Search Results (125)

Urban traffic accidents emerge from complex interactions among traffic instability, roadway structure, environmental disturbance, and temporal dynamics, yet many existing prediction approaches still treat accident risk as a discrete classification problem over isolated observations. This study proposes a Continuous Hazard Field Intelligence Framework for Traffic Accident Emergence and Urban Safety Prediction, which models hidden urban danger as a topology-aware spatio-temporal hazard field that evolves continuously across connected transportation infrastructure. The framework integrates heterogeneous urban traffic observations, including incident records, crash data, roadway attributes, temporal cues, and contextual risk factors, into a unified hazard-aware learning pipeline. A dedicated preprocessing strategy combines topology-constrained spatial alignment, temporal hazard window embedding, risk-diffusion feature lifting, hazard-sensitive normalization, and continuous hazard surface initialization to convert fragmented event-centered observations into a smooth and learning-ready hazard representation. A structured deep learning architecture is then developed to perform spatial hazard encoding, temporal hazard evolution, continuous hazard reconstruction, and localized accident emergence prediction. Experimental evaluation was conducted on two large-scale real-world traffic safety datasets, namely the XTraffic Incident Dataset (2022–2024) with 1,441,904 records and the Motor Vehicle Collisions–Crashes Dataset with 2,026,647 records. All model configurations were evaluated under the same experimental setting, using the same dataset-specific preprocessing protocol, a 70/30 train–test split, and identical evaluation metrics. The final CHFI configuration achieves 99.12% accuracy, 98.94% precision, 98.76% recall, 98.85% F1-score, and 0.998 AUC on Dataset 1, and 98.63% accuracy, 98.41% precision, 98.16% recall, 98.28% F1-score, and 0.997 AUC on Dataset 2. Compared with the initial non-hazard-aware baseline configuration evaluated under the same data split and evaluation protocol, the final CHFI model improves the F1-score by 7.91 percentage points on Dataset 1 and 8.26 percentage points on Dataset 2. These results indicate that the proposed hazard-field formulation can improve accident-emergence prediction within the controlled experimental setting, while the reported gains should be interpreted relative to the specified baseline and evaluation design. Full article

This paper introduces the Touchard process, a flexible two-parameter stochastic framework for modeling count data that depart from the classical Poisson assumptions. In contrast to standard Poisson processes, the proposed model allows for both nonstationary and dependent increments, enabling the representation of overdispersion, underdispersion, and temporal dependence within a unified structure. The main contribution lies in extending weighted Poisson models to a stochastic-process setting through recursively defined transition probabilities associated with Touchard marginal distributions. We derive key theoretical properties, including admissibility conditions and a recursive formulation for the transition probabilities, and propose an efficient simulation algorithm. Maximum likelihood estimation is developed for parameter inference, and a likelihood ratio framework is used for model comparison. An empirical application to motor vehicle crash data illustrates the ability of the model to capture dynamic patterns that are not adequately described by classical Poisson-based approaches. Full article

Seatbelt use is well established as a life-saving measure. Nevertheless, many drivers and passengers continue to neglect seatbelt use. This study examines the risks associated with unrestrained occupants involved in motor vehicle crashes. Using data from the Fatality Analysis Reporting System from 2000 to 2018, the relative risk of fatal traffic accidents for unrestrained vehicle occupants in the United States was estimated using the maximum likelihood estimation method. The findings indicate that unrestrained passengers make up about 12% of all passengers on the road and face a roughly 4.3 times greater likelihood of fatality in severe crashes. Additionally, unrestrained drivers, whose higher risk profiles are linked not only to their lack of restraint but also to broader patterns of hazardous driving behavior, account for over 8% of all drivers and exhibit a risk approximately 5.4 times higher in causing fatal crashes compared to restrained drivers. The findings of this study reveal the prevalence and consequences of unrestrained vehicle occupants and supports ongoing efforts to promote seatbelt utilization and bolster road safety protocols. By doing so, we can alleviate the burden of preventable injuries and fatalities on individuals, families, and society at large, thus fostering a safer and more secure transportation environment for all. Full article

