Accident; analysis and prevention最新文献

{"title":"Estimating safety benefit of in-vehicle work zone safety technology alerts: A counterfactual Monte-Carlo simulation approach","authors":"Qishen Ye ,&nbsp;Yihai Fang ,&nbsp;Nan Zheng","doi":"10.1016/j.aap.2025.108014","DOIUrl":"10.1016/j.aap.2025.108014","url":null,"abstract":"<div><div>Work Zone Safety Technologies (WSTs) have exhibited great potential to improve road work zone safety by detecting safety risks and providing warnings to drivers and workers involved. Yet, it remains extremely challenging to quantify the actual safety benefits of such technologies in reducing work zone intrusion accidents, mainly due to a lack of empirical data and robust evaluation methods. This paper aims to explore the patterns of drivers’ behavioural responses when approaching work zones and estimate the safety benefits of in-vehicle WSTs. First, a VR-based driving simulation experiment was conducted to collect human behavioural data on drivers’ responses when approaching work zones in critical scenarios. Second, a Linear Mixed Effect (LME) model was developed to capture the impact of in-vehicle WST alerts and scenario criticality, i.e., speed and Time-to-Collision (TTC), on drivers’ behavioural responses. Finally, the safety benefits of in-vehicle WST alerts were estimated through counterfactual Monte-Carlo simulations of vehicle trajectories. The findings highlight the mechanism by which in-vehicle WST alerts improve driver response in various critical driving scenarios involving work zones and provide crucial evidence for future decision-making regarding the evaluation of WSTs.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"215 ","pages":"Article 108014"},"PeriodicalIF":5.7,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Examining collision avoidance behavior of distracted drivers: A correlated grouped random parameters accelerated failure time model with heterogeneity-in-means","authors":"Qikai Qu ,&nbsp;Yasir Ali ,&nbsp;Yongjun Shen ,&nbsp;Qiong Bao ,&nbsp;Md Mazharul Haque","doi":"10.1016/j.aap.2025.108016","DOIUrl":"10.1016/j.aap.2025.108016","url":null,"abstract":"<div><div>Current research mostly studied the driving behavior of distracted drivers in abrupt situations, but different types of distraction may lead to differential crash risks, particularly during collision avoidance, which has been overlooked in the literature. As such, this study investigated and compared drivers’ collision avoidance performance under different distraction conditions. Forty-four licensed drivers completed driving simulation experiments under normal driving, cognitive distraction, and manual distraction conditions. To comprehend the collision avoidance behavior under different distraction conditions, this study analyzed hazard response time, deceleration time, and collision avoidance time—critical components in avoiding secondary collisions. For these performance measures, correlated grouped random parameters accelerated failure time models were developed, considering repeated experiment design and unobserved heterogeneity. Results indicate that drivers in manual distraction took more time to respond during the hazard response phase compared to cognitive distraction. The majority of distracted drivers were observed to spend less time decelerating and avoiding collisions than in normal driving conditions, indicating a risk compensation behavior. Further, this study found that gender was associated with differential increase in collision avoidance time, with male drivers having longer collision avoidance time under manual distraction than female drivers and female drivers having longer collision avoidance time under cognitive distraction than male drivers. Overall, this study provides insights into collision avoidance behavior and aids in developing automated collision avoidance assistance systems.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"215 ","pages":"Article 108016"},"PeriodicalIF":5.7,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Critical scenarios adversarial generation method for intelligent vehicles testing based on hierarchical reinforcement architecture","authors":"Bing Zhu,&nbsp;Rui Tang,&nbsp;Jian Zhao,&nbsp;Peixing Zhang,&nbsp;Wenxu Li,&nbsp;Xinran Cao,&nbsp;Siyuan Li","doi":"10.1016/j.aap.2025.108013","DOIUrl":"10.1016/j.aap.2025.108013","url":null,"abstract":"<div><div>The widespread deployment of intelligent vehicles necessitates comprehensive testing across diverse driving scenarios. A significant challenge is generating critical testing scenarios to accurately evaluate vehicle performance. To overcome the limitations of existing methods, including inadequate diversity and validity, this study proposes an adversarial generation method grounded on a hierarchical reinforcement learning framework. This approach comprises three modules: a hierarchical scheduling module, a conflict prediction module, and a scenario evaluation module. The hierarchical scheduling module segments the testing procedure into guidance, adversarial, and exploration periods, effectively managing reward sparsity to promote varied scenario generation. The conflict prediction module employs kinematic conflict prediction and adaptive action strategies to enhance learning speed and efficiency, directing traffic entities in producing critical scenarios. The evaluation module assesses scenario validity and diversity by analyzing relative trajectories, temporal characteristics, and spatial configurations, in addition to employing a perception-limited model and replay testing to assess performance within the system’s operational limits. Experimental results using the HighD dataset in the highway environment demonstrate that the proposed method efficiently generates varied critical test scenarios, improving the collision rate and period contributions throughout the testing process. When producing an equivalent number of critical scenarios, the overall testing resource utilization decreases by 49.49% relative to the conventional Deep Q-Network method.