Data for Testing Various Crash Safety Analyses: A Case Study for Rural Two-Lane Undivided Highways

Traffic safety research will continue to create new and improved methods for the analysis of safety data. Even if these models perform well, the precise underlying crash mechanism remains unknown. The missing piece is a tool that may be used to evaluate how well a method identifies the cause-and-effect relationship in the data. To meet these safety analysis needs, a high-resolution disaggregate data generating process called realistic artificial data (RAD) was developed. This tool simulates crash incidence on transportation facilities, capturing real-world causal links between individual roadway characteristics and crashes. The objective of this study was to check if the stochasticity embedded in the RAD generation process will be consistent for different random seeds and miles of data generated from the tool. To accomplish this, 10 different datasets were generated from the RAD tool and estimated using the negative binomial model; parameter estimates from the model were checked using a revised Wald statistic. The t-statistic estimates showed that the differences among the parameter values across the dataset are within a statistically acceptable level. Given the stability of the tool, the RAD framework can be useful in addressing the known limitations and knowledge gap in assessing the extent to which a statistical method succeeds in identifying the cause-and-effect relationship in the data. This in return can help guide and improve the practical application of statistical methods and eventually lead to more effective safety countermeasures that can reduce highway-related injuries and fatalities.

Investigating speed-safety association: Considering the unobserved heterogeneity and human factors mediation effects.

The relationship between mean speed and crash likelihood is unclear in the literature. The contradictory findings can be attributed to the masking effects of the confounding variables in this association. Moreover, the unobserved heterogeneity has almost been criticized as a reason behind the current inconclusive results. This research provides an effort to develop a model that analyzes the mean speed-crash frequency relationship by crash severity and type. Also, the confounding and mediation effects of the environment, driver, and traffic-related attributes have been considered. To this end, the loop detector and crash data were aggregated daily for rural multilane highways of Tehran province, Iran, covering two years, 2020-2021. The partial least squares path modeling (PLS-PM) was employed for crash causal analysis along with the finite mixture partial least squares (FIMIX-PLS) segmentation to account for potential unobserved heterogeneity between observations. The mean speed was negatively and positively associated with the frequency of property damage-only (PDO) and severe accidents, respectively. Moreover, driver-related variables, including tailgating, distracted driving, and speeding, played key mediation roles in associating traffic and environmental factors with the crash risk. The higher the mean speed and the lower the traffic volume, the higher odds of distracted driving. Distracted driving was, in turn, associated with the higher vulnerable road users (VRU) accidents and single-vehicle accidents, triggering a higher frequency of severe accidents. Moreover, lower mean speed and higher traffic volume were positively correlated with the percentage of tailgating violations, which, in turn, predicted multi-vehicle accidents as the main predictor of PDO crash frequency. In conclusion, the mean speed effects on the crash risk are entirely different for each crash type through distinct crash mechanisms. Hence, the distinct distribution of crash types in different datasets might have led to current inconsistent results in the literature.

Crash classification based on manner of collision: a comparative analysis

ABSTRACT Traffic crashes vary in the manner in which the collision occurs (collision type), and countermeasures to reduce crashes might vary significantly based on this collision type. The inherent complexity in their mechanism has motivated this study to identify significant factors influencing collision types, with the goal of better countermeasure deployment. The objective of this work is to compare the performances of statistical and machine learning (ML) models in classifying crashes based on collision type, and assess their generalizability and interpretability. Discrete choice models, Bayesian classifiers, tree-based algorithms, and support vector machines are among the data-driven methods considered for comparison. Results indicate that tree-based algorithms perform consistently well and offer a higher interpretability, with out-of-distribution robustness. However, while ML models provide a flexible framework for modeling large data volumes, statistical models provide additional interpretability on the effect of critical variables on crash mechanisms – which is relevant from a safety management standpoint.

