Search

• Machine learning models for crash risk predictions are comprehensively reviewed. • Four staged review: the first three stages summarise existing efforts, and the last stage highlights future research needs. • Critical research needs for crash risk predictions using machine learning models are discussed. • Efficient techniques for data imbalance need to be employed. • Rigorous efforts for data collection and real-time models are required. 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. [ABSTRACT FROM AUTHOR]

• Crash investigation is vital for determining effective interventions to advance road safety. • Crash investigation may focus on prosecution, retribution, compensation, or prevention. • Road crash investigation must be prevention-focused to lead to safety reform. • The Five "I" Framework is a practical guide for jurisdictions conducting road crash investigations. • The Five "I" Framework is: Immediate, In-Depth, Impartial, Independent, Injury Prevention. Crash investigation is vital to the advancement of road safety, and it is a foundation for determining effective countermeasures and interventions for true road safety reform. However, the way in which road crash investigations are conducted substantially influences the quality of understanding and the effectiveness of responses. In crash investigations, we traditionally focus first on the question: "What caused this crash?" when it would be more efficient to ask immediately: "What could have prevented this crash?" or better yet, "What are all the ways this crash could have been prevented?" In this paper, we first explore a few common road crash investigation approaches where prosecution, retribution, or compensation are primary. We then examine investigation approaches where prevention is primary, especially investigations aimed at determining every point on the timeline preceding the crash where an intervention would have prevented the outcome, as illustrated by the Swiss Cheese Model. We draw from examples from the aviation industry, the occupational health and safety field, the U.S. National Transportation Safety Board (NTSB), and others, to identify strengths and weaknesses. We bring together good practices from several investigative approaches through the lens of diverse experiences in transportation safety and root-cause analysis to present a practical and proactive framework for road crash investigation. The Five "I" Framework provides guiding characteristics for prevention-focused safety investigations for road crashes: Immediate, In-Depth, Impartial, Independent, and Injury Prevention. The Five "I" Framework is a practical guide for investigations to move beyond crash causation to crash prevention, aligning with the Safe Systems Approach, Vision Zero, and the public health perspective. Rather than focusing primarily on on any single factor such as vehicle defect or driver error, it leads investigations to an array of countermeasures that involve collective action and systems change, and thus, to more effective road safety reform. Nevertheless, as a practical framework, it is the start (not the end) of discussions on how we can continue to move towards more multidisciplinary, collaborative, innovative, and ethical prevention efforts. [ABSTRACT FROM AUTHOR]

• A dynamic test scenario generation method for AVs is proposed in this paper. The proposed method has the ability to generate a realistic driving environment and apply to more complex scenarios like lane changing scenarios, which is of significant value for AV testing and evaluation.** • Instead of reconstructing expert behavior based on the assumption of single modality, this method combines Hierarchical Dirichlet Process Hidden Semi-Markov model (HDP-HSMM) and GAIL, obtains the main modes through clustering, and directs the scenario generation process by conditioning the model on scenario class labels, which improves the scenarios diversity and generation efficiency. • A typical lane-changing scenario is used for the evaluation of the proposed method. The results show that this method can generate rich test scenarios, and test AVs' ability to deal with different kinds of dynamic scenarios. Autonomous vehicles must be comprehensively evaluated before deployed in cities and highways. However, most existing evaluation approaches for autonomous vehicles are static and model environmental vehicles with predefined trajectories, which ignore the time-sequential interactions between the ego vehicle and environmental vehicles. In this paper, we propose a dynamic test scenario generation method to evaluate autonomous vehicles by modeling environmental vehicles as agents with human behavior and simulating the interaction process between the autonomous vehicle and environmental vehicles. Considering the multimodal features of traffic scenarios, we cluster the real-word traffic environments, and integrate the scenario class labels into the conditional generative adversarial imitation learning (CGAIL) model to generate different types of traffic scenarios. The proposed method is validated in a typical lane-change scenario that involves frequent interactions between ego vehicle and environmental vehicles. Results show that the proposed method further test autonomous vehicles' ability to cope with dynamic scenarios, and can be used to infer the weaknesses of the tested vehicles. [ABSTRACT FROM AUTHOR]

• Female driving offenders are more empathetic and impulsive than male offenders. • Male driving offenders are more self-compassionate and mindful than females. • Mindfulness predicts fewer risky driving behaviors and more prosocial ones. • Aggressive driving anger expression is a risk factor for both genders. • Impulsiveness predicts more distraction while driving only among females. Although driving risk taking appears to be mainly male, an increase in driving violations has been observed in recent years among French female drivers. The main objective of the present study was to explore the driving behaviors, psychological resources, and vulnerabilities of female and male driving offenders participating in a French driver rehabilitation program. The second aim was to examine to what extent females' and males' resources and vulnerabilities predicted their violations, engagement in distracting activities while driving, and prosocial driving behaviors. In the course of 110 rehabilitation programs, 1686 driving offenders (22.4% females) completed a paper-and-pencil questionnaire. Compared to male offenders, females were more likely to have received a higher education, be divorced, or separated, and drive fewer annual kilometers. They also had had fewer demerit points than males in the last three years. They were more empathetic but also more impulsive than their male counterparts and less self-compassionate and mindful. Regression and moderation analyses revealed that, across genders, certain psychological resources such as mindfulness can be considered as protective factors for driving offenders as they tend to decrease dangerous behaviors and increase prosocial ones, while vulnerabilities such as aggressive driving anger expression seem to have the opposite effect. Our results provide a better understanding of driving offenders' behavior and the influence of personal dispositions. They also open new interesting research avenues in the prevention of dangerous behaviors among this high-risk population. [ABSTRACT FROM AUTHOR]