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"215 ","pages":"Article 108013"},"PeriodicalIF":5.7,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143681062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The existence and impacts of sequential traffic conflicts: Investigation of traffic conflict in sequences encountered by left-turning vehicles at signalized intersections","authors":"Shuke Xie ,&nbsp;Zhenyu Zhao ,&nbsp;Qiangqiang Shangguan ,&nbsp;Ting Fu ,&nbsp;Junhua Wang ,&nbsp;Hangbin Wu","doi":"10.1016/j.aap.2025.108015","DOIUrl":"10.1016/j.aap.2025.108015","url":null,"abstract":"<div><div>The traffic paths of vehicles, pedestrians and non-motorized traffic at signalized intersections are complicated, and the phenomenon of not strictly obeying the right of way is frequent, which leads to more conflict points at the intersection. Vehicles are prone to Sequential conflicts while passing through intersections, which depletes attention resources, reduces response capacity, and increases accident risk. Therefore, analyzing Sequential Traffic Conflicts at intersections is a key focus of traffic safety research. The purpose of this study is to prove the existence of complex scenarios of sequential traffic conflicts, demonstrate the impact of initial conflicts on subsequent conflicts, and discuss the impact of different class variables on the severity of sequential traffic conflicts. A multi-dimensional severity assessment system was developed, and two nonlinear binary logistic regression models were established: one considering the correlation between conflicts and one assuming independence. Significant variables influencing Sequential traffic conflicts were categorized and analyzed. A typical left-turn scenario was selected for analysis. The results show that the occurrence of the initial conflict significantly influences the subsequent conflict. The model considering correlation outperforms the independent conflict model, confirming the existence of interdependence between conflicts. The severity of the first and second conflicts is negatively correlated, with the second conflict being more severe. Factors such as participant speed, group size, arrival time at the conflict zone, non-motorized vehicle direction, and left-turning vehicles’ willingness to continue crossing significantly affect conflict severity. Based on this, effective strategies for enhancing the safety of sequential traffic conflict scenarios are proposed.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"215 ","pages":"Article 108015"},"PeriodicalIF":5.7,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143673157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating machine learning and a large language model to construct a domain knowledge graph for reducing the risk of fall-from-height accidents","authors":"Zhipeng Zhou ,&nbsp;Xinhui Yu ,&nbsp;Joseph Jonathan Magoua ,&nbsp;Jianqiang Cui ,&nbsp;Haiying Luan ,&nbsp;Dong Lin","doi":"10.1016/j.aap.2025.108009","DOIUrl":"10.1016/j.aap.2025.108009","url":null,"abstract":"<div><div>Fall-from-height (FFH) accidents remain a major source of workplace injuries and fatalities. Fall protection systems (FPS) are critical for preventing falls in the work-at-height (WAH) environment. However, challenges in designing and selecting effective FPS persist across various industries, and existing tools often lack practical references. This study aims to develop an FFH-specific knowledge graph (FFH-KG) to support FPS design. By structuring accident data, the FFH-KG provides empirical insights to help designers improve FPS frameworks, aiding safety planning and decision-making. It serves as a decision support system for FPS designers and safety professionals, guiding the selection and design of appropriate protection solutions for diverse WAH scenarios. The FFH-KG was constructed using a hybrid natural language processing approach, combining manual extraction, entity recognition, text segmentation, and rule-based relation extraction. It was grounded in a schema layer (i.e., ontology) established by experts. A text-mining approach, integrating machine learning with a large language model, facilitated the categorization of fall types, refinement of WAH scenarios, and identification of fall causes, enhancing the content and applicability of knowledge graph. A total of 2,200 entities and 4,820 relationships were created based on fall protection equipment standard documents and fall-from-height accident investigation reports, forming a foundation for developing countermeasures. The retrieval performance of FFH-KG was validated through three case studies. This research has also made significant progress in intelligent safety engineering and management across industries.