Modelling injury severity in single-vehicle crashes using full Bayesian random parameters multinomial approach

Single-vehicle (SV) crash severity model considering spatiotemporal correlations has been extensively investigated, but spatiotemporal interactions have not received sufficient attention. This research is dedicated to propose a superior spatiotemporal interaction correlated random parameters logit approach with heterogeneity in means and variances (STICRP-logit-HMV) for systematically characterizing unobserved heterogeneity, spatiotemporal correlations, and spatiotemporal interactions. Four flexible interaction formulations are developed to uncover the spatiotemporal interactions, including linear structure, Kronecker product, mixture-2 model, and mixture-5 model. Four candidate approaches-random parameters logit (RP-logit), RP-logit with heterogeneity in means and variances (RP-logit-HMV), correlated RP-logit-HMV (CRP-logit-HMV), and spatiotemporal CRP-logit-HMV (STCRP-logit-HMV)-are also established and compared with the proposed model. SV crash observations in Shandong Province, China, are employed to calibrate regression parameters. The model comparison results show that (1) the performance of the RP-logit-HMV model outperforms the RP-logit model, implying that capturing heterogeneity in the means and variances can strengthen model fit; (2) the CRP-logit-HMV model and the RP-logit-HMV model are comparable; (3) the STCRP-logit-HMV model outperforms the CRP-logit-HMV model, implying that addressing the spatiotemporal crash mechanisms is beneficial to the overall fitting of the crash model; (4) the STICRP-logit-HMV model performs better than the STCRP-logit-HMV model and this finding remains stable across different interaction formulations, indicating that comprehensively reflecting the spatiotemporal correlations and their interactions is a promising approach to model SV crashes. Among the four interaction models, the STICRP-logit-HMV model with mixture-5 component maintains the best fit, which is a recommended approach to model crash severity. The regression coefficients for young driver, male driver, and non-dry road surface are random across observations, suggesting that the influence of these factors on SV crash severity maintains significant heterogeneity effects. The research results provide transportation professionals with a superior statistical framework for diagnosing crash severity, which is beneficial for improving traffic safety.

Learning about injury severity from no-injury crashes: A random parameters with heterogeneity in means and variances approach

The traditional approach to injury-severity analyses does not allow in-depth understanding of no-injury crashes, as crash factors found to contribute to the various injury severities may have similar effects on the severity of vehicle damage even if no injury is recorded. Viewing no-injury crashes using the vehicle damage severities as sub-categories and bases for potential injuries can improve understanding of future injury crashes. To better understand the mechanism of no-injury crashes and the crash factors that contribute to the extent of vehicle damage beyond the single categorization of these crashes in injury severity analysis, this study presents a vehicle damage severity analysis for no-injury crashes. To compare the effects of crash contributing factors on crash outcomes, two injury severity models were also estimated. Random parameters multinomial logit models with heterogeneity in means and variances were developed to account for unobserved heterogeneity. Model estimation results revealed that several common factors (e.g., unsafe speed, distracted driving, driving under influence, vehicle age, and run-off-road) are correlated with both injury severity in injury crashes and vehicle damage severity in no-injury crashes. Therefore, the sub-categorization of no-injury crashes by vehicle damage severity can potentially improve estimates of injury severity considered in resource allocation decisions for traffic safety.

Mixed logit model based diagnostic analysis of bicycle-vehicle crashes at daytime and nighttime

Cycling provides an important alternative to environmental-friendly transportation modes in urban areas. However, cyclists are vulnerable road users and often suffer severe injuries once crashes occur, which has impeded the growth of bicycle uses. Identification of factors that influence injury severities of crashes involving cyclists can help policy-makers form efficient strategies to mitigate crashes. Moreover, crashes involving cyclists at daytime and nighttime are very likely to present different patterns. Hence, the objective of this study is to explore the underlying factors to injury severity in crashes involving cyclists in the daytime and nighttime separately. Mixed logit model approach is employed due to its advantage of accounting for heterogeneity in observations and four factors are found to have random effects in the mixed logit model for daytime. The differences of crash mechanisms at daytime and nighttime are discussed, and the results of this research would help to develop effective policies that aim to mitigate the injury severities of cyclists while promoting the use of bicycles.

Multivariate analysis of roadway multi-fatality crashes using association rules mining and rules graph structures: A case study in China.