Over the past decade, road safety research has experienced rapid development due to the rapid expansion of large crash databases, the adoption of artificial intelligence techniques, and the demand for proactive and predictive safety solutions. This study conducts a data-driven review of recent research trends in transport safety. It focuses on main domains including crash severity analysis, human factors, vulnerable road users (VRUs), spatial modeling, and artificial intelligence applications. A systematic search of the Scopus database identified 15,599 relevant scientific papers published between 2016 and 2025. After constructing this corpus, titles, abstracts, and keywords were preprocessed using a natural language pipeline. The analysis employed BERTopic, a transformer-based topic modeling framework. The analysis identified 29 distinct research topics, further synthesized into five major thematic areas: (1) crash severity and injury analysis, (2) driver behavior and human factors, (3) vulnerable road users, (4) artificial intelligence, machine learning, and computer vision in intelligent transportation systems, and (5) spatial analysis and hotspot detection. A notable increase in publications related to artificial intelligence and machine learning has been evident since 2020. The results show a transition from descriptive, post-crash studies to integrated, multimodal, predictive analysis. Overall, the findings reveal a paradigm shift in the field. This study also identifies ethical and economic issues associated with the use of artificial intelligence in intelligent transportation systems, including data management, infrastructure requirements, system security, and model transparency. The results signify a transition from intuition-based models to explainable, spatially explicit, and data-intensive models, ultimately facilitating proactive risk assessment and informed decision-making. Full article

Background: Traumatic spinal injuries (TSI) are often associated with substantial physical burden and potential psychological consequences. Early detection of depressive symptoms may be important for improving quality of life during recovery. Despite the high prevalence of injury, unique sociocultural factors affecting mental health, and the need to optimize long-term rehabilitation outcomes, there is a lack of longitudinal assessments of depression in TSI patients in this region of the MENA (Middle East and North Africa). This study aimed to examine the occurrence of depressive symptoms following TSI over a 3-month period. Methods: A prospective cohort study was conducted to assess the occurrence of depression in TSI patients admitted between 2019 and 2022 at the Hamad Trauma Center. Conscious patients aged 18–65 years diagnosed with TSI were included. Perceived social support was assessed using the RAND Social Support Survey (Medical Outcomes Study Social Support Survey), a validated instrument measuring multiple dimensions of social support. Patient Health Questionnaire-9 (PHQ-9), a widely validated self-administered screening tool for depressive symptoms, was utilized twice: at 2 weeks and at 3 months post-trauma to evaluate early-onset depressive symptoms and their persistence or resolution over time. Results: A total of 189 TSI were included. The cohort was predominantly young individuals. The most common mechanisms of injury included falls (42.1%) and motor vehicle crashes (31.1%). The mean Injury Severity Score was 16.5 ± 8.2 and the spine Abbreviated Injury Scale score was 2.4 ± 0.7. Injuries involved cervical (32.8%), thoracic (38.1%), and lumbo-sacral (6.9%) regions. A total of 32.6% underwent spinal surgery, and 9.0% experienced neurological deficits. Most patients reported emotional and informational support (69%), and 62% reported caregiving support. At 2 weeks post-trauma, patients demonstrated mild depressive symptoms, with a mean PHQ-9 score of 4.6 ± 5.1, which decreased to 2.5 ± 4.2 at 3 months. The proportion of patients screening positive for depressive symptoms (PHQ-9 ≥ 5) decreased from 39.1% (52/133) at 2 weeks to 19.5% (26/133) at 3 months, corresponding to a 19.6% absolute reduction over the follow-up period. A subset of patients reported increased feelings of depression or hopelessness and sleep disturbances at three months compared with two weeks post-trauma. Conclusions: Patients with TSIs experience psychological distress in the early post-injury period, with a subset screening positive for depressive symptoms. Although depressive symptom scores declined over 3 months, continued psychological screening and follow-up care remain important components of comprehensive TSI management during recovery and rehabilitation. Our results should be considered cautiously because of gender-biased findings, single center data and potential attrition bias. Full article

Pedestrian and cyclist safety at urban intersections remains a critical challenge for transportation agencies, as vulnerable road users are significantly exposed to crash risks in complex traffic environments. Identifying high-risk locations and factors that contribute to crashes is essential for improving road safety. This study developed an explainable machine learning framework to predict motor vehicle-involved pedestrian and cyclist crash occurrence at urban intersections using five years of crash, geometric, operational, and socioeconomic data from a large set of urban intersections. Five supervised machine learning algorithms were trained and evaluated, including Binary Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree, and Random Forest. The evaluated models demonstrated strong predictive performance overall, with accuracies approaching 91% and high discriminative capability. In particular, the Binary Logistic Regression and Random Forest models achieved the highest area under the receiver operating characteristic curve (AUC) values of 0.961 and 0.964, respectively. To enhance transparency, SHAP values were used to quantify the contribution of predictors and examine feature effects at both the global and local levels. The results indicate that roadway hierarchy, intersection markings, and total entering volume are among the most influential determinants of crash likelihood, while socioeconomic variables exhibit weaker but interpretable effects. Full article