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"215 ","pages":"Article 108009"},"PeriodicalIF":5.7,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143673145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Examining the role of random parameters and unobserved heterogeneity in the frequency-severity of rural freeway run-off-road and fixed-object crashes: A Bayesian hierarchical-geospatial approach","authors":"Meysam Effati,&nbsp;Amirmohammad Ramezanpoor","doi":"10.1016/j.aap.2025.108005","DOIUrl":"10.1016/j.aap.2025.108005","url":null,"abstract":"<div><div>Fixed-object collisions and run-off-road (FOC-ROR) crashes are more severe and frequent in rural freeways compared to other crash types, particularly involving light vehicles. The relationship between influential factors and crash frequency-severity is complex due to unobserved heterogeneities. This study developed a comprehensive method integrating spatial autocorrelation cluster analysis and the Bayesian Hierarchical Random Parameter (BHRP) model to quantitatively examine unobserved effects and parameter uncertainties in FOC-ROR, FOC, and ROR crashes separately. The study also emphasizes segmentation length’s impact on the proposed model performance. Based on the variables of crash type, crash severity, and segment length, the proposed approach was examined in 24 scenarios, and as a result, the FOC-ROR model for 292-meter segments demonstrated the best performance. Following this, the influential variables were identified, and Kernel Density thematic maps was employed to evaluate the spatial autocorrelation of crash frequency-severity on road segments, focusing on causes of occurrence. Results confirmed unobserved factors and influential variables like young drivers (−0.047), narrow shoulder width (−0.231), and rainfall depth (0.034) affecting fatal-injury FOC-ROR crashes, while low visibility (−0.490), low air temperature (−0.433), and driver haste (0.270) influenced PDO FOC-ROR crashes. Compared to traditional methods, the proposed spatial autocorrelation approach allows transportation authorities to prioritize geometric corrections and optimize traffic safety planning, offering a cost-effective strategy for reducing crash risks on rural freeways.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"215 ","pages":"Article 108005"},"PeriodicalIF":5.7,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Safety validation for connected autonomous vehicles using large-scale testing tracks in high-fidelity simulation environment","authors":"Zheng Xu ,&nbsp;Xiaomeng Wang ,&nbsp;Xuesong Wang ,&nbsp;Nan Zheng","doi":"10.1016/j.aap.2025.108011","DOIUrl":"10.1016/j.aap.2025.108011","url":null,"abstract":"<div><div>Public concern over the implementation of Connect Autonomous Vehicles (CAVs) remains a significant issue, and safety validation for CAVs remains a critical challenge due to the limitations of existing testing methods. While real-world testing is crucial, it can be expensive, time-consuming, and potentially impractical for evaluating the operation of CAV fleets. This paper presents a comprehensive co-simulation framework integrating the fully compiled CARLA with traffic microsimulation to establish a large-scale (20 × 20 km²) testing environment for systematic CAV safety validation. The framework encompasses three key components: 1) a high-fidelity testing environment featuring diverse road geometries and dynamic conditions including weather variations and realistic traffic flows; 2) an intelligent CAV function developed through deep reinforcement learning and enhanced with utility-based connectivity strategies; 3) A sophisticated safety measurement metric that utilizes surrogate safety assessments, integrating a multi-type Bayesian hierarchical model to comprehensively evaluate risk factors and incident probabilities. The case study assessed CAV penetration rates ranging from 0 % to 100 %, identifying an optimal safety performance at a 70 % penetration rate, which resulted in an 86.05 % reduction in accident rates compared to conventional driving scenarios. This optimal safety level was effectively achieved in rural and suburban areas, where the average conflict probability was 0.4. However, in transition zones that connect high-, medium-, and low-density areas, significant traffic conflicts persisted even at this optimal penetration rate, with a conflict probability exceeding 0.7. Key results highlight critical safety patterns under optimal conditions, revealing that roundabouts and signalized intersections account for over 70 % of conflicts involving CAVs. This work advances CAV safety validation by providing a more realistic, large-scale testing environment that compensates for real-world testing limitations and allows for comprehensive safety evaluations across diverse scenarios.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"215 ","pages":"Article 108011"},"PeriodicalIF":5.7,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143641808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a framework for risky driving scenario identification, individual risk assessment, and group risk differences estimation using naturalistic driving data from the i-DREAMS project","authors":"Yanchao Song ,&nbsp;Veerle Ross ,&nbsp;Robert A.C. Ruiter ,&nbsp;Tom Brijs ,&nbsp;Muhammad Adnan ,&nbsp;Muhammad Wisal Khattak ,&nbsp;Yongjun Shen ,&nbsp;Geert Wets ,&nbsp;Kris Brijs","doi":"10.1016/j.aap.2025.107993","DOIUrl":"10.1016/j.aap.2025.107993","url":null,"abstract":"<div><div>Driver-related factors, such as driving style and traffic offenses, are key contributors to road crashes, with driving risk varying substantially among individuals. Accurate assessment of individual driving risk and identification of high-risk driver characteristics are essential to reducing road crashes. Despite numerous studies on driving risk assessment, most rely solely on the frequency of single-threshold events, making them insufficiently comprehensive. Moreover, these studies neglect the repetitive nature of driving scenarios and differences in exposure, leading to imprecise assessments when using distance traveled as a measure of exposure.