Roadway multi-fatality crashes have always been a vital issue for traffic safety. This study aims to explore the contributory factors and interdependent characteristics of multi-fatality crashes using a novel framework combining association rules mining and rules graph structures. A case study is conducted using data from 1068 severe fatal crashes in China from 2015 to 2020, and 1452 interesting rules are generated using an association rule mining approach. Several modular rules graph structures are constructed based on graph theory to reflect the interactions and patterns between different variables. The results indicate that multi-fatality crashes are highly associated with improper operations, passenger overload, fewer lanes, mountainous terrain, and run-off-the-road crashes, representing the key variables of factors concerning driver, vehicle, road, environment, and accident, respectively. Furthermore, crashes involving different severity levels, road categories, and terrain are verified to possess unique association rules and independent crash patterns. Moreover, the proportion of severe crashes caused by a combination of human-vehicle-road-environment factors (43%) is much higher than that of normal crashes (3%). This study reveals that the hidden associations between various factors contribute to the overrepresentation and severity of multi-fatality crashes. It also demonstrates that the crash mechanisms involving multi-fatality crashes and their interactions are more complex at the system level than those for normal crashes. The proposed framework can effectively map the intrinsic link between multiple crash factors and potential risks, providing transportation agencies with helpful insights for targeted safety measures and preventive strategies.

Pediatric spinal injury patterns and management in all-terrain vehicle and dirt bike crashes, 2010-2019.

Pediatric spinal injuries in all-terrain vehicle (ATV) and dirt bike crashes are relatively uncommon but may be associated with significant morbidity. There are no recent studies examining these injuries, their management, and outcomes. Therefore, a retrospective study was performed to characterize pediatric spinal injuries related to ATV and dirt bike crashes over the last decade. Data on all patients involved in ATV or dirt bike crashes evaluated at a regional level 1 pediatric trauma center over a 10-year period (2010-2019) were analyzed. Descriptive statistics were analyzed and chi-square, Fisher exact, and Mann-Whitney U-tests were performed comparing the demographics, injury characteristics, and clinical outcomes in patients with versus those without spinal injuries. Of 680 patients evaluated, 35 (5.1%) were diagnosed with spinal injuries. Over the study period, both spinal injuries and emergency department visits related to ATV or dirt bike crashes increased in frequency. All spinal injuries were initially diagnosed on CT scans, and 57.9% underwent spinal MRI. Injuries were most commonly thoracic (50%), followed by cervical (36.8%). The injuries of most patients were classified as American Spinal Injury Association (ASIA) grade E on presentation (86.8%), while 2 (5.3%) had complete spinal cord injuries (ASIA grade A) and 3 patients (8.6%) were ASIA grade B-D. Operative management was required for 13 patients (28.9%). Nonoperative management was used in 71.1% of injuries, including bracing in 33% of all injuries. Patients with spinal injuries were older than those without (13.4 ± 3.35 vs 11.5 ± 3.79 years, p = 0.003). Spinal injuries occurred via similar crash mechanisms (p = 0.48) and in similar locations (p = 0.29) to nonspinal injuries. Patients with spinal injuries more frequently required admission to the intensive care unit (ICU; 34.2% vs 14.6%, p = 0.011) and had longer hospital stays (mean 4.7 ± 5.5 vs 2.7 ± 4.0 days, p = 0.0025). Although infrequent among young ATV and dirt bike riders, spinal injuries are associated with longer hospital stays, increased ICU use, and required operative intervention in 29%. Increasing awareness among ATV and dirt bike riders about the severity of riding-related injuries may encourage safer riding behaviors.

American Academy of Pediatrics Recommendations for the Prevention of Pediatric ATV-Related Deaths and Injuries.

Since all-terrain vehicles (ATVs) were introduced in the mid-1970s, regulatory agencies, injury prevention researchers, and pediatricians have documented their dangers to youth. Major risk factors, crash mechanisms, and injury patterns for children and adolescents have been well characterized. Despite this knowledge, preventing pediatric ATV-related deaths and injuries has proven difficult and has had limited success. This policy statement broadly summarizes key background information and provides detailed recommendations based on best practices. These recommendations are designed to provide all stakeholders with strategies that can be used to reduce the number of pediatric deaths and injuries resulting from youth riding on ATVs.

