Search Results (98)

Rapid urbanization and increasing traffic density have increased the crash risk of vulnerable road users (VRUs), particularly pedestrians and cyclists. Meanwhile, the conventional statistical models have difficulties in capturing the nonlinear and complex nature of crash data, limiting their safety analysis effectiveness. This study utilized advanced Gradient Boosting machine learning and integrated it with SHapley Additive exPlanations (SHAP) using five years of crash data from Michigan, USA, employing a two-tiered modeling design consisting of a 4-class joint structure and binary subset frameworks. Rigorously evaluated using 10-fold stratified cross-validation to predict crash severity for VRUs, the CatBoost model had better predictive performance (AUC = 0.917) than LightGBM, Random Forest and the traditional Logistic Regression models. The analysis further indicated that prior crash actions, particularly risky crossing behaviors, are the most significant determinants of injury severity for both user groups. However, the pedestrian crash severity is strongly associated with lighting conditions and speed limits, while cyclist crash severity is more heavily influenced by intersection involvement and roadway geometry. Moreover, SHAP interaction analysis showed that the speed effect on severity significantly increases when it interacts with hazardous actions or poor visibility. The findings provide a critical insight into the implementation of effective measures and infrastructure improvements to increase the safety of VRUs. Full article

Pedestrian head injuries represent one of the most severe consequences of vehicle–pedestrian collisions, primarily resulting from the impact between the pedestrian head and the vehicle hood or windshield region. Active bonnet systems have been developed to mitigate injury severity by increasing the clearance between the hood and rigid engine components during impact; however, their effectiveness strongly depends on rapid impact detection and timely deployment. This study proposes an approach for analysing pedestrian impact dynamics and evaluating the design performance of a contact-triggered active bonnet system using MATLAB/Simulink and Simscape Multibody. The pedestrian–vehicle interaction is reproduced using spatial contact force models, while the bonnet deployment is initiated through a contact-based trigger mechanism coupled with a simplified actuator integrated into the hood hinge. The model was experimentally validated using controlled pedestrian impact tests at 17 km/h and 29 km/h, including frame-by-frame kinematic analysis and measured head acceleration signals. Additional simulations were performed at multiple vehicle velocities with and without bonnet deployment to evaluate the influence of impact configuration and pedestrian trajectory on head injury severity. The results indicate that the active bonnet system can reduce peak head acceleration and HIC15 values under several investigated impact conditions. The comparative simulations further show that the protective effect is influenced by pedestrian positioning and head trajectory relative to the vehicle front-end geometry, with higher effectiveness when the head impact remains within the deformable bonnet region. Full article

This study presents a comprehensive multidimensional analysis of pedestrian accidents in Amman, Jordan, from 2014 to 2023. By integrating spatial, temporal, and statistical techniques, the research identifies critical risk patterns to inform evidence-based safety interventions. Characterizing a decade-long database of 14,821 cases, the study utilizes radar graphs, Kernel Density Estimation (KDE), and DBSCAN cluster analysis to delineate high-risk zones and temporal peaks. Temporal findings indicate that Thursdays recorded the highest accident frequency (2382 cases), with peak occurrences between 17:00 and 23:00. Spatial clustering identified five significant high-risk zones, with Central Amman emerging as the primary critical area. The study’s novelty lies in being the first in the Jordanian context to bridge accident frequency with severity mechanisms by integrating advanced spatial clustering and KDE with a robust Ordered Logit Model. Severity analysis reveals that while 59.34% of incidents resulted in minimal injuries, fatalities accounted for 5.02%. The model demonstrates that injury outcomes are systematically associated with traffic dynamics and behavior rather than environmental factors. Speed-related driver error was identified as the strongest predictor of severe outcomes (OR = 81.3). Significant dependencies were confirmed between vehicle category and road type (χ² = 2182.20, p < 0.001), lighting and road surface (χ² = 76.21, p < 0.001), and vehicle type and lighting (χ² = 148.52, p < 0.001). The study proposes a multi-layered framework combining site-specific nodal improvements with corridor-level strategies to enhance urban safety in Amman City. Full article