In recent years, cycling mobility in urban environments across Spain has grown significantly, driven by sustainability policies and behavioral shifts following the COVID-19 pandemic. However, this growth has been accompanied by an increase in accidents in urban areas, where more than 72.6% of cyclist accidents are concentrated, with large cities being the most affected. This study aims to explore and analyze the factors influencing cycling accidents in Spanish municipalities with populations exceeding 50,000, during the period of 2020–2023. A total of 24 variables were analyzed, encompassing not only innovative cyclist infrastructure network features (line connectivity), but also urban morphology and street infrastructure, weather conditions and mobility (all transportation modes). The methodological approach combines Principal Component Analysis (PCA) with two negative binomial regression models: one addressing all cycling accidents, and another focusing specifically on collisions between cyclists and motor vehicles. PCA shows the complex relations between urban features when comparing cyclist accidents among cities. The main results from the Negative Binomial analysis show that increased bicycle lane length significantly reduces cycling accident risk, while higher intersections with traffic signal density are associated with a greater likelihood of car–bicycle crashes. These findings emphasize the importance of cycling infrastructure provision and intersection design and regulation as key policy levers for improving urban cyclist safety. Future research should seek to corroborate these results through micro-spatial analyses and accident geolocation, assessing their severity and accounting for more detailed data on cycling infrastructure. Finally, the results’ discussion underscores the importance of implementing holistic urban mobility strategies that prioritize cyclist safety. Full article

Background: Although orbital fractures are common in trauma care, age-specific mechanisms and admission physiology-based risk stratification have not been systematically characterized. This study aimed to identify age–mechanism interaction patterns and develop an admission-based physiological risk score for orbital fracture patients. Methods: This retrospective cohort study analyzed 41,464 adult orbital fracture patients from the National Trauma Data Bank (2018–2020). A three-component physiological risk score was developed using admission vital signs: severe hypotension (<90 mmHg, 2 points), tachycardia (>100 bpm, 1 point), and severe traumatic brain injury (GCS ≤ 8, 1 point). Risk stratification performance was validated against composite adverse outcomes. Results: Distinct age–mechanism patterns emerged: 74.0% of elderly patients (≥65 years) sustained falls, while young adults demonstrated a bimodal distribution with motor vehicle crashes (31.2%) and violence (28.4%). Violence-related injuries occurred in younger patients (40.3 vs. 55.0 years) but had lower injury severity scores (10.0 vs. 14.4) and mortality (2.8% vs. 5.2%) than accidental mechanisms. High-/critical-risk patients (8.4% of the cohort) had 16.2% mortality versus 2.1% in stable patients. Complex facial injuries demonstrated 11-fold higher mortality (7.7% vs. 0.7%). The physiologic risk score achieved AUC 0.79 (95% CI: 0.78–0.80). Conclusions: Age–mechanism interactions revealed distinct bimodal injury patterns in young adults. Admission physiologic parameters effectively identify 8.4% of patients requiring intensive resources, while violence-related injuries paradoxically demonstrate better outcomes than accidental mechanisms. Full article

Motor vehicle crashes are a persistent cause of unintentional deaths in the United States. Scholarship on how manmade interventions and natural phenomena interact to effectuate such calamitous outcomes is longstanding. One manmade intervention of interest in the literature is daylight saving time (DST). Unfortunately, results on how the natural phenomena attributable to DST interact with driver behavior are inconsistent. To advance knowledge on DST-safety interactions, this study adopts a multilevel model approach to fatal motor vehicle crash outcomes in the contiguous United States. Results from a national analysis contextualize results from zonal analyses to unmask within- and between-time zone differences in DST-safety interactions. In the national analysis, motor vehicle crash fatalities decrease somewhat during DST (−0.10%). In the zonal analyses, motor vehicle crash fatalities decrease more so in the Central and Eastern time zones (−2.00% and −2.00%, respectively), but increase somewhat in the Pacific and Mountain time zones (+0.30%) during DST. The spatiotemporal context of the national analysis highlights specific policy implications from the zonal analyses to decrease the lethality of motor vehicle crashes. Specifically, interdictions to target alcohol and/or drug involvement in the northern latitudes of the Pacific and Mountain time zones during DST, the Central time zone at dawn or dusk before or after DST, and the northern latitudes in the Eastern time zone before or after DST are important. Generally, national DST-safety benefits mask zonal DST-safety costs in the Pacific and Mountain time zones. Full article