• An improved safety potential field, named the Work-Zone Crash Risk Field (WCRF), is developed for real-time crash risk assessment in highway work zones. • The WCRF performs better than conventional safety surrogate measures in identifying high-risk vehicles in work zones. • The impact of setting up a work zone on the crash risk of each lane at transition areas is analyzed. • Several key traffic features that may contribute to crash risk in transition areas of the work zones are identified. • The heterogeneity in the impact of risk-contributing traffic features over different work zones is discussed. Due to complex traffic conditions, transition areas in highway work zones are associated with a higher crash risk than other highway areas. Understanding risk-contributing features in transition areas is essential for ensuring traffic safety on highways. However, conventional surrogate safety measures (SSMs) are quite limited in identifying the crash risk in transition areas due to the complex traffic environment. To this end, this study proposes an improved safety potential field, named the Work-Zone Crash Risk Field (WCRF). The WCRF force can be used to measure the crash risk of individual vehicles that enter a work zone considering the influence of multiple features, upon which the overall crash risk of the road segment in a specific time window can be estimated. With the overall crash risk used as a label, the time-window-based traffic data are used to train and validate an eXtreme Gradient Boosting (XGBoost) classifier, and the Shapley Additive Explanations (SHAP) method is integrated with the XGBoost classifier to identify the key risk-contributing traffic features. To assess the proposed approach, a case study is conducted using real-time vehicle trajectory data collected in two work zones along a highway in China. The results demonstrate that the WCRF-based SSM outperforms conventional SSMs in identifying crash risks in work zone transition areas on highways. In addition, we perform lane-based analysis regarding the impact of setting up work zones on highway safety and investigate the heterogeneity in risk-contributing features across different work zones. Several interesting findings from the analysis are reported in this paper. Compared to existing SSMs, the WCRF-based SSM offers a more practical and comprehensive way to describe the crash risk in work zones. The approach using the developed WCRF technique offers improved capabilities in identifying key risk-contributing features, which is expected to facilitate the development of safety management strategies for work zones. [ABSTRACT FROM AUTHOR]

• Introduces "Safe Space" concept: validates with real-world data for pedestrians and e-bicyclists in urban crosswalks. • Explores impact of the number and speed of individuals on the morphology of the safe space. • Proposes novel methods to identify crowd congestion levels and traffic conflicts using safe space. Despite numerous theoretical and empirical studies exploring the spatial needs of road users, a significant gap remains in validating these findings with extensive real-world data sets. This study presents the idea of "safe spaces," outlining the buffer zones that both walkers and e-bicyclists maintain when crossing streets, while also taking safety and psychological well-being into consideration. We used drones to gather the study's trajectory data at three significant crossings in Xi'an, China. Multi-coordinate system transformation enabled us to determine the relative positions of individuals and moving objects within their visual domain. Relative position frequency heat maps were generated to explore safe distance demands in different directions. The safety space was then fitted using the least squares method. Our research demonstrates that whereas e-bicyclists maintain semi-elliptical safe spaces at street crossings, walkers maintain semi-circular safe spaces, and the sizes of these zones increase in direct proportion to their relative speeds. However, the safe space size oscillates within a defined range above a particular speed threshold. Notably, e-bicyclists require larger safety distances forward and are more sensitive to speed variations. Our knowledge of the dynamics of safe spaces for walkers and e-bicyclists at street crossings is improved by this work, with emphasis on the role of speed and pedestrian numbers in shaping these spaces. The incorporation of real-world data from drone footage significantly strengthens the validity and reliability of our findings, bridging a crucial empirical gap in the existing literature. Additionally, this paper introduces a crowding coefficient based on safe space and proposes a new method using safe space to aid traffic conflict metrics PET, providing valuable insights for identifying crowd congestion levels and capturing traffic conflict events. The practical implications of our findings extend to urban planning, traffic management, and safety of vulnerable road users. Ultimately, this research contributes to the development of safer and more efficient urban environments for all road users. [ABSTRACT FROM AUTHOR]