Background and Objectives: Courier-operated motorcycles and mopeds have become increasingly visible in urban traffic, raising concerns about injuries among both couriers and pedestrians struck by courier-operated vehicles. The study period coincided with the COVID-19 pandemic; however, this study was not designed to evaluate the effect of the pandemic on courier-related injuries. This multicenter retrospective study aimed to describe hospital-based injury patterns, injury severity, treatment requirements, complications, and mortality among selected courier-related casualties, including motorcycle couriers and pedestrians struck by courier-operated motorcycles or mopeds. Materials and Methods: This retrospective multicenter observational study included courier-related traffic casualties identified between 1 March 2020, and 1 June 2022, through nine hospitals in İstanbul and Ankara and, for fatal courier cases, linked emergency medical service and hospital records. The primary clinical cohort consisted of injured couriers and pedestrians evaluated or treated at participating hospitals. Linked prehospital and early fatal courier cases were analyzed separately for mortality-related and mechanism-specific fatality analyses. Injury severity was assessed using the New Injury Severity Score. Treatment was classified as conservative or surgical, including both fracture fixation and soft-tissue procedures. Results: A total of 857 courier-related traffic casualties were identified, including 491 couriers and 366 pedestrians. Among couriers, 111 fatal cases were verified through linked records. Clinical treatment and follow-up analyses were restricted to 380 hospital-treated surviving couriers and 366 pedestrians with available clinical records. In this selected hospital-treated courier cohort, multiple fractures, open fractures, higher injury severity scores, surgical treatment, and complications were more frequent than among pedestrians. All hospital-treated surviving couriers included in the orthopedic trauma cohort underwent surgery, reflecting the orthopedic trauma-based case-identification process, whereas most pedestrians were treated conservatively. Conclusions: Among this selected hospital-based cohort, courier casualties identified through hospital, trauma referral, emergency, forensic, and linked fatal-event records showed a more severe clinical profile than pedestrians evaluated after being struck by courier-operated motorcycles or mopeds. These findings should be interpreted as hospital-based injury-severity patterns rather than population-level estimates of accident incidence, relative injury risk, or public health burden. Full article

This paper proposes a Machine Learning (ML) framework designed to attribute liability between drivers and pedestrians in traffic crashes. This study applies classification algorithms and interpretability techniques to analyze judicial rulings related to pedestrian crashes in Badajoz, Spain, from 2015 to 2024. The primary objective is to identify recurring crash patterns and determine liability levels for the parties involved. Several classification algorithms were evaluated, including Support Vector Machines (SVM), Neural Network (NN), Decision Trees (DT), Boosted Trees (BT), Naïve Bayes (NB), Random Forest (RF), K-Nearest Neighbors (K-NN), and Logistic Regression (LR). Among them, the quadratic-kernel SVM achieved the highest overall performance. To address the severe class imbalance of the data, stratified k-fold cross-validation and the Synthetic Minority Oversampling Technique (SMOTE) were applied to enhance the robustness and generalization capability of the model. A multiclass classification framework was implemented, and SHAP (SHapley Additive exPlanations) was integrated to improve interpretability by quantifying the contribution of each feature to the model’s predictions. The analysis identified critical factors that play a significant role in determining liability outcomes: driver license status, crash location, lighting conditions, reaction time, and the presence of drugs or alcohol. This research aims to contribute to the legal domain. While most existing studies have focused on predicting injury severity, few have addressed liability attribution. This is a multifactorial task that requires a comprehensive analysis of judicial decisions. The results demonstrate that machine learning-driven liability attribution can support judicial decision-making and provide valuable insights for the development of proactive urban traffic safety strategies. Full article

Road traffic injuries represent one of the most critical public health challenges in the Gulf region. Predicting traffic accident severity is therefore a critical component of evidence-based road safety management. In this study, we develop machine learning frameworks for predicting traffic accident severity using Qatar’s national dataset (2020–2025), addressing extreme class imbalance and interpretability. A dataset of 588,023 accident records was systematically preprocessed from 1,000,500 raw reports. We compare three approaches: multi-class (four severity levels), binary (Safe vs. Severe), and cascaded two-stage (combining both). Six classifiers were evaluated across two encoding methods and three balancing strategies. Systematic hyperparameter tuning with 5-fold stratified cross-validation was performed for all models. The binary LightGBM classifier achieved BA = 71.04%, AUC-ROC = 0.772, Sensitivity = 61.03%, and Specificity = 81.05%, demonstrating superior performance over multi-class approaches. Temporal validation on 2025 data (trained on 2020–2024 data) supported good temporal generalization. Analysis of 10,000 test instances identified the time period as the dominant predictor of accident severity. The binary LightGBM framework provides an interpretable and effective approach for severe accident identification and risk prioritization, with SHAP findings supporting targeted temporal enforcement and pedestrian safety as evidence-based policy priorities. Full article