Traumatic liver injury remains a significant contributor to trauma-related morbidity and mortality worldwide. In Saudi Arabia, motor vehicle accidents (MVAs) are the predominant mechanism of injury, particularly among young adults. This study aimed to evaluate the clinical characteristics, management strategies, and outcomes of patients with liver trauma over a ten-year period at a tertiary academic level-one trauma center. A retrospective cohort study was conducted from January 2015 to December 2024. All adult patients (aged 18–65 years) who sustained blunt or penetrating liver injuries and underwent a pan-CT trauma survey were included. Demographic data, Injury Severity Scores (ISSs), imaging timelines, management approach, and clinical outcomes were analyzed. Statistical analysis was performed using JASP software with a significance threshold set at p < 0.05. A total of 111 patients were included, with a mean age of 33 ± 12.4 years; 78.1% were male. MVAs were the leading cause of injury (75.7%). Most patients (80.2%) had low-grade liver injuries and received non-operative management (NOM), with a high NOM success rate of 94.5%. The median time to CT was 55 ± 64 min, and the mean time to operative or IR intervention was 159.9 ± 78.8 min. Complications occurred in 32.4% of patients, with ventilator-associated pneumonia (19.8%) being most common. The overall mortality was 6.3%. Multivariate analysis revealed that shorter time to CT significantly reduced mortality risk (OR = 0.5, p < 0.05), while a positive e-FAST result was strongly associated with increased mortality (OR = 3.3, p < 0.05). Higher ISSs correlated with longer monitored unit stays (ρ = 0.3, p = 0.0014). Traumatic liver injuries in this cohort were predominantly low-grade and effectively managed conservatively, with favorable outcomes. However, delays in imaging and operative intervention were observed, underscoring the requirement for streamlined trauma workflows. These findings highlight the requirement for continuous trauma system improvement, including protocol optimization and timely access to imaging and surgical intervention. Full article

Children may suffer knee injuries due to motor vehicle crashes, sports, and falls. Additionally, children can suffer from rheumatic, neurological, musculoskeletal, and neuromuscular disorders which restrict joint movement. These types of injuries and disorders often result in knee joint impairment, thereby affecting joint mobility. Understanding the range of motion (ROM) of the pediatric knee is vital in diagnosing, examining, and treating these injuries and disorders. This study was undertaken to establish normative values for passive (PROM) and active (AROM) range of motion of the pediatric knee and to examine the effects of anthropometric and demographic factors on knee joint ROM. Normative reference values for both passive and active knee ROM were established for 295 children in the United Arab Emirates (Arab and South Asian ethnicity). The subjects’ PROM averaged 131.2° (117.2°, 140.2°) for boys and 132.8° (120.9°, 140.3°) for girls. Similarly, the observed PROM for children was 132.2° (118.6°, 141.2°), versus 130.8° (119.9°, 139.3°) for adolescents. Conversely, the subjects’ AROM averaged 129.3° (118.8°, 137.9°) for boys and 130.5° (120.9°, 137.4°) for girls. The observed AROM averaged 130.2° (119.5°, 137.8°) for children and 128.6° (121.5°, 137.4°) for adolescents. Significant differences in knee ROM based on ethnicity were identified. Additionally, significant correlations were observed between anthropometric factors and knee joint ROM. The gender and age-based normative values established in this study can be used in medical and vehicle safety analyses of knee injuries sustained by children as well as in the evaluation of knee joint impairments due to rheumatic, neurological, musculoskeletal, and neuromuscular disorders, thereby improving the outcomes of knee injuries and the treatment of joint impairments in children. Full article