• We apply Latent Dirichlet Allocation algorithm to discover activity patterns from floating vehicle trajectory data. • We incorporate activity patterns into traffic safety analysis to supplement traditional traffic exposure measures. • We use Graph Convolutional Network to explore multiple factors influencing spatial patterns of traffic crashes. • We estimate non-linear relationships between variables and traffic crashes using interpretive methodologies. In recent years, increased attention has been given to understanding the spatial pattern of crashes in urban areas. Accurately capturing the spatial relationship between crash counts and variables requires extracting hidden information from multiple data sources. In this study, we propose a machine learning model to explore the spatial impact of activity patterns on spatially aggregated crash counts. Our paper introduces a two-step framework: (a) the Latent Dirichlet Allocation (LDA) model, an unsupervised method for mining hidden activity patterns from floating vehicle trajectory data, and (b) the Graph Convolutional Network (GCN) model, which builds the spatial relationship between multi-source data. The data and hidden activity patterns were aggregated into 175 Traffic Analysis Zones (TAZs) in San Francisco using spatial partitioning. The GCN model provided higher prediction accuracy than commonly used machine learning algorithms that did not consider combined spatial relationships and those that only considered traditional vehicle counts data. Furthermore, we used attribution algorithms to obtain the respective weight scores of each factor. Our results reveal that daily vehicle kilometers traveled, road density, population density, commercial activity during weekends, and residential activity during morning peak hours on weekdays are factors associated with crashes. [ABSTRACT FROM AUTHOR]

Background: In accordance with the focus on patient safety and quality in healthcare, continuing professional development (CPD) has received increasing levels of attention as a means to ensure physicians maintain their clinical competencies and are fit to practice. There is some evidence of a beneficial effect of CPD, though few studies have evaluated its effect within anesthesia. The primary aim of this systematic review was to establish which CPD activities anesthetists are engaged in and their effectiveness. The secondary aim was to explore which methods are employed to evaluate anesthetists' clinical performance. Methods: Databases searched: Medline, Embase and Web of Science, in May 2023. Additional papers were identified through searching the references of included studies. Eligible studies included anesthetists, either exclusively or combined with other healthcare professionals, who underwent a learning activity or assessment method as part of a formalized CPD program or a stand‐alone activity. Non‐English language studies, non‐peer reviewed studies and studies published prior to 2000 were excluded. Eligible studies were quality assessed and narratively synthesized, with results presented as descriptive summaries. Results: A total of 2112 studies were identified, of which 63 were eligible for inclusion, encompassing more than 137,518 participants. Studies were primarily of quantitative design and medium quality. Forty‐one studies reported outcomes of single learning activities, whilst 12 studies investigated different roles of assessment methods in CPD and ten studies evaluated CPD programs or combined CPD activities. A 36 of the 41 studies reported positive effects of single learning activities. Investigations of assessment methods revealed evidence of inadequate performance amongst anesthetists and a mixed effect of feedback. Positive attitudes and high levels of engagement were identified for CPD programs, with some evidence of a positive impact on patient/organizational outcomes. Discussion: Anesthetists are engaged in a variety of CPD activities, with evidence of high levels of satisfaction and a positive learning effect. However, the impact on clinical practice and patient outcomes remains unclear and the role of assessment is less well‐defined. There is a need for further, high‐quality studies, evaluating a broader range of outcomes, in order to identify which methods are most effective to train and assess specialists in anesthesia. [ABSTRACT FROM AUTHOR]

This paper investigates the effects of model fidelity and parameter uncertainty on the performance of a hybrid model-based feedback-feedforward control scheme for attitude tracking of a satellite with flexible appendages. The feedforward component is an inverse model-based term produced through a computational approach known as inverse simulation (InvSim), which works by iteratively solving a discretised reference trajectory. The hybrid controller's feedback is proportional-derivative (PD) based, using body attitude and rate feedback to provide stability and robustness. Furthermore, to ensure that the flexible modes do not trigger instability, the PD control gains are tuned to give a closed-loop response that is significantly slower than the flexible modes. Additionally, excitation of the flexible modes is reduced by minimising jerk through polynomial rest-to-rest manoeuvres, following the shortest quaternion path using spherical–linear-interpolation (SLERP). The effects of the appendage flexing on attitude tracking are then compensated through the feedforward element of the hybrid controller, with performance being compared to a traditional PD tracking law. The effect of the model fidelity on the performance of the hybrid controller is investigated through the use of both rigid body and multiple-fidelity finite-element mathematical models. Additionally, the effect of uncertainties in the model parameters is investigated to determine the accuracy of the model required to obtain significant improvement in attitude tracking. It is found that in the absence of any model parameter uncertainty, the hybrid controller outperforms the PD tracking control law by at least one order of magnitude when the finite-element model is used. Increasing the number of finite elements was found to provide no significant improvement in performance, with one element being sufficient and favourable with its lower computational overhead. It was also found that to ensure good performance compared to the PD tracking controller, the uncertainty in the inertia tensor should be < 1%. Similarly, uncertainty in the first flexible modal frequency should be < 0.5 rad/s. • Inverse simulation (InvSim) used to produce model-based feedforward control. • Combined with PD feedback to improve attitude tracking. • Effects of model uncertainty and fidelity on model-based control investigated. [ABSTRACT FROM AUTHOR]