This study investigated injury severity in 18,528 police-reported vehicle-to-pedestrian crashes involving elderly pedestrians in legally classified local areas of South Korea during 2012–2021. Injury severity was coded into four ordered categories: fatal, serious, minor, and reported injury. To stabilize scenario extraction from a categorical crash database, an integrated screening workflow was applied, including near-zero-variance filtering, redundancy control among overlapping roadway encodings, representative-variable selection within redundant groups, and chi-square association checks. Classification and regression tree (CART) modeling was then used to identify rule-based combinations of environmental, roadway, driver, pedestrian, and vehicle factors associated with elevated severity, while tree complexity was controlled through cost-complexity pruning and 10-fold cross-validation. A scenario-based sensitivity analysis was further conducted to evaluate counterfactual shifts in severity distributions under targeted control of key conditions within representative high-risk scenarios. The results showed that severe outcomes were concentrated in stacked-risk combinations rather than in single factors alone. A dominant pathway involved nighttime conditions combined with maneuver-related driving contexts and speeding-related violations. High-fatality scenarios persisted even when speed-related predictors were excluded, underscoring the roles of nighttime exposure, visibility limitations, conflict-prone roadway settings, heavy-vehicle involvement, and pedestrian exposure behaviors. The proposed framework translates administrative crash records into concise, operationally interpretable scenarios and intervention-relevant evidence for local-area safety. Full article

Rapid urbanization and increasing traffic volumes necessitate effective road safety measures, particularly in metropolitan areas. Enhancing road safety is a fundamental pillar of social sustainability as it directly reduces the socio-economic burden of traffic accidents and promotes resilient urban environments. This article analyzes the impact of infrastructural traffic-calming devices on road safety parameters using a GIS-based method. This study provides a quantitative tool for monitoring and measuring the effectiveness of sustainable transport infrastructure. The study examines six different types of devices across 44 locations within the GZM Metropolis, Poland, utilizing official police data (Accident and Collision Records System—SEWIK) from a period of two years before and two years after implementation. The primary parameters analyzed include the frequency of incidents, the severity of injuries, and the structure of accident types. The results demonstrate a substantial positive association following the interventions, with an average 41.33% reduction in road incidents across all tested devices. Specifically, speed bumps proved most effective, reducing incidents by over 66%. However, the analysis revealed a critical anomaly: While pedestrian refuge islands decreased the overall number of minor injuries, they correlated with an increase in the number of severe injuries, suggesting a need for careful consideration. Furthermore, the study confirms a positive shift in the structure of incidents, notably a substantial decrease in rear-end and side-impact collisions. The findings offer practical evidence for evidence-based urban policies, contributing to the development of safe, inclusive, and sustainable transport systems in line with global sustainability goals. Full article

Motorcyclists face a disproportionately high risk of severe injury or death compared to other road users, highlighting the need for intelligent rider assistance technologies. This paper presents an initial, modular, and interpretable AI pipeline that generates context-aware safety advice from first-person motorcycle videos with practical inference latency suitable for on-device deployment, framing large language models as interpretable cognitive support agents for motorcycle safety. The system integrates lightweight perception and reasoning components to emulate the function of an Advanced Rider Assistance System (ARAS). Video frames are processed at 1 FPS using Pixtral, a Mistral-based multimodal large language model (MLLM), to produce descriptive scene captions, while YOLOv8 identifies key objects such as vehicles, pedestrians, and road hazards. A Mistral-small language model then fuses this information to generate concise, imperative safety tips. Preliminary evaluations on publicly available motorcycle POV datasets demonstrate promising performance in terms of contextual accuracy, interpretability, and scalability, suggesting potential for real-world deployment in low-resource or embedded environments. The proposed framework offers interpretable, context-aware safety assistance that is particularly valuable for young and newly licensed riders during the transition from supervised training to independent riding, where real-time hazard interpretation support is most needed. Full article