</div><div>To address these shortcomings, we collected 18 weeks of naturalistic driving data from 100 participants (50 from the UK, 50 from Belgium) and developed a framework for assessing individual driving risk, consisting of three parts: (1) identification of risky driving scenarios, (2) assessment of individual driving risks, and (3) analysis of group risk differences to identify high-risk driver characteristics.</div><div>Risky driving scenarios were characterized by critical events with high risk propensity and high heterogeneity among individual driving risks. Driving scenario indicators were developed that measure risk propensity and heterogeneity, enabling risk assessments based on the probability of critical events occurring in such scenarios. Individual driving risk was measured by the weighted probability of multi-threshold events (WPMTE) in risky driving scenarios and adjusted for differences in driving exposure. WPMTE provides a comprehensive and precise assessment of individual driving risks, aiding in the identification of high-risk drivers. Finally, statistical tests revealed significantly higher risks for young drivers (19–30) compared to middle-aged (46–60) and elderly drivers (61–79), as well as higher risks for Belgian drivers compared to UK drivers.</div><div>These findings inform the development of tailored safety education and proactive interventions, promoting safer driving behaviors and reducing crash rates.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"215 ","pages":"Article 107993"},"PeriodicalIF":5.7,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143641809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Riding with distraction: Exploring the intention and behaviour of smartphone use while riding among motorcyclists in Vietnam","authors":"Ha Hoang ,&nbsp;Mehdi Moeinaddini ,&nbsp;Mario Cools","doi":"10.1016/j.aap.2025.107992","DOIUrl":"10.1016/j.aap.2025.107992","url":null,"abstract":"<div><div>The pervasive use of smartphones has significantly contributed to distracted driving, a leading cause of road traffic accidents globally. This study investigates the behavioural intentions and patterns of smartphone use while riding among motorcyclists in Vietnam, integrating the Theory of Planned Behaviour (TPB) with the Stimuli-Organism-Response (SOR) framework to encompass factors such as riding exposure and time pressure. A questionnaire survey was conducted, gathering data from 1,051 young motorcyclists. Using Partial Least Squares Structural Equation Modelling (PLS-SEM), the study identifies high levels of smartphone engagement during riding, driven primarily by Perceived Behavioural Control (PBC), which exhibited a stronger influence on behaviour than Attitudes and Social Norms. Notably, time pressure significantly enhanced the intention to use smartphones, suggesting that riding under time constraints could exacerbate the risk of distracted riding incidents. The findings highlight critical implications for road safety interventions and policy formulation, emphasising the need for targeted educational programmes and stricter enforcement measures to mitigate smartphone-induced distractions among motorcyclists at a higher risk of traffic accidents. The study contributes to understanding distracted riding behaviours in motorcycle-dominant regions, providing a foundation for future research and preventive strategies.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"215 ","pages":"Article 107992"},"PeriodicalIF":5.7,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A review on the use of top-view surveillance videos for pedestrian detection, tracking and behavior recognition across public spaces","authors":"Hongliu Li,&nbsp;Jacqueline Tsz Yin Lo","doi":"10.1016/j.aap.2025.107986","DOIUrl":"10.1016/j.aap.2025.107986","url":null,"abstract":"<div><div>The use of top-view surveillance cameras has been considered as the feature to maintain uncovered view and privacy protection in public buildings like stations and traffic hubs. This study aims to provide a comprehensive review on recent developments and challenges related to the use of top-view surveillance videos in public places. The techniques using top-view images in pedestrian detection, tracking and behavior recognition are reviewed, specifically focusing on their influence on crowd control and safety management. The setup of top-view cameras and the characteristics of several available datasets are introduced. The methodologies, field of view, extracted features, region of interest, color space and used datasets for key literature are consolidated. This study contributes by identifying key advantages of top-view cameras, such as their ability to reduce occlusions and preserve privacy, while also addressing limitations, including restricted field of view and the challenges of adapting algorithms to this unique perspective. We highlight knowledge gaps in leveraging top-view cameras for transport hubs, such as the need for advanced algorithms and the lack of standardized datasets for dynamic crowd scenarios. Through this review, we aim to provide actionable insights for improving crowd management and safety measures in public buildings, especially transport hubs.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"215 ","pages":"Article 107986"},"PeriodicalIF":5.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143600955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}