A Comprehensive Report on All-Terrain Vehicles and Youth: Continuing Challenges for Injury Prevention.

All-terrain vehicles (ATVs) represent a serious and ongoing public health and safety concern for children and adolescents. Survey studies indicate that high proportions of youth ride ATVs in both rural and nonrural populations. The significant human and economic costs of pediatric ATV-related deaths and injuries result from a number of major risk factors that are highly common in pediatric ATV crashes: operating adult-size vehicles, riding with or as passengers, lack of protective equipment, and riding on public roads. Other less well-studied but potentially significant risk factors are speed, riding at night, alcohol use among older teenagers, and lack of training and supervision. Although potentially safer than adult ATVs, youth models present a number of safety concerns that have not been addressed with rigorous study. The most common ATV crash mechanism is a noncollision event-for example, a rollover. Common injury mechanisms include ejection from the vehicle, resulting in extremity and head injuries, and being pinned or crushed by the vehicle with resulting multiorgan trauma and/or compression asphyxia. Traumatic brain injury and multisystem trauma are the 2 most common causes of death and disabling injury. Taken together, a large multidecade body of evidence is the basis for the American Academy of Pediatrics policy statement recommendation that no child younger than 16 years of age ride on an ATV. Because children continue to be allowed to ride these vehicles, however, efforts to prevent pediatric ATV-related deaths and injuries require multipronged strategies, including education of both youth and parents, safety-based engineering, and enforcement of evidence-based safety laws.

Expressway rear-end crash risk evolution mechanism analysis under different traffic states

The proportion of rear-end crashes is the highest for expressways. An effective ways to reduce the rear-end crash risk is Active Traffic Management (ATM), and knowing the mechanism of how contributing factors affect crash risk in space and time is the foundation of ATM. However, the existing studies are mainly based on highly aggregated traffic data. It is hard to capture the evolution mechanisms of crash risk. Meanwhile, crash risk mechanisms might be heterogeneous in smooth and congestion states. This study explored the crash mechanisms in different traffic states with high-resolution trajectory data. First, an ordered clustering method is used to divide a four km expressway section into several segments as the spatial unit. Second, the spatial–temporal ranges are decided by the spatial–temporal correlations analyses between crash risk and potential contributing factors. Thirdly, three types of time-series models are established to quantitatively obtain the impacts of contributing factors on the crash risks. The results showed that crash risk is mainly decided by the upstream contributing factors under smooth states, and determined by the downstream factors under congestion conditions.

A Parallel FP-Growth Mining Algorithm with Load Balancing Constraints for Traffic Crash Data

Traffic safety is an important part of the roadway in sustainable development. Freeway traffic crashes typically cause serious casualties and property losses, being a serious threat to public safety. Figuring out the potential correlation between various risk factors and revealing their coupling mechanisms are of effective ways to explore and identity freeway crash causes. However, the existing association rule mining algorithms still have some limitations in both efficiency and accuracy. Based on this consideration, using the freeway traffic crash data obtained from WDOT (Washington Department of Transportation), this research constructed a multi-dimensional multilevel system for traffic crash analysis. Considering the load balancing, the FP-Growth (Frequent Pattern- Growth) algorithm was optimized parallelly based on Hadoop platform, to achieve an efficient and accurate association rule mining calculation for massive amounts of traffic crash data; then, according to the results of the coupling mechanism among the crash precursors, the causes of freeway traffic crashes were identified and revealed. The results show that the parallel FPgrowth algorithm with load balancing constraints has a better operating speed than both the conventional FP-growth algorithm and parallel FP-growth algorithm towards processing big data. This improved algorithm makes full use of Hadoop cluster resources and is more suitable for large traffic crash data sets mining while retaining the original advantages of conventional association rule mining algorithm. In addition, the mining association rules model with the improvement of multi-dimensional interaction proposed in this research can catch the occurrence mechanism of freeway traffic crash with serious consequences (lower support degree probably) accurately and efficiently.