Thailand’s Western New Year and Songkran festivals witness a surge in traffic crashes due to increased travel volume. This study explores risk factors influencing crash injury severity during these holidays (2017–2019). Crash data is analyzed using both the Random Parameters Ordered Logit Model with Means Heterogeneity (RPOLHM) and machine learning techniques (Multilayer Perceptron (MLP), Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), Random Forest). Crash severity is categorized as property damage only (PDO), minor injury, and severe/fatal injury. The results reveal that factors like motorcycle or pedestrian involvement, adverse weather, speeding, drunk driving, fatigue, nighttime conditions, improper overtaking, and urban location all significantly increase the risk of severe/fatal crashes. Notably, the XGBoost model outperforms both RPOLHM and other machine learning methods, achieving a validation accuracy of 83.8%. While machine learning approaches demonstrate superior predictive capability, RPOLHM provides interpretable coefficient estimates and marginal effects essential for understanding causal mechanisms. This complementarity suggests that concurrent application of both paradigms offers comprehensive insights: machine learning for prediction-oriented objectives and econometric models for policy formulation. These findings provide valuable guidance for policymakers, highway engineers, and researchers to develop targeted road safety interventions during these high-risk periods. Full article

As the deployment of Automated Driving Systems (ADS) and Advanced Driver Assistance Systems (ADAS-L2) expands, understanding their real-world safety performance becomes essential. This study examines the severity and contributing factors of crashes involving vehicles equipped with ADS and ADAS-L2 technologies using NHTSA data. Using machine learning models on crash datasets from 2021 to 2024, this research identifies patterns and risk factors influencing injury outcomes. After data preprocessing and handling missing values for severity classification, four models were trained: logistic regression, random forest, SVM, and XGBoost. XGBoost outperformed the others for both ADS and ADAS-L2, achieving the highest accuracy and recall. Variable importance analysis showed that for ADS crashes, interactions with other road users and poor lighting were the strongest predictors of injury severity, while for ADAS-L2 crashes, fixed object collisions and low light conditions were most influential. From a policy and engineering perspective, this study highlights the need for standardized crash reporting and improved ADS object detection and pedestrian response. It also emphasizes effective human–machine interface design and driver training for partial automation. Unlike previous research, this study conducts comparative model-based evaluations of both ADS and ADAS-L2 using recent crash reports to inform safety standards and policy frameworks. Full article

This study presents a comprehensive statewide analysis of pedestrian-involved crashes recorded in Tennessee between 2002 and 2025. We evaluated the influence of roadway, traffic, environmental, and socioeconomic factors on pedestrian crash frequency and severity with substantial components focused on lighting impacts including dark and nighttime. A multi-method analytical framework was implemented, combining descriptive statistics, non-parametric tests, regression analysis, and advanced machine learning techniques including the Adaptive Neuro-Fuzzy Inference System (ANFIS) and the gradient boosting model (XGBoost). Results indicated that dark and nighttime conditions accounted for a disproportionate share of severe crashes—fatal and serious injuries under dark conditions reached over 40%, compared to less than 20% during daylight. The statistical tests revealed statistically significant differences in both total injuries and fatalities between low-speed (≤35 mph) and higher-speed (40–45 mph) corridors. The regression result identified AADT and the number of lanes as the strongest predictors of crash frequency, showing that greater traffic exposure and wider cross-sections substantially elevate pedestrian risk, while terrain and peak-hour traffic exhibited negative associations with severe injuries. The XGBoost model, consisting of 300 trees, achieved R² = 0.857, in which the SHAP analysis revealed that AADT, the roadway functional class, and the number of lanes are the most influential variables. The ANFIS model demonstrated that areas with higher population density and greater proportions of households without vehicles experience more pedestrian crashes. These findings collectively establish how pedestrian crash risks are correlated with traffic exposure, roadway geometry, lighting, and socioeconomic conditions, providing a strong analytical foundation for data-driven safety interventions and policy development. Full article