The human neck is highly vulnerable in motor vehicle crashes, and cervical spine response data are essential to improve injury prediction tools (e.g., crash test dummies, human body models). This feasibility study aimed to implement the use of pressure sensors in whole-body post-mortem human subject (PMHS) cervical spine intervertebral discs (IVDs) to confirm the feasibility and repeatability of cervical IVD pressure response to biomechanic research. Two fresh frozen whole-body PMHSs were instrumented with miniature pressure sensors (Model 060S, Precision Measurement Company, Ann Arbor, MI, USA) at three cervical IVD levels (C3/C4, C5/C6, and C7/T1) using minimally invasive surgical insertion techniques. Each PMHS underwent three quasistatic motion test trials, and each trial included multiple head/neck motions (i.e., gentle traction, flexion/extension, lateral bending, axial rotation, and forced tension/compression). Results showed marked pressure differences between both the cervical level assessed and the motion undertaken as well as successful intra-subject repeatability between the three motion trials. This study demonstrates that changes in cervical IVD pressure are associated with motion events of the cervical spine. Cervical IVD response data could be utilized to assess and supplement the characterization of the head/neck complex motion, and data could facilitate the continued improvement of injury prediction tools. Full article

Complete Streets (CS) are defined as streets that accommodate all types of users, regardless of ability, safely and equitably allowing for the presence of pedestrians, bicyclists, transit users, and vehicle drivers to share the roadway. Several agencies have developed CS policies as a vital strategy to create more inclusive and accessible environments for all road users. CS are an efficient way to support the implementation of a multimodal transportation system, providing alternatives to car-oriented roadway designs. The Kentucky Transportation Cabinet recently developed the Complete Streets, Roads, and Highways Manual, aiming to implement a safe and equitable transportation system throughout the state. However, there is a need to evaluate the benefits of CS regarding their safety performance. This study aims to present crash data and summary statistics for CS projects that have been completed in Kentucky. The methodology involves a comparative analysis of safety data collected before and after the implementation of these projects. The results reveal that CS can be an effective approach to improve safety for all road users, including vulnerable and motor vehicle users. The findings also contribute to the existing knowledge on CS, offering insights into their impact on safety performance. Given that transportation agencies continue to prioritize sustainable and inclusive transportation solutions, the outcomes of this study will provide practical guidance for urban planners, policymakers, and transportation engineers seeking evidence-based solutions for creating safer roads. Full article

The rapid adoption of electric vehicles coupled with high-voltage battery packs increases safety concerns, especially during crashes. Such safety concerns can be addressed with voltage discharge strategies to reduce the voltage of the DC-bus capacitor. One discharge strategy involves injecting a negative current into the traction motor to dissipate the DC-bus energy through motor windings. One issue with strategies involving the injection of negative d- and q-axis currents into the motor to reduce the speed of the motor and discharge the capacitor quickly is the observation of a large voltage surge due to the energy recovery from the motor. A discharge strategy found in the literature deals with this with piecewise calculation of d- and q-axis currents based on the motor speed. This study investigates this strategy and provides recommendations for improvement and future work with key insights. Using MATLAB Simulink 2023b, this strategy is analysed and compared with other discharge strategies. In certain circumstances with a high-rotor-inertia motor, the performance of the strategy was not deemed adequate. In essence, the lack of testing of discharge strategies on multiple powertrains is deemed as one potential cause of such problems which needs to be addressed in future research. Full article

Roadway mortality increased during COVID-19, reversing a multi-decade downward trend. The Fatality Analysis Reporting System (FARS) was used to examine contributing factors pre-COVID-19 and in the COVID-19 era using the five pillars of the Safe System framework: (1) road users; (2) vehicles; (3) roadways; (4) speed; and (5) post-crash care. Two study time periods were matched to control for seasonality differences pre-COVID-19 (n = 1725, 1 April 2018–31 December 2019) and in the COVID-19 era (n = 2010, 1 April 2020–31 December 2021) with a three-month buffer period between the two time frames excluded. Four of the five pillars of the safe system had road safety indicators that worsened during the pandemic. Mortality was 19.7% higher for motor vehicle occupants and 45.1% higher for riders of motorized two-wheeled vehicles. In adjusted analyses, failure to use safety equipment (safety belts/helmets) was associated with 44% higher mortality. Two road user groups, non-motorized bicyclists and pedestrians, did not contribute significantly to higher mortality. Urban roadway crashes were higher compared to rural crashes. Additional scientific inquiry into factors associated with COVID-19-era mortality using the Safe System framework yielded important scientific insights to inform prevention efforts. Motorized two-wheeled vehicles contribute disproportionately to pandemic-era higher mortality and constitute an emerging road safety issue that deserves further attention. Full article