Aim: Older adult pedestrians are at greater risk of severe injuries than younger pedestrians due to gradual physical changes and coexisting medical conditions. This leads to longer hospital stays, increased mortality risk, and higher inpatient costs. Focusing on the aging population, this study explores the characteristics and injury profiles of pedestrian crossing accidents in the capital city of Bern, Switzerland. Methods: Our retrospective cohort study comprised adult patients admitted to our ED between 1 January 2013 and 31 December 2023, as crossing (or zebra crossing)-related pedestrian victims. Two cohorts were formed on the basis of age < 65 and ≥65 years and compared according to the setting of the accident, type, pattern of the injury, and clinical outcomes (short-term mortality, ICU/hospital length of stay). Results: Of a total of 124 patients, 31.5% (n = 39) of patients were elderly (65+ group). In contrast to the younger patients, the aging population was predominantly admitted as inpatients (64.1% vs. 35.3%, p = 0.001) and was hospitalised in the intensive care unit (20.5% vs. 6%, p = 0.020). Older patients were more likely to be polytraumatised (41% vs. 11.8%, p = 0.001) and to have been tossed or hurled than patients under 65 years (75% vs. 47.3%, p = 0.016). Fractures of the upper extremities (17.9% vs. 4.7%, p = 0.016), pelvis (30.8% vs. 9.4%, p = 0.003), and thoracic spine (12.8% vs. 2.4%, p = 0.019) were significantly more common in the elderly population. Intracranial haemorrhage (35.9% vs. 17.6%, p = 0.026), abdominal trauma (17.9% vs. 5.9%, p = 0.035), and relevant vessel damage (30.8% vs. 3.5%, p < 0.001) were also significantly higher in geriatric patients. Trauma indices were slightly more increased in the older population than in the younger group (ISS; p = 0.004 and AIS > 2 of chest and thoracic spine; abdomen, pelvic contents, and lumbar spine; extremities & bony pelvis p < 0.05). The 65+ group had a longer length of hospital stay (p = 0.001) and ICU stay (p = 0.002). A hospital stay longer than 7 days was also significantly more common in elderly individuals (p = 0.007). In-hospital (15.4% vs. 1.2%, p = 0.001) and 30-day mortality (17.9% vs. 1.2%, p < 0.001) were significantly higher in patients over 65 years of age. Conclusion: In our study, the impact of pedestrian crossing accidents was more severe in the elderly, as indicated by the severity of injuries, hospitalisation rate, longer length of hospital and ICU stays, and higher mortality rates. These findings underline the importance of developing tailored strategies to reduce crosswalk accidents and to optimise management approaches for these vulnerable patients. Full article

Background/Objectives: Due to its potent local anesthetic and vasoconstrictive properties, cocaine is sometimes used in otolaryngologic surgical interventions. However, cocaine topical administration is not always adequately documented by practitioners, which can lead to serious legal consequences, particularly in the context of drug-impaired driving (DUID) investigations. This study retrospectively analyzes five road accident cases where cocaine was detected in biological samples after medical interventions. Case descriptions: Following pedestrian–car, or car–car accidents, five distinct patients aged between 30 and 84 years underwent maxillofacial surgery due to significant injuries. Given the severity of the accident and the circumstances, the police requested blood toxicological analysis to determine whether the patients were under the influence of psychoactive substances at the moment of the accidents. Results: The five cases described in this manuscript had blood cocaine concentrations exceeding the Swiss legal limit for drivers (15 µg/L). Since no information was initially provided about the medical use of cocaine after the crash, recreational use of cocaine was suspected. However, subsequent investigations confirmed that the cases involved medical administration. Conclusions: After sinonasal procedures involving the topical application of cocaine, patients may yield positive results on urine and blood drug tests, potentially resulting in serious legal repercussions, including the withdrawal of their driving license. Therefore, practitioners should thoroughly document the medical use of topical cocaine, particularly in DUID cases. These results also raise questions about the benefit–risk ratio of such use, considering that alternatives exist. Full article

With declining physical functions, elderly pedestrians face a significantly higher risk of severe injuries and fatalities in traffic accidents. This study investigates the factors influencing injury severity among elderly pedestrians using traffic accident reports collected by the Shaanxi Chang’an University Traffic Accident Evidence Identification Center, covering nationwide cases from 2023 to 2024. By analyzing 2351 accident reports involving pedestrians aged 60 and above, 31 feature variables closely related to accident severity were selected to build a predictive model based on the XGBoost algorithm. Additionally, the SHAP method was employed to perform feature attribution analysis on the model’s key variables. The experimental results show that: (1) the model achieved 86% accuracy, 83% precision, 87% recall, and an F1 score of 85%, demonstrating the reliability of XGBoost in predicting injury severity among elderly pedestrians. (2) Global analysis identified collision speed, injury location, and driver awareness as the main factors influencing injury severity. However, the key factors differ across accidents of different severity levels. (3) The effect of the same factor also varies by severity level. For example, driver awareness reduces the likelihood of minor injuries but has less impact on severe injuries or fatalities. This study provides a theoretical foundation for developing traffic safety policies targeting elderly pedestrians and contributes to effectively reducing the severity of injuries in elderly pedestrian traffic accidents. Full article